Seasonal Weather Pattern Prediction From Enso Indices Using Machine Learning

Seasonal Weather Pattern Prediction From Enso Indices Using Machine Learning | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Seasonal Weather Pattern Prediction From Enso Indices Using Machine Learning M. Mohsin, T. Ghosh, F. Akter, S. Sarkar, Md. R.A. Mullick This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7673222/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 13 You are reading this latest preprint version Abstract The accurate prediction of seasonal weather patterns holds significant importance in supporting agriculture, disaster management, and economic planning in Bangladesh. However, the non-linear characteristics of weather and climatic patterns makes it quite challenging. Recently, the significant impact of El Nino-Southern Oscillation (ENSO) indices on regional climate variability have increasingly been recognized. This study investigates the correlation between nine ENSO indices and both temperature and rainfall patterns across Bangladesh and also evaluates the effectiveness of machine learning (ML) models in predicting these weather variables. Historical monthly data from 29 meteorological stations, spanning 1977 to 2022, were analyzed. Six supervised ML models—Random Forest (RF), Decision Tree (DT), K-Fold Cross-Validation (KFCV), XGBoost (XGB), Linear Regression (LR), and K-Nearest Neighbors (KNN) were applied. Performance was evaluated using R² score, Mean Absolute Error (MAE), and Root Mean Square Error (RMSE). Results revealed that ENSO indices have a notable impact on climate parameters in Bangladesh. Among these models, XGB achieved the highest R² scores for temperature prediction, with values of 0.8824 (T max ), 0.9706 (T min ), and 0.9559 (T avg ). RF and KFCV also showed strong performance, with RF achieving R² values of 0.8770 (T max ), 0.9699 (T min ) and 0.9531 (T avg ) and KFCV achieving R² scores of 0.8606 (T max ), 0.9619 (T min ), and 0.9438 (T avg ). Rainfall prediction, however, yielded lower accuracy, with RF recording the highest R² of 0.6273. The study highlights the impact of ENSO indices and concludes that XGB, RF, and KFCV are highly effective in modeling seasonal climate patterns influenced by ENSO. Seasonal weather patterns prediction ENSO Supervised machine learning Temperature Rainfall Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 Figure 8 Figure 9 Figure 10 Figure 11 Figure 12 1. Introduction Weather describes the short-term state of the atmosphere at a given place and time, whereas climate is the long-term (e.g. 30-year) average of those weather conditions (Amin & Mourshed, 2024 ). Weather events impact people’s everyday lives and so on the society; accurate weather forecasts, therefore is essential. A slight change in the weather pattern can have a significant impact on temperature and precipitation, which in turn can affect infrastructure, agriculture, water supply management, hydropower generation, fisheries, industry, health, everyday life, and the livelihoods of millions of people each day (Ehsan et al., 2023a ). Meteorologists use complex numerical models to predict the weather by solvpageing the equations of atmospheric motion. In recent decades, the weather models have gained a substantial improvement and a 7–10 day forecast now is far more reliable than a 4-day forecast of 20 to 30 years ago. However, even the best models often face some fundamental limits. A small error in a 7–10 day forecast can become a large error in a seasonal forecast (Pinheiro & Ouarda, 2025 ). Hence, the weather prediction in practical typically does not exceed about two weeks. To partially compensate the issue, forecasts are often run as large ensembles of slightly varied simulations (Monte Carlo method), nonetheless this is computationally expensive (Pinheiro & Ouarda, 2025 ). In short, deterministic weather forecasts beyond about 14 days are generally unreliable. On the other hand, if the pattern of the seasonal weather, the one to two season ahead of the current can be foreseen with a fair degree of accuracy, it can save resources and lives. Community can prepare for any extreme natural events, and make wise decisions in agricultural, sports, and many other areas of lives (Islam et al., 2016 ). In Bangladesh, almost 75 to 80% of yearly rainfall falls during the summer monsoon or rainy season and this period of time in a year often observes a floods that cause significant harm to property, livestock, crops, and human life. The floods in 1987 and 1988, 1998, 2007 and 2024 are examples of flood events that reach catastrophic levels requiring large-scale international relief efforts (Ahmed & Kim, 2003 ). Similarly, drought and extreme cold events affect the societal life as well as the economy of the region. Therefore, predicting next to current seasonal weather conditions with a level of accuracy will create the opportunity for preparedness and will result benefit to society as well as regional economy particularly for the country like Bangladesh that is vulnerable to various disasters related to weather and climate. Seasonal weather forecasting takes a different approach compare to short duration weather forecast. Rather than relying on rapidly changing initial weather states, seasonal forecasts leverage slowly varying climate drivers. For example, researchers have found large-scale climate oscillations like ENSO (El Niño–Southern Oscillation) is one of the key drivers of seasonal weather as well as climate pattern. The difference in sea level pressure between Tahiti in the eastern Pacific Ocean and Darwin in the western Pacific Ocean indicates the atmospheric component of ENSO, which is the focus of SOI. El Nino phases are indicated by negative SOI values, whereas La Nina phases are indicated by positive values. (Fang et al., 2022 ; Jaroszewicz et al., 2024 ; Power & Kociuba, 2011 ). With a cycle of two to seven years, it is the most common periodic climate pattern and results from the interaction of the tropical Pacific Ocean's atmosphere and ocean. Its occurrence in the tropical Pacific Ocean determines whether it is considered eastern or central Pacific, and its influence spreads globally, causing variations in rainfall, temperature, and other factors (Sattar et al., 2021 ). ENSO has three stages: the neutral phase is in between the extreme El Nino and La Nina phases (Ibebuchi & Richman, 2024 ; Mir et al., 2024 ). El Nino can be described by the central and eastern tropical Pacific Ocean’s Sea surface temperatures being higher than normal, which weakens trade winds. La Nina, that produces the opposite weather pattern of El Nino, is characterized by sea surface temperatures that are lower than usual in the same area of the Pacific Ocean. The phenomenon known as the "neutral phase," which is neither El Nino nor La Nina, occurs when sea surface temperatures are almost average [12]. The ONI (Oceanic Nino Index), on the other hand, is NOAA's primary indicator of the oceanic component of ENSO. It measures mean sea surface temperature anomalies in the central and eastern tropical Pacific Ocean (Nino 3.4 region, 5°N-5°S, 120°-170°W) over a 3-month period. El Nino phases are indicated by ONI values of + 0.5 or higher, and La Nina phases by values of -0.5 or lower. A full-fledged El Nino or La Nina would develop if these anomalies persisted for at least five months in a row (Capotondi et al., 2015 ). In the same location as ONI, Nino 3.4 SST shows 5-month running mean SST anomalies. It is the indicator most frequently used to characterize the ENSO phase (Fang et al., 2022 ). Prior research finds only a modest correlation between Bangladesh’s summer monsoon rainfall and the Niño3.4 index (Ehsan et al., 2023b ). Additional important factors that can affect not only the ENSO phenomenon but the entire climatic pattern includes the Indian Ocean Dipole (IOD), Pacific Decadal Oscillation (PDO), Bivariate ENSO Timeseries (BEST), Trans-Nino Index (TNI), Pacific North American (PNA) pattern, and 200mb Zonal Winds as suggested from several literature. IOD represents the discrepancy between SST anomalies in the western equatorial Indian Ocean (50°E to 70°E and 10°S to 10°N) and eastern equatorial Indian Ocean (90°E to 110°E and 10°S to 0°S). A positive IOD term is identified by warmer than average tropical western Indian Ocean and cooler than average water tropical eastern Indian Ocean. During this period, Indonesia and Australia are prone to be more arid than normal increasing the probability of bushfires. Conversely, eastern Africa is prone to be more moist than normal, increasing the chances of floods. Similarly, a negative IOD results an opposite (Forootan et al., 2016 ). PDO index on the other hand can be treated as an effective indicator of ENSO-like Pacific climate convertibility. The PDO fluctuates approximately every 20 to 30 years.(Newman et al., 2003 ) Two extreme phases of the PDO are warm or cool, depending on the oceanic temperature variation in the northeast and tropical Pacific Ocean. The PDO index seems to be positive when SST values are abnormally cold inside the North Pacific and torrid towards the Pacific Coast, and sea surface pressures are very low over the North Pacific. Similarly, the reverse situation indicates a negative PDO index. Another index, BEST makes the calculation simpler and provides a long-period ENSO index. By considering the SOI along with Nino 3.4 SST, the impact of SST data skewness induced by alteration is minimized. High and low values are taken into account for differentiating El Nino and La Nina events respectively, and close to zero indicate ENSO-neutral phases. Since any of SOI and Nino 3.4 SST can be dominating, it would be more accurate to use the months that conform to both high Nino3.4 SST and low SOI or vice versa (Wei, 2024 ). TNI is introduced to define the unique character of each El Nino or La Nina event. It refers to the difference in normalized SST anomalies between the Niño 1 + 2 and Niño 4 regions and thus measures the gradient in SST anomalies between the central and eastern equatorial Pacific (Kao et al., 2009). PNA denotes a climatic pattern related to the air circulation over the North Pacific Ocean to that over the North American continent. This index is measured by the geopotential elevation anomalies (generally at 500 and 700 mb) over the western and eastern United States ( Pacific North American Index (PNA) , n.d.). According to the previous research, PNA is strongly influenced by the ENSO phenomenon. (Li et al., 2019 ) The positive PNA can be characterized by the above-average pressure near Hawaii and across the mountainous region of western North America, along with the below-average pressure south of Alaska and over the southeastern United States, which are generally associated with Pacific warm episodes or El Nino. The opposite scenario is observed in the same region during negative PNA patterns, which tend to occur during Pacific cold episodes or La Nina ( Climate Variability: Pacific–North American Pattern | NOAA Climate.Gov , n.d.). The zonal wind speed indicates winds blowing horizontally along the latitude lines, rather than the vertical winds. The role of 200mb Zonal Winds is highly significant in the ENSO phenomenon. Zonal winds weaken in the central Pacific during El Nino while it strengthens in the same region in La Nina. According to a recent study, the efficiency and overall performance of Nino 3.4 SST index-based models have declined due to inconsistent performance of the models. Multi-model ensemble system comparisons were done in a study (Barnston et al., 2019 ). The model’s performance can decrease due to the change in the dynamics of ENSO indices. Since the very beginning, both dynamical models and statistical models have been used to predict El Nino events (Chen et al., 2024 ; Latif et al., 1994 ; Yeh & Kirtman, 2007 ). Errors are greatly amplified due to the coupled feedback in the equatorial ocean-atmosphere system in spring, resulting in the phenomenon of the Spring Predictability Barrier. (Duan & Wei, 2013 ) That is also a reason why prediction accuracy is not satisfactory in statistical models. To obtain higher accuracy, more development is necessary along with regular ENSO index models. In comparison to linear regression model predictions, the LSTM machine learning model outperforms them. (Song et al., 2023 ) Machine learning-based models are more suitable as they can establish relationships between input and output parameters regardless of the complexity. However, there have been numerous studies conducted on unsupervised machine learning and deep learning techniques, less attention was paid to supervised machine learning models. Supervised machine learning models can also accurately predict extreme weather events and their intensity. For rainfall prediction, an analysis conducted in a previous study revealed that the Random Forest model to be the most accurate for rainfall prediction in the respective research area (Saleh & Rasel, 2024 ). Besides, the majority of the existing research concentrates on a single index and short-term predictions. Because of this, the incorporation of multiple indices into the machine learning model remains unexplored properly. ENSO indices, such as SOI, ONI, and Nino 3.4 SST reflects specific elements of the ENSO phenomenon while other indices, such as IOD, PDO, TNI, etc. offer insights into more general regional and global climate dynamics. These considerations raise three pressing research questions. First, how do ENSO indices affect the seasonal weather patterns of Bangladesh? While previous studies suggest modest to moderate correlations between ENSO phases and monsoon rainfall, the physical mechanisms and predictive strength of these relationships remain under-explored, particularly across different seasons and events within Bangladesh. Second, given the growing interest in data-driven methods, should we explore the suitability of machine learning (ML) models in the context of seasonal weather forecasting? ML models are known to handle nonlinear, high-dimensional data and may capture complex interactions between ENSO indices and local climate variability patterns that often elude traditional statistical or physics-based models. Third, are machine learning models truly worth considering for operational seasonal weather forecasting in Bangladesh? This question requires a careful comparison: how well can ML models, trained on historical ENSO and climate data, predict seasonal outcomes such as rainfall and temperature? Can they offer better solution than existing forecasting methods? This study solely focuses on these gaps in the prediction of seasonal weather patterns, and ENSO indices. This endeavor seeks to employ a number of models, including K-Fold Cross-Validation, Random Forest, Decision Tree, Linear Regression, XGBoost, and K-Nearest Neighbors, for performance analysis in order to determine which model would be most appropriate for these situations by examining Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Coefficient of Determination (R 2 ). Besides, inclusion of multiple indices in this study improves the model's capacity to represent the complicated relationships between oceanic and atmospheric systems that affect seasonal weather patterns. Therefore, the study aims to predict the temperature and rainfall by establishing a relationship between ENSO indices and seasonal climatic parameters. 2. Methodology 2.1. Dataset and Study Area Four datasets of monthly maximum temperature, monthly minimum temperature, monthly average temperature and monthly average rainfall intensity have been processed using the data of 29 stations covering entire Bangladesh. The stations are namely, Barisal, Bhola, Bogra, Chandpur, Chittagong, Comilla, Cox's Bazar, Dhaka, Dinajpur, Faridpur, Feni, Hatiya, Ishurdi, Jessore, Khepupara, Khulna, M.Court, Madaripur, Mymensingh, Patuakhali, Rajshahi, Rangamati, Rangpur, Sandwip, Satkhira, Sitakunda, Srimangal, Sylhet, Teknaf. All the datasets also contain nine ENSO indices. They are ONI, NINO 3.4 SST, SOI, IOD, PDO, BEST, PNA, TNI, and 200mb Zonal Winds. Besides, each dataset also contains other parameters such as Year, Month, Season, Dominant Cycle, ENSO Event and its Intensity. 2.2. Data Source The ENSO indices were taken from the National Weather Service Climate Prediction Center and the datasets of temperature and rainfall were taken from the Bangladesh Agricultural Research Council (BARC). Table 1 represents an overview of the data type, data source, period, and unit. Table 1 Data Overview by Type, Source, Period, and Unit Data Type Data source Period Unit ENSO Indices https://www.cpc.ncep.noaa.gov 1977–2022 - Temperature https://barc.gov.bd/ 1977–2022 °C Rainfall https://barc.gov.bd/ 1977–2022 mm 2.3. Workflow The research workflow began with framing the problem and understanding the types of data required. Then, the required data were collected. Subsequently, data pre-processing was conducted to handle duplicate & missing values and remove outliers. After pre-processing, the exploratory data analysis (EDA) was conducted. In the EDA, Univariate, Bi-variate, and multi-variate analysis was carried out. EDA helps to understand the data, find the correlation among them and facilitate the model selection. Before feeding the data to train the model, data post-processing is required. Data post-processing is also known as ‘Feature Engineering’. Feature engineering was required for encoding categorical data and scaling the numerical data. Then, all the datasets were divided into two parts to train and validate the model. 70% of the total data were used to train the model and later, 30% of the total data were used to validate the model. Then, the models were assessed by using three performance metrics, namely Mean absolute error (MAE), root mean squared error (RMSE), and coefficient of determination (R 2 ) metrics. Finally, a comparison was demonstrated between actual scenario to predicted scenario, which highlighted the worthiness of the ML model. 2.4. Model Selection Decision tree is an improved supervised learning algorithm. Because each branch in this model represents an attribute value and each incremental node evaluates a property, the structure is remarkably similar to a tree, and each leaf node stands for the final assessment or prediction that is used to both regression and classification. The classification and regression tree (CART) is the modern term for the decision tree. Decision trees are associated with a few important terms. A sample is said to be a "root node" if it is divided into two or more homogeneous sets. A node can be broken into multiple smaller nodes. When sub-nodes split into further sub-nodes, decision nodes are produced. (Liu, 2025) Random Forest mixes several decision trees to forecast more precise outcomes for a given problem. It is among the most popular methods since it can be applied to regression analysis and several decision trees are created during the training stage in order to arrive at a shared result. To create a single tree, a random dataset is used. The decision tree model has a danger of overfitting, however, this issue is fixed by using random datasets in random forests, which lowers the risk of overfitting while simultaneously enhancing performance. The Random Forest method votes or, in the case of regression, averages the decisions made by all the trees. (Biau & Fr, 2012 ) Linear regression is a supervised machine learning technique that establishes a linear relationship between dependent and one or more independent variables by means of fitting a linear equation by observed data. The aim while using linear regression is to find the best-fit line, which implies that the error between the predicted and actual values should be kept to a minimum. There will be the least error in the best-fit line. The best-fit line equation provides a straight line that represents the relationship between the dependent and independent variables. Linear regression performs the task of predicting a dependent variable value (y) based on a given independent variable (x)). That is the reason why, it is named linear regression. (Starbuck, 2023 ) XGBoost refers to extreme gradient boosting which is a type of ensemble learning. The concept of ensemble learning is a combination of all the advantages of different machine learning models which can achieve better results than other models alone. By combining the decisions or predictions of normal weak models, XGBoost makes the best possible prediction. The optimization method (gradient) repeatedly changes the model’s parameters in response to the gradients of the errors. The algorithm also presents the idea of “gradient boosting with decision trees,” in which the importance of the decision trees is measured and added to the ensemble in turn. By adding a regularization term and utilizing a more advanced optimization algorithm, XGBoost goes one step further and improves accuracy and efficiency. Combining both regularization and shrinkage along with pruning technique, XGBoost avoids overfitting. (Kuthuru, 2025 ) K-Fold cross-validation is a repetitive method used to assess the performance of machine learning models. The dataset is split into k equal parts called k fold in which each fold is used for testing and the remaining k-1 fold is used for training purposes. The procedure is iterated k-times by changing the training and testing datasets, and, the best model is selected based on the minimum error between calculated and estimated parameters using RMSE. It provides a reliable estimate of model performance and minimizes the risk of overfitting. (Nti et al., 2021 ) The K-Nearest Neighbors (KNN) algorithm is a supervised machine-learning technique used for both classification and regression tasks. Known for its simplicity and ease of implementation, KNN does not rely on assumptions about the data's underlying distribution. It can manage both numerical and categorical data, making it a versatile option for various datasets. As a non-parametric method, it makes predictions by evaluating the similarity between data points in a given dataset. Additionally, KNN tends to be less sensitive to outliers compared to other algorithms. The K-NN algorithm works by finding the K nearest neighbors to a given data point based on a distance metric, such as Euclidean distance, Manhattan Distance, Minkowski Distance, etc. The class or value of the data point is then determined by the majority vote or average of the K neighbors. This approach allows the algorithm to adapt to different patterns and make predictions based on the local structure of the data. The value of k is very crucial in the KNN algorithm to define the number of neighbors in the algorithm. It is recommended to choose an odd value for k to avoid ties in classification. (Halder et al., 2024 ) 2.5. Model Training and Validation This study utilized a data-driven methodology to examine the influence of 13 critical climate indices, including the Year, Month, ONI, NINO 3.4 SST, SOI, IOD, PDO, PNA, TNI, BEST, 200mb Zonal Winds, ENSO Events, and their intensity. A data partitioning strategy was adopted, dividing the dataset into training (70%) and validation (30%) subsets, in line with standard practices in machine learning research (Douglass, 2020 ; Tareq, 2024 ). This splitting approach aimed to mitigate the risk of overfitting by ensuring the model's generalizability through performance assessment on unseen data (Sarker, 2021 ). The trained model was then subjected to rigorous evaluation on the independent validation set to measure its predictive accuracy and uncover potential biases. Such practices align with recommendations by leading machine learning practitioners to ensure robust model validation and avoid spurious conclusions in predictive studies (Wu & Vos, 2018 ). To evaluate the models, three widely used statistical metrics were employed: Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and the Coefficient of Determination (R²). These metrics provide complementary insights into model accuracy and predictive performance. 2.5.1. Mean Absolute Error (MAE) The Mean Absolute Error (MAE) measures the average magnitude of absolute errors between the predicted and actual values, providing a straightforward interpretation of prediction accuracy. Lower MAE values indicate better model performance, as they signify smaller deviations from the observed data. $$\:\varvec{M}\varvec{A}\varvec{E}\:=\:\frac{1}{\varvec{n}}\sum\:_{\varvec{i}=1}^{\varvec{n}}\left|{\varvec{y}}_{\varvec{i}}-{\widehat{\varvec{y}}}_{\varvec{i}}\right|$$ 1 2.5.2. Root Mean Squared Error (RMSE) The Root Mean Squared Error (RMSE) is the square root of the mean of the squared differences between the predicted and observed values. It penalizes larger errors more heavily due to the squaring operation. A lower RMSE value indicates higher model accuracy. However, as RMSE is scale-dependent, it is most effective when the errors follow a normal distribution. $$\:\varvec{R}\varvec{M}\varvec{S}\varvec{E}=\sqrt{\frac{\sum\:_{\varvec{i}=1}^{\varvec{n}}{\left({\varvec{y}}_{\varvec{i}}-{\widehat{\varvec{y}}}_{\varvec{i}}\right)}^{2}}{\varvec{n}}}$$ 2 2.5.3. Coefficient of Determination (R 2 ) The Coefficient of Determination (R²) quantifies the proportion of variance in the dependent variable that is explained by the independent variables in the model. Its value ranges from 0 to 1, with values closer to 1 indicating better predictive power. However, higher R² values may sometimes indicate overfitting, especially when the model performs exceptionally well on training data but poorly on unseen data. $$\:{\varvec{R}}^{2}=1-\frac{\sum\:_{\varvec{i}=1}^{\varvec{n}}{\left({\varvec{y}}_{\varvec{i}}-{\widehat{\varvec{y}}}_{\varvec{i}}\right)}^{2}}{\sum\:_{\varvec{i}=1}^{\varvec{n}}{\left({\varvec{y}}_{\varvec{i}}-{\stackrel{-}{\varvec{y}}}_{\varvec{i}}\right)}^{2}}$$ 3 3. Results and Discussion 3.1. Data Pre-processing During the data preprocessing phase, we identified a few instances of null values within the dataset. However, no duplicate entries were detected. Given the limited number of null values, we opted to remove the corresponding rows entirely to ensure data integrity. This was achieved using the dropna function provided by the Pandas library, which allowed us to eliminate rows containing null values efficiently. This approach preserved the overall quality and consistency of the dataset while minimizing the impact of missing data on subsequent analyses. After completing the data cleaning process, the temperature datasets were reduced to dimensions of 539 rows and 47 columns, while the rainfall dataset was reduced to dimensions of 527 rows and 47 columns. 3.2. Exploratory Data Analysis (EDA) To gain a comprehensive understanding of the dataset, exploratory data analysis (EDA) was conducted. This study involved univariate, bivariate, and multivariate analyses to examine the data from different perspectives and identify underlying patterns. 3.2.1. Univariate Analysis For categorical variables, such as ENSO Event, and Season, monthly count plots were generated to analyze their frequency distributions. For numerical variables, Kernel Density Estimate (KDE) plots were utilized to examine the data distribution. Figure 3 highlights La Nina events occur more frequently than El Nino and Neutral events, showing variability in the ENSO Events. On the other hand, Fig. 4 shows the Neutral events have the highest frequency, followed by Weak El Nino. Besides, Very Strong El Nino have much lower counts, indicating they are less frequent. Figure 5 represents the Neutral - Neutral phase condition is dominant with a higher frequency compared to remaining conditions. This suggests a higher occurrence of Neutral – Neutral conditions in the dataset and highlights the count of occurrences for different seasons. The El Nino - Neutral, Neutral - El Nino, Neutral - La Nina, La Nina - Neutral has the lowest count. Figure 6 visualizes the distribution of different ENSO indices. The indices ONI, SOI, IOD, PDO, BEST, PNA, and TNI exhibit peaks near zero, with their distributions demonstrating approximate symmetry. This observation indicates that these indices may closely follow a normal distribution. Therefore, normalization of these data is not required. 3.2.2. Bi-variate Analysis Figure 7 illustrates the distribution of ENSO events (El Nino, Neutral, and La Nina) across four seasons: Winter, Pre monsoon, Monsoon, and Post monsoon. In all seasons except Post monsoon, Neutral events exhibit the highest frequency, while El Nino events are the least common. But, La Nina events have the highest frequency in the Post monsoon. Figure 8 depicts the phase condition across different seasons. In all four seasons, fewer phase changes are observed, indicating that most conditions remained stable. The figure also highlights that there were no direct transitions from El Nino to La Nina or vice versa. 3.2.3. Multi-variate Analysis In this study, multivariate analysis is applied to explore the relationships between ENSO indices and weather parameters across 29 stations. To gain more specific insights, the datasets for T max , T min , T avg , and Rainfall were divided into eight ENSO events: Weak El Nino, Moderate El Nino, Strong El Nino, Very Strong El Nino, Neutral, Weak La Nina, Moderate La Nina, and Strong La Nina, facilitating a detailed examination of event-specific correlations. This approach enhances the precision of the analysis, uncovering complicated associations that deepen the understanding of how ENSO indices influence regional climate variability. Figure 9 shows the correlation between various climate indices and rainfall across different regions during strong La Nina events. Notably, IOD and TNI exhibit strong negative correlations in most regions, indicating reduced rainfall influence. PNA shows a consistently strong positive correlation, especially in southeastern areas. NINO 3.4 SST also shows moderate positive correlations. These patterns suggest that during strong La Nina, regional rainfall is more strongly influenced by IOD, PNA, and TNI. Figure 10 shows strong correlations between climate indices and minimum temperature during strong La Nina events. PNA exhibits a consistently strong positive correlation across all regions, while IOD and TNI show strong negative correlations, indicating significant influence on minimum temperature. NINO 3.4 SST also shows moderate to strong positive correlations. Overall, the pattern suggests that during strong La Nina, PNA, IOD, and TNI play key roles in shaping minimum temperature variations. Figure 11 shows how average temperature in different parts of Bangladesh relates to various climate factors during strong El Nino events. The PDO has the strongest and most consistent positive relationship with temperature across all stations. NINO 3.4 SST, TNI, and upper-level winds also show clear positive links, especially in eastern regions. In contrast, the PNA index is linked with lower temperatures. Some indices like ONI, SOI, and BEST have little or no clear effect. The color scale makes it easy to compare the strength and direction of these relationships. Figure 12 shows how maximum temperature (T max ) in Bangladesh correlates with climate indices during strong El Nino events. NINO 3.4 SST, PDO, and TNI have positive moderate correlations across all stations. *** Here, four correlation heatmaps derived from four datasets—T max , T min , T avg , and Rainfall—for four significant ENSO events were presented. The remaining correlation heatmaps are included in the annexure for reference. In total, 32 correlation heatmaps were generated, encompassing all combinations of the four datasets across the dfferent ENSO events, to comprehensively analyze the relationships between ENSO indices and climate variables across Bangladesh. *** 3.3. Feature Engineering To prepare the dataset for machine learning modeling, several preprocessing techniques were applied to handle categorical variables and scale numerical features. The steps are outlined below: 3.3.1. Categorical Feature Encoding The dataset contained categorical variables, including SEASON, and ENSO Event, which required transformation into a numerical format. One-hot encoding was applied to these categorical features using the OneHotEncoder function from Scikit-learn. To prevent multicollinearity, the first category of each feature was dropped (i.e., drop='first' was used), ensuring that redundant dummy variables were eliminated. The encoded categorical features were then concatenated with the original dataset after removing the respective categorical columns. Feature Selection After encoding, non-informative columns such as Index, Phase Change, and Phase Duration were excluded from the dataset. The dataset was then split into input features (X) and target variables (𝑦). Specifically, the input features (X) were obtained by removing the dependent variables, while the target variables (y) were extracted by selecting relevant columns from the dataset. Data Scaling To standardize the numerical features and improve the performance of machine learning models, feature scaling was applied. Standard scaling was performed using the StandardScaler function from Scikit-learn, which transforms the data to have a mean of 0 and a standard deviation of 1. The scaler was fitted on the training data, and the same transformation was applied to the test data to maintain consistency. 3.4. Model Performance Evaluation Table 2 Performance Comparison of Machine Learning Models for Predicting Climate Variable Performance Metrics Dataset Model Name Random Forest Regressor Decision Tree Regressor K fold Cross validation XGBoosting Linear Regression KNN Regressor R2 Score T max 0.8512 0.7918 0.7751 ± 0.0318 0.8509 0.6425 0.6095 T min 0.9693 0.9584 0.9787 ± 0.0054 0.9702 0.9679 0.8589 T avg 0.9521 0.9386 0.9456 ± 0.0115 0.9559 0.8472 0.7873 Rainfall 0.6253 0.6146 0.6216 ± 0.0235 0.5897 0.5662 0.4325 MAE T max 0.7921 0.9195 0.9423 ± 0.0599 0.7889 1.1940 1.2683 T min 0.5144 0.6243 0.5149 ± 0.0542 0.5120 0.5529 1.2357 T avg 0.5719 0.6563 0.6449 ± 0.0537 0.5479 1.0951 1.2344 Rainfall 94.3346 94.9789 85.6627 ± 5.4976 101.2635 107.4055 125.6424 RMSE T max 1.0180 1.2043 1.2812 ± 0.1035 1.0252 1.5982 1.6749 T min 0.7772 0.9042 0.6917 ± 0.0785 0.7678 0.7953 1.6955 T avg 0.7644 0.8630 0.8764 ± 0.0720 0.7316 1.3677 1.6149 Rainfall 149.2662 152.6571 135.9836 ± 7.6475 154.7295 161.8352 188.6645 Table 2 presents the performance of six machine learning models, Random Forest Regressor, Decision Tree Regressor, K-Fold Cross Validation, XGBoosting, Linear Regression, and KNN Regressor, evaluated across four datasets: T max , T min , T avg , and Rainfall. Three metrics are used: R² Score, MAE (Mean Absolute Error), and RMSE (Root Mean Square Error). The best-performing model is Random Forest in predicting T max , with an R² score of 0.8512, the MAE of 0.7921, and RMSE of 1.0180. Similarly, Random Forest also excels in predicting Rainfall, achieving the highest R² score (0.6253), the MAE (94.3346), and the RMSE (149.2662). On the other hand, XGBoosting leads for T avg dataset, with an R² score of 0.9559, the MAE (0.5479), and RMSE of 0.7316. XGBoosting shows superior performance in T min prediction, achieving the best balance across metrics with an R² score of 0.9702, an MAE of 0.5120, and RMSE of 0.7316. The XGBoosting model performed best for T min and T avg due to the consistency in these datasets. These datasets exhibit stable patterns, allowing XGBoost's gradient boosting approach to effectively capture and predict the underlying relationships with high precision. Its ability to handle non-linear relationships and outliers and fine-tune its performance through regularization further contributes to its success. The Random Forest Regressor excelled in predicting T max and Rainfall, despite the dataset's random variability. Random Forest's ensemble approach, which combines predictions from multiple decision trees, effectively handles random variations and avoids overfitting. This robustness makes it ideal for datasets with less predictable patterns. Table 3 Comparison between Actual and Predicted Scenario under Different Conditions Season Phase Rainfall T avg T min T max Actual Predicted Actual Predicted Actual Predicted Actual Predicted Winter El Nino - El Nino Both 3 Increase 2 Decrease 1 Decrease Both Both Decrease Decrease El Nino - Neutral Increase Increase Decrease Decrease Increase Increase Decrease Increase Neutral - Neutral Decrease Both Decrease Decrease Both Both Both Both Neutral - La Nina Decrease Decrease Decrease Decrease Decrease Decrease Decrease Decrease La Nina - La Nina Decrease Both Decrease Decrease Both Both Both Both La Nina - Neutral Decrease Decrease Decrease Decrease Decrease Decrease Decrease Decrease Neutral - El Nino Decrease Decrease Decrease Decrease Decrease Decrease Decrease Decrease Pre Monsoon El Nino - El Nino Decrease Both Increase Increase Both Both Decrease Both El Nino - Neutral Decrease Decrease Increase Increase Both Both Both Both Neutral - Neutral Both Both Increase Increase Increase Increase Both Both Neutral - La Nina Increase Increase Increase Increase Increase Increase Decrease Decrease La Nina - La Nina Decrease Decrease Increase Increase Both Both Both Both La Nina - Neutral Decrease Decrease Increase Increase Increase Increase Increase Increase Neutral - El Nino Increase Increase Increase Increase Increase Increase Decrease Decrease Monsoon El Nino - El Nino Both Increase Increase Increase Increase Increase Decrease Decrease El Nino - Neutral Decrease Decrease Increase Increase Increase Increase Increase Decrease Neutral - Neutral Both Both Increase Increase Increase Increase Decrease Decrease Neutral - La Nina Increase Increase Increase Increase Increase Increase Decrease Decrease La Nina - La Nina Decrease Both Increase Increase Increase Increase Decrease Decrease La Nina - Neutral Increase Increase Increase Increase Increase Increase Decrease Decrease Neutral - El Nino Increase Both Increase Increase Increase Decrease Decrease Decrease Post Monsoon El Nino - El Nino Decrease Both Both Both Both Both Decrease Both El Nino - Neutral Decrease Decrease Decrease Decrease Decrease Decrease Decrease Decrease Neutral - Neutral Both Both Both Both Both Both Both Both Neutral - La Nina Decrease Decrease Decrease Decrease Decrease Decrease Increase Decrease La Nina - La Nina Both Both Both Both Both Both Increase Increase La Nina - Neutral Decrease Decrease Decrease Decrease Decrease Decrease Decrease Decrease Neutral - El Nino Decrease Increase Increase Increase Increase Increase Increase Increase 1 Decrease = The probability is higher for the case where the actual or predicted value of the output parameters (Rainfall, T avg , T min , T max ) is smaller than the respective 10-year average value during the respective season 2 Increase = The probability is higher for the case where the actual or predicted value of the output parameters (Rainfall, T avg , T min , T max ) is greater than the respective 10-year average value during the respective season 3 Both = The probability is almost same for both cases The Table 3 presents a comparative analysis between actual observations and Random Forest model predictions of key climate variables, Rainfall, Average Temperature (T avg ), Minimum Temperature (T min ), and Maximum Temperature (T max ), across different ENSO (El Niño–Southern Oscillation) phases and four seasonal periods: Winter, Pre-Monsoon, Monsoon, and Post-Monsoon. The changes are evaluated relative to the average of the preceding ten years, with classifications as "Increase", "Decrease", or "Both" (indicating uncertainty or variability). Critically, the model demonstrates moderate alignment with actual trends, particularly for temperature variables (T avg , T min , T max ), where the predicted direction often matches the observed change. However, prediction accuracy appears more varied for rainfall, which shows several mismatches or uncertain classifications ("Both"), reflecting the complex and nonlinear nature of precipitation dynamics. Some combinations (e.g., La Nina – El Nino in Pre-Monsoon) show high concordance across all variables, while others (e.g., Neutral – Neutral in Post-Monsoon) reflect greater ambiguity. 4. Conclusion This study investigated the intricate connections between ENSO indices and seasonal weather patterns across Bangladesh, leveraging supervised machine learning models to predict rainfall and temperature variations. By integrating historical climate data from 29 meteorological stations and nine ENSO-related indices over 45 years (1977–2022), the research provides robust insights into the impact of large-scale ocean-atmosphere phenomena on local climate variability. Univariate and bivariate analyses revealed that La Nina events occurred more frequently, while Neutral phases dominated in terms of intensity. The multivariate correlation analysis across different ENSO phases and seasonal datasets underscored significant associations, particularly during strong El Nino and La Nina events. Variables like NINO 3.4 SST, SOI, PDO, and TNI exhibited consistent correlations with rainfall and temperature parameters, revealing their influence on regional climate anomalies. Six machine learning models were evaluated using R², MAE, and RMSE metrics for four key climate datasets: T max , T min , T avg , and Rainfall. Among them, XGBoost demonstrated the highest accuracy for T min (R² = 0.9702) and T avg (R² = 0.9559), whereas Random Forest was most effective for T max (R² = 0.8512) and Rainfall (R² = 0.6253). A comparative analysis between actual observations and Random Forest model predictions across ENSO phases and seasonal periods further validated the model's effectiveness. The predictions showed strong alignment with actual trends for temperature variables (T avg , T min , T max ), while rainfall predictions were more uncertain due to their inherent variability. In the winter season, predictions show a decrease in the average temperature across all the ENSO phases. T min , and T max are forecasted to decline during transitions like Neutral–La Nina, La Nina–Neutral, and Neutral–El Nino phases. Rainfall is forecasted to increase in the El Nino–El Nino, and El Nino–Neutral phases. These forecasts suggest that colder and drier conditions are expected in the winter season during ENSO transitions involving La Nina. Moving into the pre-monsoon season, the forecasts predict a consistent increase in the average temperature across all the ENSO phases. Rainfall predictions are more varied, but generally follow an increasing trend during transitions such as Neutral–La Nina, and Neutral–El Nino. This suggests that pre-monsoon conditions are likely to be hotter and wetter, especially when the ENSO phase shifts away from neutrality. In the monsoon season, seasonal forecasts indicate continued warming, particularly in T avg and T min , which are predicted to increase under almost every ENSO phases, T max is mostly predicted to decrease, pointing to a possible narrowing of the daily temperature range. During the post-monsoon season, predicted patterns are more mixed. Transitions like Neutral–El Nino show a consistent increase in all parameters, suggesting a warmer and wetter late season. In contrast, phases such as El Nino–Neutral, Neutral–La Nina, and La Nina–Neutral are predicted to bring decreases in rainfall and temperature, indicating a return to cooler, drier conditions. In summary, temperature trends are consistently forecasted, with T avg and T min increasing in most seasons and transitions. Rainfall predictions are more variable, but tend to rise during La Nina-related transitions and decline during shifts involving El Nino. This highlights both the model’s strengths in capturing temperature dynamics and its limitations in handling nonlinear rainfall patterns. Besides, these forecasted trends demonstrate the usefulness of seasonal weather forecasting in anticipating climate-driven variations, supporting informed planning in agriculture, infrastructure, and disaster preparedness in Bangladesh. Reliable seasonal forecasts can guide farmers in crop planning, assist policymakers in developing early warning systems, and support infrastructure development to mitigate climate risks. Conducted with the goal of enhancing climate resilience and promoting evidence-based decision-making, this study offers valuable insights for meteorologists, researchers, government agencies, and disaster management authorities. Looking ahead, future research should focus on incorporating satellite and remote sensing data, expanding the scope of climate indices, applying advanced deep learning models such as LSTM or hybrid networks, and simulating extreme weather scenarios like droughts and floods. These improvements will further strengthen model performance and contribute to the development of robust strategies for mitigating the socio-economic impacts of climate variability in Bangladesh and other ENSO-prone regions. Author Contributions Statement : M.M.: Conceptualization, Data sourcing & collection, Data processing, Analysis, Validation, Visualization, Result interpretation, Design, Writing – original draft, Writing – review & editing T.G.: Conceptualization, Data sourcing & collection, Data processing, Analysis, Validation, Visualization, Result interpretation, Design, Writing – original draft, Writing – review & editing F.A.: Conceptualization, Data sourcing & collection, Design, Writing – original draft, Writing – review & editing S.S: Conceptualization, Data sourcing & collection, Design, Writing – original draft, Writing – review & editing M.R.A.M.: Conceptualization, Supervision, Writing – review & editing Declarations Author Contributions Statement: M.M.: Conceptualization, Data sourcing & collection, Data processing, Analysis, Validation, Visualization, Result interpretation, Design, Writing – original draft, Writing – review & editing T.G.: Conceptualization, Data sourcing & collection, Data processing, Analysis, Validation, Visualization, Result interpretation, Design, Writing – original draft, Writing – review & editing F.A.: Conceptualization, Data sourcing & collection, Design, Writing – original draft, Writing – review & editing S.S: Conceptualization, Data sourcing & collection, Design, Writing – original draft, Writing – review & editing M.R.A.M.: Conceptualization, Supervision, Writing – review & editing Funding Statement: The authors declare that no funds, grants, or other support were received during the preparation of this manuscript. Data Availability: The datasets analyzed during the current study are not publicly available due to confidentiality agreements and institutional data-sharing restrictions, but are available from the corresponding author on reasonable request. Consent to Publish declaration: Not applicable. Consent to Participate declaration: Not applicable Ethics declaration: Not applicable Competing Interests: The authors have no relevant financial or non-financial interests to disclose . References Ahmed R, Kim IK. Patterns of Daily Rainfall in Bangladesh During the Summer Monsoon Season: Case Studies at Three Stations. Phys Geogr. 2003;24(4):295–318. https://doi.org/10.2747/0272-3646.24.4.295 . Amin A, Mourshed M. Weather and climate data for energy applications. Renew Sustain Energy Rev. 2024;192:114247. https://doi.org/10.1016/J.RSER.2023.114247 . Barnston AG, Tippett MK, Ranganathan M, L’Heureux ML. Deterministic skill of ENSO predictions from the North American Multimodel Ensemble. Clim Dyn. 2019;53(12):7215–34. https://doi.org/10.1007/s00382-017-3603-3 . Biau G, Fr GB. (2012). Analysis of a Random Forests Model. In J Mach Learn Res (13). Capotondi A, Wittenberg AT, Newman M, Di Lorenzo E, Yu JY, Braconnot P, Cole J, Dewitte B, Giese B, Guilyardi E, Jin FF, Karnauskas K, Kirtman B, Lee T, Schneider N, Xue Y, Yeh SW. Understanding enso diversity. Bull Am Meteorol Soc. 2015;96(6):921–38. https://doi.org/10.1175/BAMS-D-13-00117.1 . Chen S, Chen W, Xie SP, Yu B, Wu R, Wang Z, Lan X, Graf HF. Strengthened impact of boreal winter North Pacific Oscillation on ENSO development in warming climate. Npj Clim Atmospheric Sci. 2024;7(1). https://doi.org/10.1038/s41612-024-00615-3 . Climate Variability: Pacific–North American Pattern | NOAA Climate.gov . (n.d.). Retrieved August 31, 2024, from https://www.climate.gov/news-features/understanding-climate/climate-variability-pacific-north-american-pattern Douglass MJJ. (2020). Book Review: Hands-on Machine Learning with Scikit-Learn, Keras, and Tensorflow, 2nd edition by Aurélien Géron. Physical and Engineering Sciences in Medicine , 43 (3), 1135–1136. https://doi.org/10.1007/s13246-020-00913-z Duan W, Wei C. The spring predictability barrier for ENSO predictions and its possible mechanism: Results from a fully coupled model. Int J Climatol. 2013;33(5):1280–92. https://doi.org/10.1002/joc.3513 . Ehsan MA, Tippett MK, Robertson AW, Singh B, Rahman MA. The ENSO Fingerprint on Bangladesh Summer Monsoon Rainfall. Earth Syst Environ. 2023a;7(3):617–27. https://doi.org/10.1007/s41748-023-00347-z . Ehsan MA, Tippett MK, Robertson AW, Singh B, Rahman MA. The ENSO Fingerprint on Bangladesh Summer Monsoon Rainfall. Earth Syst Environ. 2023b;7(3):617–27. https://doi.org/10.1007/S41748-023-00347-Z/FIGURES/6 . Fang W, Sha Y, Sheng VS. Survey on the Application of Artificial Intelligence in ENSO Forecasting. Math 2022. 2022;10(20):3793. https://doi.org/10.3390/MATH10203793 . 10 . Forootan E, Khandu, Awange JL, Schumacher M, Anyah RO, van Dijk A, I. J. M, Kusche J. Quantifying the impacts of ENSO and IOD on rain gauge and remotely sensed precipitation products over Australia. Remote Sens Environ. 2016;172:50–66. https://doi.org/10.1016/J.RSE.2015.10.027 . Halder RK, Uddin MN, Uddin MA, Aryal S, Khraisat A. Enhancing K-nearest neighbor algorithm: a comprehensive review and performance analysis of modifications. J Big Data. 2024;11(1). https://doi.org/10.1186/s40537-024-00973-y . Ibebuchi CC, Richman MB. Deep learning with autoencoders and LSTM for ENSO forecasting. Clim Dyn. 2024. https://doi.org/10.1007/s00382-024-07180-8 . Islam T, Saha S, Evan AA, Halder N, Dey SC. Monthly Weather Forecasting through ANN Model: A Case Study in Barisal, Bangladesh. IJARCCE. 2016;5(6):1–6. https://doi.org/10.17148/ijarcce.2016.5601 . Jaroszewicz S, Mariani MC, Tweneboah OK, Beccar-Varela MP. Multifractal analysis of the Southern Oscillation Index. J Atmos Solar Terr Phys. 2024;254:106161. https://doi.org/10.1016/J.JASTP.2023.106161 . Kao HY, Yu JY. Contrasting Eastern-Pacific and Central-Pacific types of ENSO. J Clim. 2009;22(3):615–32. https://doi.org/10.1175/2008JCLI2309.1 . Kuthuru A. Semantic Data Contracts: A New Integration Paradigm for Enterprise AI and Database Systems. Eur J Comput Sci Inform Technol. 2025;13(31):1–9. https://doi.org/10.37745/ejcsit.2013/vol13n3119 . Latif M, Barnett TP, Cane MA, Flügel M, Graham NE, von Storch H, Xu JS, Zebiak SE. A review of ENSO prediction studies. Clim Dyn. 1994;9(4–5):167–79. https://doi.org/10.1007/BF00208250/METRICS . Li X, Hu ZZ, Liang P, Zhu J. Contrastive Influence of ENSO and PNA on Variability and Predictability of North American Winter Precipitation. J Clim. 2019;32(19):6271–84. https://doi.org/10.1175/JCLI-D-19-0033.1 . Liu Z. Leo. (2025). Decision Trees. Artif Intell Eng, 115–28. https://doi.org/10.1007/978-3-031-75953-6_4 Mir S, Arbab MA, Rehman Sur. ENSO dataset & comparison of deep learning models for ENSO forecasting. Earth Sci Inf. 2024;17(3):2623–8. https://doi.org/10.1007/s12145-024-01295-6 . Newman M, Compo GP, Alexander MA. ENSO-Forced Variability of the Pacific Decadal Oscillation. J Clim. 2003;16(23):3853–7. https://doi.org/10.1175/1520-0442(2003)016%3C3853:EVOTPD%3E2.0.CO;2 . Nti IK, Nyarko-Boateng O, Aning J. Performance of Machine Learning Algorithms with Different K Values in K-fold CrossValidation. Int J Inform Technol Comput Sci. 2021;13(6):61–71. https://doi.org/10.5815/ijitcs.2021.06.05 . Pacific North American Index (PNA) . (n.d.). Retrieved August 31, 2024, from https://www.daculaweather.com/4_pna_index.php Pinheiro E, Ouarda TBMJ. (2025). An interpretable machine learning model for seasonal precipitation forecasting. Communications Earth & Environment 2025 6:1 , 6 (1), 1–14. https://doi.org/10.1038/s43247-025-02207-2 Power SB, Kociuba G. The impact of global warming on the Southern Oscillation Index. Clim Dyn. 2011;37(9–10):1745–54. https://doi.org/10.1007/S00382-010-0951-7/FIGURES/5 . Saleh MA, Rasel HM. (2024). Performance evaluation of Machine Learning based regression models for rainfall forecasting . https://doi.org/10.21203/RS.3.RS-3856741/V1 Sarker IH. Machine Learning: Algorithms, Real-World Applications and Research Directions. SN Comput Sci. 2021;2(3):1–21. https://doi.org/10.1007/S42979-021-00592-X/METRICS . Sattar MA, Mia S, Shanta AA, Ahad Biswas A, A. K. M., Ludwig F. Remote impacts from el niño and la niña on climate variables and major crops production in coastal bangladesh. Atmosphere. 2021;12(11). https://doi.org/10.3390/atmos12111449 . Song WJ, Yu JY, Lian T. The efficacy of tropical and extratropical predictors for long-lead El Niño-Southern Oscillation prediction: A study using a machine learning algorithm. Int J Climatol. 2023;43(14):6887–99. https://doi.org/10.1002/joc.8241 . Starbuck C. (2023). Linear Regression. In The Fundamentals of People Analytics (pp. 181–206). Springer International Publishing. https://doi.org/10.1007/978-3-031-28674-2_10 Tareq WZT. (2024). Deep learning. Decision-Making Models: A Perspective of Fuzzy Logic and Machine Learning , 317–327. https://doi.org/10.1016/B978-0-443-16147-6.00016-5 Wei L. Summary of Commonly Used ENSO Indices. Highlights Sci Eng Technol. 2024;88:687–94. https://doi.org/10.54097/VNDV3190 . Wu Q, Vos P. Inference and Prediction. Handb Stat. 2018;38:111–72. https://doi.org/10.1016/BS.HOST.2018.06.004 . Yeh SW, Kirtman BP. ENSO amplitude changes due to climate change projections in different coupled models. J Clim. 2007;20(2):203–17. https://doi.org/10.1175/JCLI4001.1 . Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 30 Oct, 2025 Reviews received at journal 29 Oct, 2025 Reviewers agreed at journal 22 Oct, 2025 Reviewers agreed at journal 11 Oct, 2025 Reviewers agreed at journal 09 Oct, 2025 Reviews received at journal 08 Oct, 2025 Reviewers agreed at journal 08 Oct, 2025 Reviewers agreed at journal 07 Oct, 2025 Reviewers invited by journal 06 Oct, 2025 Editor invited by journal 06 Oct, 2025 Editor assigned by journal 26 Sep, 2025 Submission checks completed at journal 26 Sep, 2025 First submitted to journal 22 Sep, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7673222","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":530726686,"identity":"6536b07f-9b09-45c7-a2f3-b1556db2b6bf","order_by":0,"name":"M. Mohsin","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABE0lEQVRIiWNgGAWjYFACHjDJ2MDAwMbAYABiMx8AEhIypGhhSwBp4SFSC0TEACGOBei29x78dDPHTrZB7PCxhz8K7jDwt/d8fnWjxoKHgf3w0Q1YtJidOZcsnbst2bhBOi3dmMfgGYPEmbPbrHOOAR3Gk5Z2A5uWGzkGQC3MiQ3SOWbSDAaHGQwkcrcZ57ABtUjwmOHQYvw7d1s9WIvkD5AW+TfPjHP+4dViBrTlMFiLBA/YFh7mx7lteLScOWNmnbvtuHGbdFqaNFALj8SZNDPm3D4JHjZcfjneY3w7d1u1bL908jHJH38Oy/G3H378OedbnRw/++Fj2LTAATxSQGwJZBGiAPMHUlSPglEwCkbBsAcA7I1eCjhEyCAAAAAASUVORK5CYII=","orcid":"","institution":"Chittagong University of Engineering \u0026 Technology","correspondingAuthor":true,"prefix":"","firstName":"M.","middleName":"","lastName":"Mohsin","suffix":""},{"id":530726689,"identity":"5dd84e20-9f46-425d-a309-c724dfb57f3c","order_by":1,"name":"T. Ghosh","email":"","orcid":"","institution":"Chittagong University of Engineering \u0026 Technology","correspondingAuthor":false,"prefix":"","firstName":"T.","middleName":"","lastName":"Ghosh","suffix":""},{"id":530726693,"identity":"86ef6a33-3597-4ec7-8aef-e46081df69a7","order_by":2,"name":"F. Akter","email":"","orcid":"","institution":"Chittagong University of Engineering \u0026 Technology","correspondingAuthor":false,"prefix":"","firstName":"F.","middleName":"","lastName":"Akter","suffix":""},{"id":530726695,"identity":"c34b0043-c82d-413f-a1f9-f42bc0e20b23","order_by":3,"name":"S. Sarkar","email":"","orcid":"","institution":"Chittagong University of Engineering \u0026 Technology","correspondingAuthor":false,"prefix":"","firstName":"S.","middleName":"","lastName":"Sarkar","suffix":""},{"id":530726700,"identity":"8f904d45-e1e8-45ba-bbfe-a7c48fe1bf33","order_by":4,"name":"Md. R.A. Mullick","email":"","orcid":"","institution":"Chittagong University of Engineering \u0026 Technology","correspondingAuthor":false,"prefix":"","firstName":"Md.","middleName":"R.A.","lastName":"Mullick","suffix":""}],"badges":[],"createdAt":"2025-09-22 11:24:45","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7673222/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7673222/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":93773387,"identity":"2ec74869-0978-4624-b0bc-088405fa0532","added_by":"auto","created_at":"2025-10-17 12:22:57","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2070174,"visible":true,"origin":"","legend":"","description":"","filename":"FirstSubmission.docx","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/0ff573196cda10d337ff2028.docx"},{"id":93775354,"identity":"33f9984c-aabe-47c4-aaae-3ed67e8b262e","added_by":"auto","created_at":"2025-10-17 12:30:58","extension":"jpg","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1577377,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofModerateElNinoRainfall.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/92965f2d1507b1bc15f237cc.jpg"},{"id":93773393,"identity":"d8fb974d-522e-41a9-b9d6-fd56b94a8282","added_by":"auto","created_at":"2025-10-17 12:22:58","extension":"jpg","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1554077,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofModerateElNinoTavg.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/52390e28573a4d6bc90c6a8c.jpg"},{"id":93773384,"identity":"7a733237-5bd1-446c-bb3d-dc7011db868a","added_by":"auto","created_at":"2025-10-17 12:22:57","extension":"jpg","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1534080,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofModerateElNinoTmax.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/dd565c1b35cbce7ef646d632.jpg"},{"id":93777068,"identity":"d60996d5-4947-419c-bab7-bfcd23bcea50","added_by":"auto","created_at":"2025-10-17 12:38:58","extension":"jpg","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1567733,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofModerateElNinoTmin.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/5c1d194052404508040adbb5.jpg"},{"id":93775351,"identity":"b6b40797-f394-4e0f-927c-8a7470cedd6d","added_by":"auto","created_at":"2025-10-17 12:30:57","extension":"jpg","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1586117,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofModerateLaNinaRainfall.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/1e73cbe8bd26427b62574fc3.jpg"},{"id":93773401,"identity":"3025a970-0e6b-45c4-8fff-0905fc8f2ba2","added_by":"auto","created_at":"2025-10-17 12:22:58","extension":"jpg","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1575884,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofModerateLaNinaTavg.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/53f0b50035b57d5c62016010.jpg"},{"id":93773388,"identity":"400fbc14-b44e-46ee-b18f-078a755f1334","added_by":"auto","created_at":"2025-10-17 12:22:57","extension":"jpg","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1576142,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofModerateLaNinaTmax.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/b63b63e1d54446361dfe6161.jpg"},{"id":93773438,"identity":"5a23ccc4-b36a-43b4-bc3b-db9a36f67ab9","added_by":"auto","created_at":"2025-10-17 12:23:00","extension":"jpg","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1569354,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofModerateLaNinaTmin.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/0eb83df63ea2d7fccedf8197.jpg"},{"id":93773474,"identity":"c1c2486c-9312-4a15-a7cb-ab63c5c8d281","added_by":"auto","created_at":"2025-10-17 12:23:01","extension":"jpg","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1602546,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofNeutralRainfall.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/311c1da46ef881ee3316dc26.jpg"},{"id":93773390,"identity":"3986a38b-bb95-402c-bdf8-9a7018fd9ae2","added_by":"auto","created_at":"2025-10-17 12:22:58","extension":"jpg","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1583254,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofNeutralTavg.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/6f2414e58d051eb320110fb9.jpg"},{"id":93775353,"identity":"334e227e-a9b3-48e9-8060-58704c68b9f5","added_by":"auto","created_at":"2025-10-17 12:30:58","extension":"jpg","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1581004,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofNeutralTmax.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/5b0336ac768382c0e5f91cc3.jpg"},{"id":93773385,"identity":"19a967aa-8e7e-49f0-bda0-6233ff564791","added_by":"auto","created_at":"2025-10-17 12:22:57","extension":"jpg","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1580649,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofNeutralTmin.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/e7a0ab0f1fd7166ce13b78dd.jpg"},{"id":93778425,"identity":"f535bcde-47c5-43ca-8eba-76d4101a25f0","added_by":"auto","created_at":"2025-10-17 12:47:00","extension":"jpg","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1561598,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofStrongElNinoRainfall.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/2490ea8656e6ef24b5dce77a.jpg"},{"id":93775369,"identity":"6a959ddb-78d4-4060-9e09-2e8f8cb3e5b0","added_by":"auto","created_at":"2025-10-17 12:30:58","extension":"jpg","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1555534,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofStrongElNinoTavg.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/517b93436ea769d501d1132c.jpg"},{"id":93777077,"identity":"69e2c3b2-87cc-4fc0-9124-e938381eb90a","added_by":"auto","created_at":"2025-10-17 12:39:00","extension":"jpg","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1552476,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofStrongElNinoTmax.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/3dc612f5ce02803f0b07c07a.jpg"},{"id":93773413,"identity":"78968fb2-f95f-4ccb-a6d9-85f240d5f054","added_by":"auto","created_at":"2025-10-17 12:22:59","extension":"jpg","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1554544,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofStrongElNinoTmin.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/8cebdced7e99a96a80b86c5b.jpg"},{"id":93775373,"identity":"19f48ca2-1545-4aed-9e58-1cc94afe8d06","added_by":"auto","created_at":"2025-10-17 12:30:59","extension":"jpg","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1551842,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofStrongLaNinaRainfall.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/d46dbc875616e2d01925068c.jpg"},{"id":93775404,"identity":"e6865124-9a46-46c9-99b5-f43443177da7","added_by":"auto","created_at":"2025-10-17 12:31:01","extension":"jpg","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1526202,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofStrongLaNinaTavg.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/453eb5e69bae882c6e6ca3ff.jpg"},{"id":93773395,"identity":"bfa8e3c7-b4b2-41f3-b90a-9f25fe3f8cb1","added_by":"auto","created_at":"2025-10-17 12:22:58","extension":"jpg","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1532054,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofStrongLaNinaTmax.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/77793366f28ba6af315339c9.jpg"},{"id":93775359,"identity":"fe74a239-1ca9-47aa-aef5-eaed53481ce9","added_by":"auto","created_at":"2025-10-17 12:30:58","extension":"jpg","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1527430,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofStrongLaNinaTmin.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/43bc45388f735aba3cf33066.jpg"},{"id":93773427,"identity":"3362e023-d91f-4f56-a9ed-b519f2e68d40","added_by":"auto","created_at":"2025-10-17 12:22:59","extension":"jpg","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1550403,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofVeryStrongElNinoTavg.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/b400c8927ecac2949a49404b.jpg"},{"id":93775377,"identity":"4b8cf28d-182d-46ba-a604-a7b52d422cc7","added_by":"auto","created_at":"2025-10-17 12:30:59","extension":"jpg","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1564954,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofVeryStrongElNinoTmax.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/824924c018ff4defe24b250f.jpg"},{"id":93775394,"identity":"9ac0cfcf-5f49-4c83-840e-fa589de691b5","added_by":"auto","created_at":"2025-10-17 12:31:00","extension":"jpg","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1544148,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofVeryStrongElNinoTmin.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/9bea1ce40e2cc406815b91dd.jpg"},{"id":93773397,"identity":"578856c8-66d8-4430-850a-ccf44cec67da","added_by":"auto","created_at":"2025-10-17 12:22:58","extension":"jpg","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1573156,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofVeryStrongElNinoRainfall.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/7b643256c9e5233a617641ea.jpg"},{"id":93775383,"identity":"443ce26d-674a-42ee-8d97-72e75889187e","added_by":"auto","created_at":"2025-10-17 12:30:59","extension":"jpg","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1592315,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofWeakElNinoRainfall.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/792ae27d614417f187dcdec9.jpg"},{"id":93773518,"identity":"11d5c5a9-9128-4eda-bb81-647a48c98b48","added_by":"auto","created_at":"2025-10-17 12:23:03","extension":"jpg","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1564209,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofWeakElNinoTavg.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/9b2f818a3d3c46a719874b78.jpg"},{"id":93775362,"identity":"240ff2e8-7403-4868-b5ed-2a2babecb651","added_by":"auto","created_at":"2025-10-17 12:30:58","extension":"jpg","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1582685,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofWeakElNinoTmax.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/a7bfe9c98a149f9e80b66484.jpg"},{"id":93777073,"identity":"547a79ad-e13c-4b1f-ab8f-4502af0328da","added_by":"auto","created_at":"2025-10-17 12:38:59","extension":"jpg","order_by":28,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1560709,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofWeakElNinoTmin.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/7d0e1acb1627ea8e02189bba.jpg"},{"id":93773409,"identity":"eab5fad8-25d1-4de1-b8ec-7633b535bec3","added_by":"auto","created_at":"2025-10-17 12:22:59","extension":"jpg","order_by":29,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1573186,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofWeakLaNinaRainfall.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/60f4cc6395cc114ec54dba6d.jpg"},{"id":93773451,"identity":"ddd7b080-dbb5-4e3d-8032-3d70b1d3a5e4","added_by":"auto","created_at":"2025-10-17 12:23:00","extension":"jpg","order_by":30,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1569281,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofWeakLaNinaTavg.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/696895f3788fc53dd9b178f0.jpg"},{"id":93777109,"identity":"a297b253-10b1-4f57-bad7-c35764e79474","added_by":"auto","created_at":"2025-10-17 12:39:01","extension":"jpg","order_by":31,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1572718,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofWeakLaNinaTmax.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/d1d802e85790381a7bad50df.jpg"},{"id":93773412,"identity":"f5895e22-dcff-4021-9dea-83d19a375df9","added_by":"auto","created_at":"2025-10-17 12:22:59","extension":"jpg","order_by":32,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1568414,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofWeakLaNinaTmin.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/4821a709e1503c1ee4097c31.jpg"},{"id":93775402,"identity":"33f7dc30-2d2d-4a94-b670-554c3c28cb41","added_by":"auto","created_at":"2025-10-17 12:31:01","extension":"json","order_by":33,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7345,"visible":true,"origin":"","legend":"","description":"","filename":"ac4aabb730d645d4be428726747129bb.json","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/9c93b404347175983612f4dd.json"},{"id":93773405,"identity":"7c7b6129-32d2-47a1-8d75-0c98a2ba7e08","added_by":"auto","created_at":"2025-10-17 12:22:58","extension":"xml","order_by":34,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":160343,"visible":true,"origin":"","legend":"","description":"","filename":"ac4aabb730d645d4be428726747129bb1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/ce394f896889f8f4a6db88dd.xml"},{"id":93773408,"identity":"5acbae39-d86c-45ce-b97a-559f88b01c7a","added_by":"auto","created_at":"2025-10-17 12:22:58","extension":"jpg","order_by":35,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1577377,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofModerateElNinoRainfall.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/21f260eaef72071932941efb.jpg"},{"id":93773440,"identity":"06857c86-2d7f-48c8-8361-d9d2b3f7b731","added_by":"auto","created_at":"2025-10-17 12:23:00","extension":"jpg","order_by":36,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1554077,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofModerateElNinoTavg.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/6be161f71a1f86e7ddfeab35.jpg"},{"id":93773442,"identity":"b77d5f9c-614d-475e-a0c6-60030ef46643","added_by":"auto","created_at":"2025-10-17 12:23:00","extension":"jpg","order_by":37,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1534080,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofModerateElNinoTmax.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/76a951c051d1f16002089983.jpg"},{"id":93775375,"identity":"21e39987-384e-4375-a354-4c08c048f559","added_by":"auto","created_at":"2025-10-17 12:30:59","extension":"jpg","order_by":38,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1567733,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofModerateElNinoTmin.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/3e8006b57232dc615f825b7f.jpg"},{"id":93773470,"identity":"a83a1518-b793-48d4-9f43-2e3a22ca16e8","added_by":"auto","created_at":"2025-10-17 12:23:01","extension":"jpg","order_by":39,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1586117,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofModerateLaNinaRainfall.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/672a42542278a1eaa8ff4a4c.jpg"},{"id":93773417,"identity":"0b1a934d-57ef-48cf-8977-a55fd580a5b3","added_by":"auto","created_at":"2025-10-17 12:22:59","extension":"jpg","order_by":40,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1575884,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofModerateLaNinaTavg.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/ceffcc7f06723f04173598c7.jpg"},{"id":93777076,"identity":"96f4c16c-2265-4d24-9103-52044e1c4910","added_by":"auto","created_at":"2025-10-17 12:38:59","extension":"jpg","order_by":41,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1576142,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofModerateLaNinaTmax.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/201488b528a005dc09d3c5ed.jpg"},{"id":93777103,"identity":"f3561e18-4c0f-4a6b-8516-cf67921b10af","added_by":"auto","created_at":"2025-10-17 12:39:01","extension":"jpg","order_by":42,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1569354,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofModerateLaNinaTmin.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/c1982e803dfc5d8e8980c488.jpg"},{"id":93773449,"identity":"2f66aa89-ab0b-4165-8004-7ceb7250c851","added_by":"auto","created_at":"2025-10-17 12:23:00","extension":"jpg","order_by":43,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1602546,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofNeutralRainfall.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/c3acbea533324fe053a36260.jpg"},{"id":93775389,"identity":"4a30e86e-56af-4252-9b73-b4db853b447d","added_by":"auto","created_at":"2025-10-17 12:31:00","extension":"jpg","order_by":44,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1583254,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofNeutralTavg.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/ebb9d333ab4c30e37a78ae01.jpg"},{"id":93773488,"identity":"a895600a-5958-4e1a-ab1d-79e940db7aca","added_by":"auto","created_at":"2025-10-17 12:23:02","extension":"jpg","order_by":45,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1581004,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofNeutralTmax.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/5a083a1c8b9a81519da579bd.jpg"},{"id":93773453,"identity":"26923c8d-581d-42fc-b9b5-b504ec5062a5","added_by":"auto","created_at":"2025-10-17 12:23:00","extension":"jpg","order_by":46,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1580649,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofNeutralTmin.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/9d8f24aa9840d2779e56d1e9.jpg"},{"id":93775384,"identity":"67292e1e-8445-4236-bdc8-5a1b88126c3d","added_by":"auto","created_at":"2025-10-17 12:30:59","extension":"jpg","order_by":47,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1561598,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofStrongElNinoRainfall.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/3117afdd5c818c5a9c9070c9.jpg"},{"id":93773522,"identity":"67a0590b-48a5-4201-84d6-7d928790af78","added_by":"auto","created_at":"2025-10-17 12:23:03","extension":"jpg","order_by":48,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1555534,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofStrongElNinoTavg.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/589f83cb9c7320ee68015708.jpg"},{"id":93775381,"identity":"98d57561-cc6a-4770-aeff-0e6329503493","added_by":"auto","created_at":"2025-10-17 12:30:59","extension":"jpg","order_by":49,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1552476,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofStrongElNinoTmax.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/cc5b5514c6a92f962370ca24.jpg"},{"id":93773477,"identity":"9bf5c585-71a0-4476-ad4a-2aee272fd1c8","added_by":"auto","created_at":"2025-10-17 12:23:01","extension":"jpg","order_by":50,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1554544,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofStrongElNinoTmin.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/c97b9da88ad61cb8a6b1cdfc.jpg"},{"id":93775406,"identity":"f201127d-a840-4dfb-ad00-a21b582efc47","added_by":"auto","created_at":"2025-10-17 12:31:01","extension":"jpg","order_by":51,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1551842,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofStrongLaNinaRainfall.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/27e80df6a1ca7ae6223b77b5.jpg"},{"id":93773469,"identity":"5930ad7c-eac1-47fa-8035-77ffc98e3807","added_by":"auto","created_at":"2025-10-17 12:23:01","extension":"jpg","order_by":52,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1526202,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofStrongLaNinaTavg.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/efa619ca310ebcdd6d7ead09.jpg"},{"id":93775392,"identity":"50560fd3-7ffb-4379-82af-786628775d83","added_by":"auto","created_at":"2025-10-17 12:31:00","extension":"jpg","order_by":53,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1532054,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofStrongLaNinaTmax.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/167cd619d6a4a20667120c67.jpg"},{"id":93773471,"identity":"661638e1-88c9-45aa-8d47-ce215d03440d","added_by":"auto","created_at":"2025-10-17 12:23:01","extension":"jpg","order_by":54,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1527430,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofStrongLaNinaTmin.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/3a61cc691224df726d071232.jpg"},{"id":93775379,"identity":"a804d7b2-15bb-4c5f-ac4b-d991dee88dae","added_by":"auto","created_at":"2025-10-17 12:30:59","extension":"jpg","order_by":55,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1550403,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofVeryStrongElNinoTavg.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/2f71fb91e11adbbae478bf5e.jpg"},{"id":93773434,"identity":"69b63350-a1db-407a-931d-1a1aca7d156e","added_by":"auto","created_at":"2025-10-17 12:23:00","extension":"jpg","order_by":56,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1564954,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofVeryStrongElNinoTmax.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/089df346fbe1372d3120ab72.jpg"},{"id":93773520,"identity":"342b6ed5-2343-4296-97c9-667791f7c505","added_by":"auto","created_at":"2025-10-17 12:23:03","extension":"jpg","order_by":57,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1544148,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofVeryStrongElNinoTmin.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/9f1bd65cc70cf40c855e2f2a.jpg"},{"id":93775413,"identity":"3e5a920c-abe4-4c2a-ab25-71bd32836144","added_by":"auto","created_at":"2025-10-17 12:31:02","extension":"jpg","order_by":58,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1573156,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofVeryStrongElNinoRainfall.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/5d3d836338fed86a4678117a.jpg"},{"id":93773445,"identity":"fda3a67f-92fc-463e-86fb-8973185bb4c0","added_by":"auto","created_at":"2025-10-17 12:23:00","extension":"jpg","order_by":59,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1592315,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofWeakElNinoRainfall.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/95e331506a4d68777eb85714.jpg"},{"id":93773502,"identity":"54578062-fd43-471c-88c1-d4e524fe6bd4","added_by":"auto","created_at":"2025-10-17 12:23:02","extension":"jpg","order_by":60,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1564209,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofWeakElNinoTavg.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/f6ffd939d7ddeb3f8fc7a020.jpg"},{"id":93773482,"identity":"c47e1bba-893b-4778-9444-7bc8be4cb183","added_by":"auto","created_at":"2025-10-17 12:23:01","extension":"jpg","order_by":61,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1582685,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofWeakElNinoTmax.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/ff2d43ff2a6f9176bf298581.jpg"},{"id":93775415,"identity":"046a683c-29c1-4139-a124-d7ee5f3cec3d","added_by":"auto","created_at":"2025-10-17 12:31:02","extension":"jpg","order_by":62,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1560709,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofWeakElNinoTmin.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/967db0a65f37919fb09d2026.jpg"},{"id":93775378,"identity":"930126e6-cbc7-4608-9358-17c1fe0b9395","added_by":"auto","created_at":"2025-10-17 12:30:59","extension":"jpg","order_by":63,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1573186,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofWeakLaNinaRainfall.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/ce8eac891ec038d5aa058507.jpg"},{"id":93773415,"identity":"1a00d1b0-0400-4f33-9271-dc5a1f67f55f","added_by":"auto","created_at":"2025-10-17 12:22:59","extension":"jpg","order_by":64,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1569281,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofWeakLaNinaTavg.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/6739de7681488ae5930296f8.jpg"},{"id":93777114,"identity":"f189132e-4fef-48a4-942f-85b61b559bca","added_by":"auto","created_at":"2025-10-17 12:39:03","extension":"jpg","order_by":65,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1572718,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofWeakLaNinaTmax.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/04a537a9b34c89746e94fa8f.jpg"},{"id":93777097,"identity":"911ba135-4d5e-4000-a590-24d1fa3d53ab","added_by":"auto","created_at":"2025-10-17 12:39:01","extension":"jpg","order_by":66,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1568414,"visible":true,"origin":"","legend":"","description":"","filename":"HeatmapofWeakLaNinaTmin.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/8d6f1de1b8463ec1cd3c5db1.jpg"},{"id":93773433,"identity":"2c0df2c8-72da-4872-b0c1-a2f42d78c8f2","added_by":"auto","created_at":"2025-10-17 12:23:00","extension":"png","order_by":67,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":152759,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/8bf56f068b5e8ee2d59601c7.png"},{"id":93773464,"identity":"8870ca6a-56fa-4a0f-bd93-a97091a24170","added_by":"auto","created_at":"2025-10-17 12:23:01","extension":"jpeg","order_by":68,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":258506,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage10.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/9dfb45a5a31ccef9f992e3a2.jpeg"},{"id":93775380,"identity":"8a661808-e233-4b49-9bb8-f9c6e1c549e5","added_by":"auto","created_at":"2025-10-17 12:30:59","extension":"jpeg","order_by":69,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":261187,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage11.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/7a07b66fb6e5241d82b423e0.jpeg"},{"id":93773447,"identity":"8f763b71-cc6b-4925-9d4a-48e9d41b15fc","added_by":"auto","created_at":"2025-10-17 12:23:00","extension":"jpeg","order_by":70,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":265356,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage12.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/28ce704add7189eb946cd929.jpeg"},{"id":93773420,"identity":"f9443a63-760a-4f0e-a769-da5e87e99bfe","added_by":"auto","created_at":"2025-10-17 12:22:59","extension":"png","order_by":71,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":300911,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/96fefda2f7c2e5e31311c59a.png"},{"id":93773443,"identity":"b75fb9ef-8cf5-4ea9-a514-2c2b87c1184f","added_by":"auto","created_at":"2025-10-17 12:23:00","extension":"png","order_by":72,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":12888,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/2ef8941687e6004a122b5ea3.png"},{"id":93773416,"identity":"cd415920-abac-4e11-8889-59693c00cef5","added_by":"auto","created_at":"2025-10-17 12:22:59","extension":"png","order_by":73,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":30760,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/684d4886d11de36160d492e2.png"},{"id":93777091,"identity":"5d624ebf-8e4b-495e-a9ff-ad240f49351b","added_by":"auto","created_at":"2025-10-17 12:39:00","extension":"png","order_by":74,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":20184,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/cd0c356e8a44aca32304fd70.png"},{"id":93773461,"identity":"5fedf22d-607b-423d-8af1-fabbccee2e20","added_by":"auto","created_at":"2025-10-17 12:23:01","extension":"png","order_by":75,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":155281,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/b1b0ec04749f44062f7b336b.png"},{"id":93775388,"identity":"d41d847d-2dfe-4bec-9ced-d4386dabc5ec","added_by":"auto","created_at":"2025-10-17 12:31:00","extension":"png","order_by":76,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":30232,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/c0f5abdda7178322f0bf1c6f.png"},{"id":93773505,"identity":"72e8c76f-99ee-4f31-8403-f1b0e4499e99","added_by":"auto","created_at":"2025-10-17 12:23:02","extension":"png","order_by":77,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":38556,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/8012107840ef18d08590e9ce.png"},{"id":93773486,"identity":"0445e0e9-b179-4439-a5da-e345419e42d6","added_by":"auto","created_at":"2025-10-17 12:23:02","extension":"jpeg","order_by":78,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":258691,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage9.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/706b0390c7c558b54a584dd4.jpeg"},{"id":93773422,"identity":"24a3f790-bbde-46b0-a760-d0f3c42d6881","added_by":"auto","created_at":"2025-10-17 12:22:59","extension":"png","order_by":79,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":718033,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineHeatmapofModerateElNinoRainfall.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/4c984dc62ac5762022e69d5a.png"},{"id":93775409,"identity":"7a74eeec-0f9d-4a5b-b7b8-dfe1ce03dadd","added_by":"auto","created_at":"2025-10-17 12:31:01","extension":"png","order_by":80,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":670765,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineHeatmapofModerateElNinoTavg.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/a4bccd173ab242d382a4fc16.png"},{"id":93775411,"identity":"1bd780bd-c122-4d5a-859b-0c9d54b8a809","added_by":"auto","created_at":"2025-10-17 12:31:02","extension":"png","order_by":81,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":614892,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineHeatmapofModerateElNinoTmax.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/baeeed2b6a981521867ecdbe.png"},{"id":93773523,"identity":"0d097d92-0835-4283-9d37-93b95e84bde0","added_by":"auto","created_at":"2025-10-17 12:23:03","extension":"png","order_by":82,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":670494,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineHeatmapofModerateElNinoTmin.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/ef4fcb25a3c77e60e7a4b9fa.png"},{"id":93773509,"identity":"1a0f181f-590c-4f78-9351-863128ad0cc1","added_by":"auto","created_at":"2025-10-17 12:23:02","extension":"png","order_by":83,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":696846,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineHeatmapofModerateLaNinaRainfall.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/9d54512c0e1ddf8c54ef0ec1.png"},{"id":93777105,"identity":"14088295-2352-4013-9b27-ff88735a10b4","added_by":"auto","created_at":"2025-10-17 12:39:01","extension":"png","order_by":84,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":648757,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineHeatmapofModerateLaNinaTavg.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/b32ee0f8dfde9a6b09a0428a.png"},{"id":93777099,"identity":"cb4f88d4-6dad-49bc-bba1-5373bca2a2d3","added_by":"auto","created_at":"2025-10-17 12:39:01","extension":"png","order_by":85,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":686604,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineHeatmapofModerateLaNinaTmax.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/5a55a2f293999d5b7d3c7053.png"},{"id":93773455,"identity":"026f5006-1d1f-4636-b7e8-a4d2be11e747","added_by":"auto","created_at":"2025-10-17 12:23:00","extension":"png","order_by":86,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":631641,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineHeatmapofModerateLaNinaTmin.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/f8d99eb43211741440a80628.png"},{"id":93773483,"identity":"e7cb90d9-5549-47a5-a432-151b729303a2","added_by":"auto","created_at":"2025-10-17 12:23:02","extension":"png","order_by":87,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":728786,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineHeatmapofNeutralRainfall.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/a810dca200de8b339a6c1990.png"},{"id":93775417,"identity":"f2b8dead-3e95-496d-9076-fe56a99790fd","added_by":"auto","created_at":"2025-10-17 12:31:02","extension":"png","order_by":88,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":662694,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineHeatmapofNeutralTavg.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/211f1b62cf2d5369ec0c6dfe.png"},{"id":93773457,"identity":"d305a2d2-1586-467e-b81e-a66f8f625e9c","added_by":"auto","created_at":"2025-10-17 12:23:01","extension":"png","order_by":89,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":683514,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineHeatmapofNeutralTmax.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/4695ca832a590ef7abc26cf2.png"},{"id":93777110,"identity":"2260a2ab-c8f5-4809-bc46-34db63f7f43c","added_by":"auto","created_at":"2025-10-17 12:39:01","extension":"png","order_by":90,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":650831,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineHeatmapofNeutralTmin.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/7ca5ad57814eca9b1228d774.png"},{"id":93775414,"identity":"b8773ea6-c231-479e-9ecf-df6ac7a38c72","added_by":"auto","created_at":"2025-10-17 12:31:02","extension":"png","order_by":91,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":681313,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineHeatmapofStrongElNinoRainfall.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/d0f03ad9fe4ae1e6f4fc6142.png"},{"id":93777111,"identity":"caa1697e-65d8-43f2-a5ef-8652ab620637","added_by":"auto","created_at":"2025-10-17 12:39:02","extension":"png","order_by":92,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":677531,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineHeatmapofStrongElNinoTavg.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/591842bc5654d93643592f89.png"},{"id":93777104,"identity":"7fff4ec6-41a3-4d72-b19b-461ca9479a73","added_by":"auto","created_at":"2025-10-17 12:39:01","extension":"png","order_by":93,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":689209,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineHeatmapofStrongElNinoTmax.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/91733f18c0fddef5498d9710.png"},{"id":93775385,"identity":"9a1de40e-8cbc-469c-9f38-b5156e54aae9","added_by":"auto","created_at":"2025-10-17 12:31:00","extension":"png","order_by":94,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":666168,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineHeatmapofStrongElNinoTmin.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/3fa6b3fd7c0ea21c55787534.png"},{"id":93778456,"identity":"d30c6217-a594-45f4-b8dc-c637f2c65b37","added_by":"auto","created_at":"2025-10-17 12:47:02","extension":"png","order_by":95,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":670819,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineHeatmapofStrongLaNinaRainfall.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/f19aa63da9ad97b0ad61365f.png"},{"id":93775408,"identity":"67219920-b7c9-48ce-9b7c-f17a2d31d326","added_by":"auto","created_at":"2025-10-17 12:31:01","extension":"png","order_by":96,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":638951,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineHeatmapofStrongLaNinaTavg.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/0004cb621a2c71f6c15c4ef9.png"},{"id":93773456,"identity":"479eda9b-d053-435a-9e3b-8ac73e482f29","added_by":"auto","created_at":"2025-10-17 12:23:01","extension":"png","order_by":97,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":663566,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineHeatmapofStrongLaNinaTmax.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/71320f0270c912febb2f0950.png"},{"id":93773473,"identity":"204e30b4-0491-445a-a1bb-76a2003fcd3c","added_by":"auto","created_at":"2025-10-17 12:23:01","extension":"png","order_by":98,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":631792,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineHeatmapofStrongLaNinaTmin.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/09ed15333d27950f399cb6a4.png"},{"id":93777083,"identity":"6e198b59-a1f8-4393-bffb-479a4daeb156","added_by":"auto","created_at":"2025-10-17 12:39:00","extension":"png","order_by":99,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":665245,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineHeatmapofVeryStrongElNinoTavg.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/3e6f294aa9265106c9defecd.png"},{"id":93773480,"identity":"410dcb14-d982-4725-bd52-732ed5d9c84c","added_by":"auto","created_at":"2025-10-17 12:23:01","extension":"png","order_by":100,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":680183,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineHeatmapofVeryStrongElNinoTmax.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/8e17a06e941dad01038ec50a.png"},{"id":93773503,"identity":"4fa20ec8-fb0e-4726-9df6-831eff35315b","added_by":"auto","created_at":"2025-10-17 12:23:02","extension":"png","order_by":101,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":649026,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineHeatmapofVeryStrongElNinoTmin.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/a53d9792004d2dce094e9272.png"},{"id":93773526,"identity":"d02dd510-49e1-4906-b23c-7abe7a8e84bd","added_by":"auto","created_at":"2025-10-17 12:23:04","extension":"png","order_by":102,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":665267,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineHeatmapofVeryStrongElNinoRainfall.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/f20696aafc4ab43699b26f14.png"},{"id":93773466,"identity":"d03ba98c-5fc9-400a-a754-b591c68f1228","added_by":"auto","created_at":"2025-10-17 12:23:01","extension":"png","order_by":103,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":725359,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineHeatmapofWeakElNinoRainfall.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/36e8b3553ba13479e9f54bbe.png"},{"id":93773521,"identity":"d548b956-d355-4fc0-8bed-ad6729b67d1e","added_by":"auto","created_at":"2025-10-17 12:23:03","extension":"png","order_by":104,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":637645,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineHeatmapofWeakElNinoTavg.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/3631d8d76e21de2d144c64db.png"},{"id":93777087,"identity":"bf109a3f-d60b-4c35-b26e-0fef23b60120","added_by":"auto","created_at":"2025-10-17 12:39:00","extension":"png","order_by":105,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":678621,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineHeatmapofWeakElNinoTmax.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/a511c5e0c0a859d2543073f6.png"},{"id":93775418,"identity":"700064e4-4d20-4e18-83ca-c1b6ec04ebca","added_by":"auto","created_at":"2025-10-17 12:31:02","extension":"png","order_by":106,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":638969,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineHeatmapofWeakElNinoTmin.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/041197f8fd05e21351936856.png"},{"id":93773481,"identity":"13840a05-f839-4af0-a80d-977cf605b83c","added_by":"auto","created_at":"2025-10-17 12:23:01","extension":"png","order_by":107,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":688422,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineHeatmapofWeakLaNinaRainfall.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/85b4ee463a1743dcdd103168.png"},{"id":93773423,"identity":"86927d06-e4fe-45ae-b1b4-6601c64b5f7e","added_by":"auto","created_at":"2025-10-17 12:22:59","extension":"png","order_by":108,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":644816,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineHeatmapofWeakLaNinaTavg.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/9b974c36eaf69517b82b4169.png"},{"id":93775400,"identity":"43025ace-6460-4483-8b33-c308aeb2fd45","added_by":"auto","created_at":"2025-10-17 12:31:01","extension":"png","order_by":109,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":687183,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineHeatmapofWeakLaNinaTmax.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/21de9a8f43c2f39c0b39b7d1.png"},{"id":93773513,"identity":"41bd5fc7-f2f4-4801-8e5b-1238f37ffd2b","added_by":"auto","created_at":"2025-10-17 12:23:03","extension":"png","order_by":110,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":624261,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineHeatmapofWeakLaNinaTmin.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/21d4b3b717a2db3d3fa710b7.png"},{"id":93775425,"identity":"22827ee2-a296-4450-92bc-6354c6f6ba9a","added_by":"auto","created_at":"2025-10-17 12:31:04","extension":"png","order_by":111,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":48058,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/aee356f5b417693774b93717.png"},{"id":93778455,"identity":"558ceb3f-0f9c-46c1-98cc-397176cc0d12","added_by":"auto","created_at":"2025-10-17 12:47:02","extension":"png","order_by":112,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":56550,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage10.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/629ae4c8784eb3504910ad85.png"},{"id":93775421,"identity":"b4870316-a477-40d4-b664-7166699f62ee","added_by":"auto","created_at":"2025-10-17 12:31:03","extension":"png","order_by":113,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":59660,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage11.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/c0a8d89a76c55cb76ffa458b.png"},{"id":93775424,"identity":"d94c6102-b915-4bf8-b924-66118e84206c","added_by":"auto","created_at":"2025-10-17 12:31:03","extension":"png","order_by":114,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":56191,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage12.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/77c522217a07ef94608df4e7.png"},{"id":93773492,"identity":"292352be-868e-407b-8568-100467a10ef2","added_by":"auto","created_at":"2025-10-17 12:23:02","extension":"png","order_by":115,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":71555,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/15589e69fa8097c206040aae.png"},{"id":93777108,"identity":"2a92955d-649f-4ffc-8e0d-8f716867635d","added_by":"auto","created_at":"2025-10-17 12:39:01","extension":"png","order_by":116,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6255,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/b7f00a8089fb6f96d6311dd6.png"},{"id":93773516,"identity":"08c6d8ed-3acc-43df-8f75-db8db4902989","added_by":"auto","created_at":"2025-10-17 12:23:03","extension":"png","order_by":117,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8194,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/cbab6dfe0a50d3c90fe905a9.png"},{"id":93775422,"identity":"fa24bfb6-d775-472c-828b-c22fc7bb1bbc","added_by":"auto","created_at":"2025-10-17 12:31:03","extension":"png","order_by":118,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6040,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/edfd332b267649a02cc7639d.png"},{"id":93773501,"identity":"ad469be2-221e-4655-b500-c4b1d099b6bd","added_by":"auto","created_at":"2025-10-17 12:23:02","extension":"png","order_by":119,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":50114,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/4c6084e6811871fcc2315656.png"},{"id":93773506,"identity":"991dbc88-42e9-4b2f-8305-535c30769e81","added_by":"auto","created_at":"2025-10-17 12:23:02","extension":"png","order_by":120,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":14463,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/3bc5a8ffda62076a33099ad7.png"},{"id":93775387,"identity":"b1ffeb40-d1e0-4439-98cf-738154c51d17","added_by":"auto","created_at":"2025-10-17 12:31:00","extension":"png","order_by":121,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":17909,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/42d7e2c904acf0b6f9c1013c.png"},{"id":93775397,"identity":"4bb82a85-6297-4401-8f74-f0ebbf932c25","added_by":"auto","created_at":"2025-10-17 12:31:01","extension":"png","order_by":122,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":54829,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/bf4dff1e83f098b5086ab938.png"},{"id":93773525,"identity":"93f32021-702b-47d2-bbf0-a8f4a14906d7","added_by":"auto","created_at":"2025-10-17 12:23:04","extension":"xml","order_by":123,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":159766,"visible":true,"origin":"","legend":"","description":"","filename":"ac4aabb730d645d4be428726747129bb1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/7e67a06028e9525d65d7083f.xml"},{"id":93773478,"identity":"eb4dd190-99c1-4b41-8f04-c7bfcaf4ab16","added_by":"auto","created_at":"2025-10-17 12:23:01","extension":"html","order_by":124,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":171555,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/16eb148e2fa89ba0037f3554.html"},{"id":93773399,"identity":"2f605b60-91a7-49c9-add4-554eb16ac872","added_by":"auto","created_at":"2025-10-17 12:22:58","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":152759,"visible":true,"origin":"","legend":"\u003cp\u003eGeographical Distribution of Meteorological 29 Stations in Bangladesh\u003c/p\u003e","description":"","filename":"image1.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/f8613db1e23d8db6b9e3c65d.png"},{"id":93773382,"identity":"e594b395-a5bd-4d2c-97b1-6d0ac9f717ea","added_by":"auto","created_at":"2025-10-17 12:22:57","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":300911,"visible":true,"origin":"","legend":"\u003cp\u003eWorkflow Diagram\u003c/p\u003e","description":"","filename":"image2.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/4de08013867030513b31f6b0.png"},{"id":93775355,"identity":"f5b46351-c37d-4915-96cc-248f8731d4b9","added_by":"auto","created_at":"2025-10-17 12:30:58","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":12888,"visible":true,"origin":"","legend":"\u003cp\u003eMonthly Count Plot of ENSO Event\u003c/p\u003e","description":"","filename":"image3.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/84a232d7b96cfdffb16acb6e.png"},{"id":93773404,"identity":"d8494c9b-42ee-47ce-b2ee-7d1e4a86808e","added_by":"auto","created_at":"2025-10-17 12:22:58","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":30760,"visible":true,"origin":"","legend":"\u003cp\u003eMonthly Count Plot of ENSO Event with Intensity\u003c/p\u003e","description":"","filename":"image4.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/aae85895bb039046c1926c30.png"},{"id":93775352,"identity":"2d970a00-9c50-45f1-abaf-d151273248e7","added_by":"auto","created_at":"2025-10-17 12:30:58","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":20184,"visible":true,"origin":"","legend":"\u003cp\u003eMonthly Count Plot of Phase Conditions\u003c/p\u003e","description":"","filename":"image5.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/c541f1c0fe971a88e9d850a9.png"},{"id":93775357,"identity":"51bf9813-3ee6-408c-ab7f-b5367a97e997","added_by":"auto","created_at":"2025-10-17 12:30:58","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":155281,"visible":true,"origin":"","legend":"\u003cp\u003eKDE Plot of Different ENSO Indices\u003c/p\u003e","description":"","filename":"image6.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/8c818479d326a37b386a3f49.png"},{"id":93773392,"identity":"ba0e30d8-76b5-4aff-8489-8d0add181642","added_by":"auto","created_at":"2025-10-17 12:22:58","extension":"png","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":30232,"visible":true,"origin":"","legend":"\u003cp\u003eBivariate Analysis Between 4 Seasons and ENSO Event\u003c/p\u003e","description":"","filename":"image7.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/e6f57e91a07cf07edb9db9e5.png"},{"id":93773383,"identity":"e7102d9d-47c7-4e8b-84fe-c8f6a671f81b","added_by":"auto","created_at":"2025-10-17 12:22:57","extension":"png","order_by":8,"title":"Figure 8","display":"","copyAsset":false,"role":"figure","size":38556,"visible":true,"origin":"","legend":"\u003cp\u003eBivariate Analysis Between 4 Seasons and Phase Condition\u003c/p\u003e","description":"","filename":"image8.png","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/add5db26099a710b5a56255b.png"},{"id":93773431,"identity":"911c0322-2ec9-42ea-b14e-1563cdf836e2","added_by":"auto","created_at":"2025-10-17 12:22:59","extension":"jpeg","order_by":9,"title":"Figure 9","display":"","copyAsset":false,"role":"figure","size":258691,"visible":true,"origin":"","legend":"\u003cp\u003eCorrelation of ENSO Indices with Rainfall Across 29 Stations in Bangladesh during Strong La Nina Events\u003c/p\u003e","description":"","filename":"image9.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/d2a850316576f6f69f2c0c66.jpeg"},{"id":93775390,"identity":"32aa7c3d-35a5-4ceb-a609-0beb2e8458d0","added_by":"auto","created_at":"2025-10-17 12:31:00","extension":"jpeg","order_by":10,"title":"Figure 10","display":"","copyAsset":false,"role":"figure","size":258506,"visible":true,"origin":"","legend":"\u003cp\u003eCorrelation of ENSO Indices with T\u003csub\u003emin\u003c/sub\u003e Across 29 Stations in Bangladesh during Strong La Nina Events\u003c/p\u003e","description":"","filename":"image10.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/ddc01148598ad1fd8c1eaf76.jpeg"},{"id":93773429,"identity":"41d276e3-79e1-4219-a5d3-22b07ba353d7","added_by":"auto","created_at":"2025-10-17 12:22:59","extension":"jpeg","order_by":11,"title":"Figure 11","display":"","copyAsset":false,"role":"figure","size":261187,"visible":true,"origin":"","legend":"\u003cp\u003eCorrelation of ENSO Indices with T\u003csub\u003eavg\u003c/sub\u003e Across 29 Stations in Bangladesh during Strong El Nino Events\u003c/p\u003e","description":"","filename":"image11.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/8a2e02915f9373068ba8bbe0.jpeg"},{"id":93773428,"identity":"1fa00fd9-e74f-487f-99c8-e4dbfc99c91d","added_by":"auto","created_at":"2025-10-17 12:22:59","extension":"jpeg","order_by":12,"title":"Figure 12","display":"","copyAsset":false,"role":"figure","size":265356,"visible":true,"origin":"","legend":"\u003cp\u003eCorrelation of ENSO Indices with T\u003csub\u003emax\u003c/sub\u003e Across 29 Stations in Bangladesh during Strong El Nino Event\u003c/p\u003e","description":"","filename":"image12.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/fade56fa681af1e3f8bce407.jpeg"},{"id":93778479,"identity":"203986e0-8603-41c0-9171-4a18aedda53c","added_by":"auto","created_at":"2025-10-17 12:47:09","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2870352,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7673222/v1/1db1ca41-69b3-432c-a1d8-70732def4267.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003eSeasonal Weather Pattern Prediction From Enso Indices Using Machine Learning\u003c/p\u003e","fulltext":[{"header":"1. Introduction","content":"\u003cp\u003eWeather describes the short-term state of the atmosphere at a given place and time, whereas climate is the long-term (e.g. 30-year) average of those weather conditions (Amin \u0026amp; Mourshed, \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2024\u003c/span\u003e). Weather events impact people\u0026rsquo;s everyday lives and so on the society; accurate weather forecasts, therefore is essential. A slight change in the weather pattern can have a significant impact on temperature and precipitation, which in turn can affect infrastructure, agriculture, water supply management, hydropower generation, fisheries, industry, health, everyday life, and the livelihoods of millions of people each day (Ehsan et al., \u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e2023a\u003c/span\u003e). Meteorologists use complex numerical models to predict the weather by solvpageing the equations of atmospheric motion. In recent decades, the weather models have gained a substantial improvement and a 7\u0026ndash;10 day forecast now is far more reliable than a 4-day forecast of 20 to 30 years ago. However, even the best models often face some fundamental limits. A small error in a 7\u0026ndash;10 day forecast can become a large error in a seasonal forecast (Pinheiro \u0026amp; Ouarda, \u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e2025\u003c/span\u003e). Hence, the weather prediction in practical typically does not exceed about two weeks. To partially compensate the issue, forecasts are often run as large ensembles of slightly varied simulations (Monte Carlo method), nonetheless this is computationally expensive (Pinheiro \u0026amp; Ouarda, \u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e2025\u003c/span\u003e). In short, deterministic weather forecasts beyond about 14 days are generally unreliable.\u003c/p\u003e\u003cp\u003eOn the other hand, if the pattern of the seasonal weather, the one to two season ahead of the current can be foreseen with a fair degree of accuracy, it can save resources and lives. Community can prepare for any extreme natural events, and make wise decisions in agricultural, sports, and many other areas of lives (Islam et al., \u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e2016\u003c/span\u003e). In Bangladesh, almost 75 to 80% of yearly rainfall falls during the summer monsoon or rainy season and this period of time in a year often observes a floods that cause significant harm to property, livestock, crops, and human life. The floods in 1987 and 1988, 1998, 2007 and 2024 are examples of flood events that reach catastrophic levels requiring large-scale international relief efforts (Ahmed \u0026amp; Kim, \u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e2003\u003c/span\u003e). Similarly, drought and extreme cold events affect the societal life as well as the economy of the region. Therefore, predicting next to current seasonal weather conditions with a level of accuracy will create the opportunity for preparedness and will result benefit to society as well as regional economy particularly for the country like Bangladesh that is vulnerable to various disasters related to weather and climate.\u003c/p\u003e\u003cp\u003eSeasonal weather forecasting takes a different approach compare to short duration weather forecast. Rather than relying on rapidly changing initial weather states, seasonal forecasts leverage slowly varying climate drivers. For example, researchers have found large-scale climate oscillations like ENSO (El Ni\u0026ntilde;o\u0026ndash;Southern Oscillation) is one of the key drivers of seasonal weather as well as climate pattern. The difference in sea level pressure between Tahiti in the eastern Pacific Ocean and Darwin in the western Pacific Ocean indicates the atmospheric component of ENSO, which is the focus of SOI. El Nino phases are indicated by negative SOI values, whereas La Nina phases are indicated by positive values. (Fang et al., \u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e2022\u003c/span\u003e; Jaroszewicz et al., \u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e2024\u003c/span\u003e; Power \u0026amp; Kociuba, \u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e2011\u003c/span\u003e). With a cycle of two to seven years, it is the most common periodic climate pattern and results from the interaction of the tropical Pacific Ocean's atmosphere and ocean. Its occurrence in the tropical Pacific Ocean determines whether it is considered eastern or central Pacific, and its influence spreads globally, causing variations in rainfall, temperature, and other factors (Sattar et al., \u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e2021\u003c/span\u003e).\u003c/p\u003e\u003cp\u003eENSO has three stages: the neutral phase is in between the extreme El Nino and La Nina phases (Ibebuchi \u0026amp; Richman, \u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e2024\u003c/span\u003e; Mir et al., \u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e2024\u003c/span\u003e). El Nino can be described by the central and eastern tropical Pacific Ocean\u0026rsquo;s Sea surface temperatures being higher than normal, which weakens trade winds. La Nina, that produces the opposite weather pattern of El Nino, is characterized by sea surface temperatures that are lower than usual in the same area of the Pacific Ocean. The phenomenon known as the \"neutral phase,\" which is neither El Nino nor La Nina, occurs when sea surface temperatures are almost average [12]. The ONI (Oceanic Nino Index), on the other hand, is NOAA's primary indicator of the oceanic component of ENSO. It measures mean sea surface temperature anomalies in the central and eastern tropical Pacific Ocean (Nino 3.4 region, 5\u0026deg;N-5\u0026deg;S, 120\u0026deg;-170\u0026deg;W) over a 3-month period. El Nino phases are indicated by ONI values of +\u0026thinsp;0.5 or higher, and La Nina phases by values of -0.5 or lower. A full-fledged El Nino or La Nina would develop if these anomalies persisted for at least five months in a row (Capotondi et al., \u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e2015\u003c/span\u003e). In the same location as ONI, Nino 3.4 SST shows 5-month running mean SST anomalies. It is the indicator most frequently used to characterize the ENSO phase (Fang et al., \u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e2022\u003c/span\u003e). Prior research finds only a modest correlation between Bangladesh\u0026rsquo;s summer monsoon rainfall and the Ni\u0026ntilde;o3.4 index (Ehsan et al., \u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e2023b\u003c/span\u003e). Additional important factors that can affect not only the ENSO phenomenon but the entire climatic pattern includes the Indian Ocean Dipole (IOD), Pacific Decadal Oscillation (PDO), Bivariate ENSO Timeseries (BEST), Trans-Nino Index (TNI), Pacific North American (PNA) pattern, and 200mb Zonal Winds as suggested from several literature.\u003c/p\u003e\u003cp\u003eIOD represents the discrepancy between SST anomalies in the western equatorial Indian Ocean (50\u0026deg;E to 70\u0026deg;E and 10\u0026deg;S to 10\u0026deg;N) and eastern equatorial Indian Ocean (90\u0026deg;E to 110\u0026deg;E and 10\u0026deg;S to 0\u0026deg;S). A positive IOD term is identified by warmer than average tropical western Indian Ocean and cooler than average water tropical eastern Indian Ocean. During this period, Indonesia and Australia are prone to be more arid than normal increasing the probability of bushfires. Conversely, eastern Africa is prone to be more moist than normal, increasing the chances of floods. Similarly, a negative IOD results an opposite (Forootan et al., \u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e2016\u003c/span\u003e). PDO index on the other hand can be treated as an effective indicator of ENSO-like Pacific climate convertibility. The PDO fluctuates approximately every 20 to 30 years.(Newman et al., \u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e2003\u003c/span\u003e) Two extreme phases of the PDO are warm or cool, depending on the oceanic temperature variation in the northeast and tropical Pacific Ocean. The PDO index seems to be positive when SST values are abnormally cold inside the North Pacific and torrid towards the Pacific Coast, and sea surface pressures are very low over the North Pacific. Similarly, the reverse situation indicates a negative PDO index.\u003c/p\u003e\u003cp\u003eAnother index, BEST makes the calculation simpler and provides a long-period ENSO index. By considering the SOI along with Nino 3.4 SST, the impact of SST data skewness induced by alteration is minimized. High and low values are taken into account for differentiating El Nino and La Nina events respectively, and close to zero indicate ENSO-neutral phases. Since any of SOI and Nino 3.4 SST can be dominating, it would be more accurate to use the months that conform to both high Nino3.4 SST and low SOI or vice versa (Wei, \u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e2024\u003c/span\u003e). TNI is introduced to define the unique character of each El Nino or La Nina event. It refers to the difference in normalized SST anomalies between the Ni\u0026ntilde;o 1\u0026thinsp;+\u0026thinsp;2 and Ni\u0026ntilde;o 4 regions and thus measures the gradient in SST anomalies between the central and eastern equatorial Pacific (Kao et al., 2009). PNA denotes a climatic pattern related to the air circulation over the North Pacific Ocean to that over the North American continent. This index is measured by the geopotential elevation anomalies (generally at 500 and 700 mb) over the western and eastern United States (\u003cem\u003ePacific North American Index (PNA)\u003c/em\u003e, n.d.). According to the previous research, PNA is strongly influenced by the ENSO phenomenon. (Li et al., \u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e2019\u003c/span\u003e) The positive PNA can be characterized by the above-average pressure near Hawaii and across the mountainous region of western North America, along with the below-average pressure south of Alaska and over the southeastern United States, which are generally associated with Pacific warm episodes or El Nino. The opposite scenario is observed in the same region during negative PNA patterns, which tend to occur during Pacific cold episodes or La Nina (\u003cem\u003eClimate Variability: Pacific\u0026ndash;North American Pattern | NOAA Climate.Gov\u003c/em\u003e, n.d.). The zonal wind speed indicates winds blowing horizontally along the latitude lines, rather than the vertical winds. The role of 200mb Zonal Winds is highly significant in the ENSO phenomenon. Zonal winds weaken in the central Pacific during El Nino while it strengthens in the same region in La Nina.\u003c/p\u003e\u003cp\u003eAccording to a recent study, the efficiency and overall performance of Nino 3.4 SST index-based models have declined due to inconsistent performance of the models. Multi-model ensemble system comparisons were done in a study (Barnston et al., \u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e2019\u003c/span\u003e). The model\u0026rsquo;s performance can decrease due to the change in the dynamics of ENSO indices. Since the very beginning, both dynamical models and statistical models have been used to predict El Nino events (Chen et al., \u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e2024\u003c/span\u003e; Latif et al., \u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e1994\u003c/span\u003e; Yeh \u0026amp; Kirtman, \u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e2007\u003c/span\u003e). Errors are greatly amplified due to the coupled feedback in the equatorial ocean-atmosphere system in spring, resulting in the phenomenon of the Spring Predictability Barrier. (Duan \u0026amp; Wei, \u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e2013\u003c/span\u003e) That is also a reason why prediction accuracy is not satisfactory in statistical models. To obtain higher accuracy, more development is necessary along with regular ENSO index models. In comparison to linear regression model predictions, the LSTM machine learning model outperforms them. (Song et al., \u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e2023\u003c/span\u003e) Machine learning-based models are more suitable as they can establish relationships between input and output parameters regardless of the complexity. However, there have been numerous studies conducted on unsupervised machine learning and deep learning techniques, less attention was paid to supervised machine learning models. Supervised machine learning models can also accurately predict extreme weather events and their intensity. For rainfall prediction, an analysis conducted in a previous study revealed that the Random Forest model to be the most accurate for rainfall prediction in the respective research area (Saleh \u0026amp; Rasel, \u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e2024\u003c/span\u003e). Besides, the majority of the existing research concentrates on a single index and short-term predictions. Because of this, the incorporation of multiple indices into the machine learning model remains unexplored properly. ENSO indices, such as SOI, ONI, and Nino 3.4 SST reflects specific elements of the ENSO phenomenon while other indices, such as IOD, PDO, TNI, etc. offer insights into more general regional and global climate dynamics.\u003c/p\u003e\u003cp\u003eThese considerations raise three pressing research questions. First, how do ENSO indices affect the seasonal weather patterns of Bangladesh? While previous studies suggest modest to moderate correlations between ENSO phases and monsoon rainfall, the physical mechanisms and predictive strength of these relationships remain under-explored, particularly across different seasons and events within Bangladesh. Second, given the growing interest in data-driven methods, should we explore the suitability of machine learning (ML) models in the context of seasonal weather forecasting? ML models are known to handle nonlinear, high-dimensional data and may capture complex interactions between ENSO indices and local climate variability patterns that often elude traditional statistical or physics-based models. Third, are machine learning models truly worth considering for operational seasonal weather forecasting in Bangladesh? This question requires a careful comparison: how well can ML models, trained on historical ENSO and climate data, predict seasonal outcomes such as rainfall and temperature? Can they offer better solution than existing forecasting methods?\u003c/p\u003e\u003cp\u003eThis study solely focuses on these gaps in the prediction of seasonal weather patterns, and ENSO indices. This endeavor seeks to employ a number of models, including K-Fold Cross-Validation, Random Forest, Decision Tree, Linear Regression, XGBoost, and K-Nearest Neighbors, for performance analysis in order to determine which model would be most appropriate for these situations by examining Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Coefficient of Determination (R\u003csup\u003e2\u003c/sup\u003e). Besides, inclusion of multiple indices in this study improves the model's capacity to represent the complicated relationships between oceanic and atmospheric systems that affect seasonal weather patterns. Therefore, the study aims to predict the temperature and rainfall by establishing a relationship between ENSO indices and seasonal climatic parameters.\u003c/p\u003e"},{"header":"2. Methodology","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e\u003ch2\u003e2.1. Dataset and Study Area\u003c/h2\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eFour datasets of monthly maximum temperature, monthly minimum temperature, monthly average temperature and monthly average rainfall intensity have been processed using the data of 29 stations covering entire Bangladesh. The stations are namely, Barisal, Bhola, Bogra, Chandpur, Chittagong, Comilla, Cox's Bazar, Dhaka, Dinajpur, Faridpur, Feni, Hatiya, Ishurdi, Jessore, Khepupara, Khulna, M.Court, Madaripur, Mymensingh, Patuakhali, Rajshahi, Rangamati, Rangpur, Sandwip, Satkhira, Sitakunda, Srimangal, Sylhet, Teknaf.\u003c/p\u003e\u003cp\u003eAll the datasets also contain nine ENSO indices. They are ONI, NINO 3.4 SST, SOI, IOD, PDO, BEST, PNA, TNI, and 200mb Zonal Winds. Besides, each dataset also contains other parameters such as Year, Month, Season, Dominant Cycle, ENSO Event and its Intensity.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec4\" class=\"Section2\"\u003e\u003ch2\u003e2.2. Data Source\u003c/h2\u003e\u003cp\u003eThe ENSO indices were taken from the National Weather Service Climate Prediction Center and the datasets of temperature and rainfall were taken from the Bangladesh Agricultural Research Council (BARC). Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e represents an overview of the data type, data source, period, and unit.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eData Overview by Type, Source, Period, and Unit\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"4\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eData Type\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eData source\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003ePeriod\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eUnit\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eENSO Indices\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.cpc.ncep.noaa.gov\u003c/span\u003e\u003cspan address=\"https://www.cpc.ncep.noaa.gov\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e1977\u0026ndash;2022\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e-\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eTemperature\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://barc.gov.bd/\u003c/span\u003e\u003cspan address=\"https://barc.gov.bd/\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e1977\u0026ndash;2022\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u0026deg;C\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRainfall\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://barc.gov.bd/\u003c/span\u003e\u003cspan address=\"https://barc.gov.bd/\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e1977\u0026ndash;2022\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003emm\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec5\" class=\"Section2\"\u003e\u003ch2\u003e2.3. Workflow\u003c/h2\u003e\u003cp\u003eThe research workflow began with framing the problem and understanding the types of data required. Then, the required data were collected. Subsequently, data pre-processing was conducted to handle duplicate \u0026amp; missing values and remove outliers. After pre-processing, the exploratory data analysis (EDA) was conducted. In the EDA, Univariate, Bi-variate, and multi-variate analysis was carried out. EDA helps to understand the data, find the correlation among them and facilitate the model selection. Before feeding the data to train the model, data post-processing is required. Data post-processing is also known as \u0026lsquo;Feature Engineering\u0026rsquo;. Feature engineering was required for encoding categorical data and scaling the numerical data. Then, all the datasets were divided into two parts to train and validate the model. 70% of the total data were used to train the model and later, 30% of the total data were used to validate the model. Then, the models were assessed by using three performance metrics, namely Mean absolute error (MAE), root mean squared error (RMSE), and coefficient of determination (R\u003csup\u003e2\u003c/sup\u003e) metrics. Finally, a comparison was demonstrated between actual scenario to predicted scenario, which highlighted the worthiness of the ML model.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec6\" class=\"Section2\"\u003e\u003ch2\u003e2.4. Model Selection\u003c/h2\u003e\u003cp\u003eDecision tree is an improved supervised learning algorithm. Because each branch in this model represents an attribute value and each incremental node evaluates a property, the structure is remarkably similar to a tree, and each leaf node stands for the final assessment or prediction that is used to both regression and classification. The classification and regression tree (CART) is the modern term for the decision tree. Decision trees are associated with a few important terms. A sample is said to be a \"root node\" if it is divided into two or more homogeneous sets. A node can be broken into multiple smaller nodes. When sub-nodes split into further sub-nodes, decision nodes are produced. (Liu, 2025)\u003c/p\u003e\u003cp\u003eRandom Forest mixes several decision trees to forecast more precise outcomes for a given problem. It is among the most popular methods since it can be applied to regression analysis and several decision trees are created during the training stage in order to arrive at a shared result. To create a single tree, a random dataset is used. The decision tree model has a danger of overfitting, however, this issue is fixed by using random datasets in random forests, which lowers the risk of overfitting while simultaneously enhancing performance. The Random Forest method votes or, in the case of regression, averages the decisions made by all the trees. (Biau \u0026amp; Fr, \u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e2012\u003c/span\u003e)\u003c/p\u003e\u003cp\u003eLinear regression is a supervised machine learning technique that establishes a linear relationship between dependent and one or more independent variables by means of fitting a linear equation by observed data. The aim while using linear regression is to find the best-fit line, which implies that the error between the predicted and actual values should be kept to a minimum. There will be the least error in the best-fit line. The best-fit line equation provides a straight line that represents the relationship between the dependent and independent variables. Linear regression performs the task of predicting a dependent variable value (y) based on a given independent variable (x)). That is the reason why, it is named linear regression. (Starbuck, \u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e2023\u003c/span\u003e)\u003c/p\u003e\u003cp\u003eXGBoost refers to extreme gradient boosting which is a type of ensemble learning. The concept of ensemble learning is a combination of all the advantages of different machine learning models which can achieve better results than other models alone. By combining the decisions or predictions of normal weak models, XGBoost makes the best possible prediction. The optimization method (gradient) repeatedly changes the model\u0026rsquo;s parameters in response to the gradients of the errors. The algorithm also presents the idea of \u0026ldquo;gradient boosting with decision trees,\u0026rdquo; in which the importance of the decision trees is measured and added to the ensemble in turn. By adding a regularization term and utilizing a more advanced optimization algorithm, XGBoost goes one step further and improves accuracy and efficiency. Combining both regularization and shrinkage along with pruning technique, XGBoost avoids overfitting. (Kuthuru, \u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e2025\u003c/span\u003e)\u003c/p\u003e\u003cp\u003eK-Fold cross-validation is a repetitive method used to assess the performance of machine learning models. The dataset is split into k equal parts called k fold in which each fold is used for testing and the remaining k-1 fold is used for training purposes. The procedure is iterated k-times by changing the training and testing datasets, and, the best model is selected based on the minimum error between calculated and estimated parameters using RMSE. It provides a reliable estimate of model performance and minimizes the risk of overfitting. (Nti et al., \u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e2021\u003c/span\u003e)\u003c/p\u003e\u003cp\u003eThe K-Nearest Neighbors (KNN) algorithm is a supervised machine-learning technique used for both classification and regression tasks. Known for its simplicity and ease of implementation, KNN does not rely on assumptions about the data's underlying distribution. It can manage both numerical and categorical data, making it a versatile option for various datasets. As a non-parametric method, it makes predictions by evaluating the similarity between data points in a given dataset. Additionally, KNN tends to be less sensitive to outliers compared to other algorithms. The K-NN algorithm works by finding the K nearest neighbors to a given data point based on a distance metric, such as Euclidean distance, Manhattan Distance, Minkowski Distance, etc. The class or value of the data point is then determined by the majority vote or average of the K neighbors. This approach allows the algorithm to adapt to different patterns and make predictions based on the local structure of the data. The value of k is very crucial in the KNN algorithm to define the number of neighbors in the algorithm. It is recommended to choose an odd value for k to avoid ties in classification. (Halder et al., \u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e2024\u003c/span\u003e)\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec7\" class=\"Section2\"\u003e\u003ch2\u003e2.5. Model Training and Validation\u003c/h2\u003e\u003cp\u003eThis study utilized a data-driven methodology to examine the influence of 13 critical climate indices, including the Year, Month, ONI, NINO 3.4 SST, SOI, IOD, PDO, PNA, TNI, BEST, 200mb Zonal Winds, ENSO Events, and their intensity. A data partitioning strategy was adopted, dividing the dataset into training (70%) and validation (30%) subsets, in line with standard practices in machine learning research (Douglass, \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e2020\u003c/span\u003e; Tareq, \u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e2024\u003c/span\u003e). This splitting approach aimed to mitigate the risk of overfitting by ensuring the model's generalizability through performance assessment on unseen data (Sarker, \u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e2021\u003c/span\u003e).\u003c/p\u003e\u003cp\u003eThe trained model was then subjected to rigorous evaluation on the independent validation set to measure its predictive accuracy and uncover potential biases. Such practices align with recommendations by leading machine learning practitioners to ensure robust model validation and avoid spurious conclusions in predictive studies (Wu \u0026amp; Vos, \u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e2018\u003c/span\u003e). To evaluate the models, three widely used statistical metrics were employed: Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and the Coefficient of Determination (R\u0026sup2;). These metrics provide complementary insights into model accuracy and predictive performance.\u003c/p\u003e\u003cdiv id=\"Sec8\" class=\"Section3\"\u003e\u003ch2\u003e2.5.1. Mean Absolute Error (MAE)\u003c/h2\u003e\u003cp\u003eThe Mean Absolute Error (MAE) measures the average magnitude of absolute errors between the predicted and actual values, providing a straightforward interpretation of prediction accuracy. Lower MAE values indicate better model performance, as they signify smaller deviations from the observed data.\u003cdiv id=\"Equ1\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ1\" name=\"EquationSource\"\u003e\n$$\\:\\varvec{M}\\varvec{A}\\varvec{E}\\:=\\:\\frac{1}{\\varvec{n}}\\sum\\:_{\\varvec{i}=1}^{\\varvec{n}}\\left|{\\varvec{y}}_{\\varvec{i}}-{\\widehat{\\varvec{y}}}_{\\varvec{i}}\\right|$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e1\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec9\" class=\"Section3\"\u003e\u003ch2\u003e2.5.2. Root Mean Squared Error (RMSE)\u003c/h2\u003e\u003cp\u003eThe Root Mean Squared Error (RMSE) is the square root of the mean of the squared differences between the predicted and observed values. It penalizes larger errors more heavily due to the squaring operation. A lower RMSE value indicates higher model accuracy. However, as RMSE is scale-dependent, it is most effective when the errors follow a normal distribution.\u003cdiv id=\"Equ2\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ2\" name=\"EquationSource\"\u003e\n$$\\:\\varvec{R}\\varvec{M}\\varvec{S}\\varvec{E}=\\sqrt{\\frac{\\sum\\:_{\\varvec{i}=1}^{\\varvec{n}}{\\left({\\varvec{y}}_{\\varvec{i}}-{\\widehat{\\varvec{y}}}_{\\varvec{i}}\\right)}^{2}}{\\varvec{n}}}$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e2\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec10\" class=\"Section3\"\u003e\u003ch2\u003e2.5.3. Coefficient of Determination (R\u003csup\u003e2\u003c/sup\u003e)\u003c/h2\u003e\u003cp\u003eThe Coefficient of Determination (R\u0026sup2;) quantifies the proportion of variance in the dependent variable that is explained by the independent variables in the model. Its value ranges from 0 to 1, with values closer to 1 indicating better predictive power. However, higher R\u0026sup2; values may sometimes indicate overfitting, especially when the model performs exceptionally well on training data but poorly on unseen data.\u003cdiv id=\"Equ3\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ3\" name=\"EquationSource\"\u003e\n$$\\:{\\varvec{R}}^{2}=1-\\frac{\\sum\\:_{\\varvec{i}=1}^{\\varvec{n}}{\\left({\\varvec{y}}_{\\varvec{i}}-{\\widehat{\\varvec{y}}}_{\\varvec{i}}\\right)}^{2}}{\\sum\\:_{\\varvec{i}=1}^{\\varvec{n}}{\\left({\\varvec{y}}_{\\varvec{i}}-{\\stackrel{-}{\\varvec{y}}}_{\\varvec{i}}\\right)}^{2}}$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e3\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e"},{"header":"3. Results and Discussion","content":"\u003cdiv id=\"Sec12\" class=\"Section2\"\u003e\u003ch2\u003e3.1. Data Pre-processing\u003c/h2\u003e\u003cp\u003eDuring the data preprocessing phase, we identified a few instances of null values within the dataset. However, no duplicate entries were detected. Given the limited number of null values, we opted to remove the corresponding rows entirely to ensure data integrity. This was achieved using the dropna function provided by the Pandas library, which allowed us to eliminate rows containing null values efficiently. This approach preserved the overall quality and consistency of the dataset while minimizing the impact of missing data on subsequent analyses. After completing the data cleaning process, the temperature datasets were reduced to dimensions of 539 rows and 47 columns, while the rainfall dataset was reduced to dimensions of 527 rows and 47 columns.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec13\" class=\"Section2\"\u003e\u003ch2\u003e3.2. Exploratory Data Analysis (EDA)\u003c/h2\u003e\u003cp\u003eTo gain a comprehensive understanding of the dataset, exploratory data analysis (EDA) was conducted. This study involved univariate, bivariate, and multivariate analyses to examine the data from different perspectives and identify underlying patterns.\u003c/p\u003e\u003cdiv id=\"Sec14\" class=\"Section3\"\u003e\u003ch2\u003e3.2.1. Univariate Analysis\u003c/h2\u003e\u003cp\u003eFor categorical variables, such as ENSO Event, and Season, monthly count plots were generated to analyze their frequency distributions. For numerical variables, Kernel Density Estimate (KDE) plots were utilized to examine the data distribution.\u003c/p\u003e\u003cp\u003eFigure 3 highlights La Nina events occur more frequently than El Nino and Neutral events, showing variability in the ENSO Events. On the other hand, Fig.\u0026nbsp;4 shows the Neutral events have the highest frequency, followed by Weak El Nino. Besides, Very Strong El Nino have much lower counts, indicating they are less frequent.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eFigure \u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e5\u003c/span\u003e represents the Neutral - Neutral phase condition is dominant with a higher frequency compared to remaining conditions. This suggests a higher occurrence of Neutral \u0026ndash; Neutral conditions in the dataset and highlights the count of occurrences for different seasons. The El Nino - Neutral, Neutral - El Nino, Neutral - La Nina, La Nina - Neutral has the lowest count.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eFigure \u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e6\u003c/span\u003e visualizes the distribution of different ENSO indices. The indices ONI, SOI, IOD, PDO, BEST, PNA, and TNI exhibit peaks near zero, with their distributions demonstrating approximate symmetry. This observation indicates that these indices may closely follow a normal distribution. Therefore, normalization of these data is not required.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec15\" class=\"Section3\"\u003e\u003ch2\u003e3.2.2. Bi-variate Analysis\u003c/h2\u003e\u003cp\u003eFigure \u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e7\u003c/span\u003e illustrates the distribution of ENSO events (El Nino, Neutral, and La Nina) across four seasons: Winter, Pre monsoon, Monsoon, and Post monsoon. In all seasons except Post monsoon, Neutral events exhibit the highest frequency, while El Nino events are the least common. But, La Nina events have the highest frequency in the Post monsoon.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eFigure \u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e8\u003c/span\u003e depicts the phase condition across different seasons. In all four seasons, fewer phase changes are observed, indicating that most conditions remained stable. The figure also highlights that there were no direct transitions from El Nino to La Nina or vice versa.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec16\" class=\"Section3\"\u003e\u003ch2\u003e3.2.3. Multi-variate Analysis\u003c/h2\u003e\u003cp\u003eIn this study, multivariate analysis is applied to explore the relationships between ENSO indices and weather parameters across 29 stations. To gain more specific insights, the datasets for T\u003csub\u003emax\u003c/sub\u003e, T\u003csub\u003emin\u003c/sub\u003e, T\u003csub\u003eavg\u003c/sub\u003e, and Rainfall were divided into eight ENSO events: Weak El Nino, Moderate El Nino, Strong El Nino, Very Strong El Nino, Neutral, Weak La Nina, Moderate La Nina, and Strong La Nina, facilitating a detailed examination of event-specific correlations. This approach enhances the precision of the analysis, uncovering complicated associations that deepen the understanding of how ENSO indices influence regional climate variability.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eFigure \u003cspan refid=\"Fig7\" class=\"InternalRef\"\u003e9\u003c/span\u003e shows the correlation between various climate indices and rainfall across different regions during strong La Nina events. Notably, IOD and TNI exhibit strong negative correlations in most regions, indicating reduced rainfall influence. PNA shows a consistently strong positive correlation, especially in southeastern areas. NINO 3.4 SST also shows moderate positive correlations. These patterns suggest that during strong La Nina, regional rainfall is more strongly influenced by IOD, PNA, and TNI.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eFigure \u003cspan refid=\"Fig8\" class=\"InternalRef\"\u003e10\u003c/span\u003e shows strong correlations between climate indices and minimum temperature during strong La Nina events. PNA exhibits a consistently strong positive correlation across all regions, while IOD and TNI show strong negative correlations, indicating significant influence on minimum temperature. NINO 3.4 SST also shows moderate to strong positive correlations. Overall, the pattern suggests that during strong La Nina, PNA, IOD, and TNI play key roles in shaping minimum temperature variations.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eFigure \u003cspan refid=\"Fig9\" class=\"InternalRef\"\u003e11\u003c/span\u003e shows how average temperature in different parts of Bangladesh relates to various climate factors during strong El Nino events. The PDO has the strongest and most consistent positive relationship with temperature across all stations. NINO 3.4 SST, TNI, and upper-level winds also show clear positive links, especially in eastern regions. In contrast, the PNA index is linked with lower temperatures. Some indices like ONI, SOI, and BEST have little or no clear effect. The color scale makes it easy to compare the strength and direction of these relationships.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eFigure \u003cspan refid=\"Fig10\" class=\"InternalRef\"\u003e12\u003c/span\u003e shows how maximum temperature (T\u003csub\u003emax\u003c/sub\u003e) in Bangladesh correlates with climate indices during strong El Nino events. NINO 3.4 SST, PDO, and TNI have positive moderate correlations across all stations.\u003c/p\u003e\u003cp\u003e*** Here, four correlation heatmaps derived from four datasets\u0026mdash;T\u003csub\u003emax\u003c/sub\u003e, T\u003csub\u003emin\u003c/sub\u003e, T\u003csub\u003eavg\u003c/sub\u003e, and Rainfall\u0026mdash;for four significant ENSO events were presented. The remaining correlation heatmaps are included in the annexure for reference. In total, 32 correlation heatmaps were generated, encompassing all combinations of the four datasets across the dfferent ENSO events, to comprehensively analyze the relationships between ENSO indices and climate variables across Bangladesh. ***\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv id=\"Sec17\" class=\"Section2\"\u003e\u003ch2\u003e3.3. Feature Engineering\u003c/h2\u003e\u003cp\u003eTo prepare the dataset for machine learning modeling, several preprocessing techniques were applied to handle categorical variables and scale numerical features. The steps are outlined below:\u003c/p\u003e\u003cdiv id=\"Sec18\" class=\"Section3\"\u003e\u003ch2\u003e3.3.1. Categorical Feature Encoding\u003c/h2\u003e\u003cp\u003eThe dataset contained categorical variables, including SEASON, and ENSO Event, which required transformation into a numerical format. One-hot encoding was applied to these categorical features using the \u003cb\u003eOneHotEncoder\u003c/b\u003e function from Scikit-learn. To prevent multicollinearity, the first category of each feature was dropped (i.e., drop='first' was used), ensuring that redundant dummy variables were eliminated. The encoded categorical features were then concatenated with the original dataset after removing the respective categorical columns.\u003c/p\u003e\u003cp\u003e\u003cb\u003eFeature Selection\u003c/b\u003e\u003c/p\u003e\u003cp\u003eAfter encoding, non-informative columns such as Index, Phase Change, and Phase Duration were excluded from the dataset. The dataset was then split into input features (X) and target variables (\u0026#119910;). Specifically, the input features (X) were obtained by removing the dependent variables, while the target variables (y) were extracted by selecting relevant columns from the dataset.\u003c/p\u003e\u003cp\u003e\u003cb\u003eData Scaling\u003c/b\u003e\u003c/p\u003e\u003cp\u003eTo standardize the numerical features and improve the performance of machine learning models, feature scaling was applied. Standard scaling was performed using the \u003cb\u003eStandardScaler\u003c/b\u003e function from Scikit-learn, which transforms the data to have a mean of 0 and a standard deviation of 1. The scaler was fitted on the training data, and the same transformation was applied to the test data to maintain consistency.\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv id=\"Sec19\" class=\"Section2\"\u003e\u003ch2\u003e3.4. Model Performance Evaluation\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003ePerformance Comparison of Machine Learning Models for Predicting Climate Variable\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"8\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003ePerformance Metrics\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003eDataset\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"6\" nameend=\"c8\" namest=\"c3\"\u003e\u003cp\u003eModel Name\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eRandom Forest Regressor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eDecision Tree Regressor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eK fold Cross validation\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eXGBoosting\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eLinear Regression\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eKNN Regressor\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"3\" rowspan=\"4\"\u003e\u003cp\u003e\u003cb\u003eR2 Score\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003eT\u003c/b\u003e\u003csub\u003e\u003cb\u003emax\u003c/b\u003e\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.8512\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.7918\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.7751\u0026thinsp;\u0026plusmn;\u0026thinsp;0.0318\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.8509\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.6425\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.6095\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003eT\u003c/b\u003e\u003csub\u003e\u003cb\u003emin\u003c/b\u003e\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.9693\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.9584\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.9787\u0026thinsp;\u0026plusmn;\u0026thinsp;0.0054\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.9702\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.9679\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.8589\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003eT\u003c/b\u003e\u003csub\u003e\u003cb\u003eavg\u003c/b\u003e\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.9521\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.9386\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.9456\u0026thinsp;\u0026plusmn;\u0026thinsp;0.0115\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.9559\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.8472\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.7873\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003eRainfall\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.6253\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.6146\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.6216\u0026thinsp;\u0026plusmn;\u0026thinsp;0.0235\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.5897\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.5662\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.4325\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"3\" rowspan=\"4\"\u003e\u003cp\u003e\u003cb\u003eMAE\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003eT\u003c/b\u003e\u003csub\u003e\u003cb\u003emax\u003c/b\u003e\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.7921\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.9195\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.9423\u0026thinsp;\u0026plusmn;\u0026thinsp;0.0599\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.7889\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e1.1940\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e1.2683\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003eT\u003c/b\u003e\u003csub\u003e\u003cb\u003emin\u003c/b\u003e\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.5144\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.6243\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.5149\u0026thinsp;\u0026plusmn;\u0026thinsp;0.0542\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.5120\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.5529\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e1.2357\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003eT\u003c/b\u003e\u003csub\u003e\u003cb\u003eavg\u003c/b\u003e\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.5719\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.6563\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.6449\u0026thinsp;\u0026plusmn;\u0026thinsp;0.0537\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.5479\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e1.0951\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e1.2344\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003eRainfall\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e94.3346\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e94.9789\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e85.6627\u0026thinsp;\u0026plusmn;\u0026thinsp;5.4976\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e101.2635\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e107.4055\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e125.6424\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"3\" rowspan=\"4\"\u003e\u003cp\u003e\u003cb\u003eRMSE\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003eT\u003c/b\u003e\u003csub\u003e\u003cb\u003emax\u003c/b\u003e\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e1.0180\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1.2043\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e1.2812\u0026thinsp;\u0026plusmn;\u0026thinsp;0.1035\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e1.0252\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e1.5982\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e1.6749\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003eT\u003c/b\u003e\u003csub\u003e\u003cb\u003emin\u003c/b\u003e\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.7772\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.9042\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.6917\u0026thinsp;\u0026plusmn;\u0026thinsp;0.0785\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.7678\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.7953\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e1.6955\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003eT\u003c/b\u003e\u003csub\u003e\u003cb\u003eavg\u003c/b\u003e\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.7644\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.8630\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.8764\u0026thinsp;\u0026plusmn;\u0026thinsp;0.0720\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.7316\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e1.3677\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e1.6149\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003eRainfall\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e149.2662\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e152.6571\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e135.9836\u0026thinsp;\u0026plusmn;\u0026thinsp;7.6475\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e154.7295\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e161.8352\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e188.6645\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e presents the performance of six machine learning models, Random Forest Regressor, Decision Tree Regressor, K-Fold Cross Validation, XGBoosting, Linear Regression, and KNN Regressor, evaluated across four datasets: T\u003csub\u003emax\u003c/sub\u003e, T\u003csub\u003emin\u003c/sub\u003e, T\u003csub\u003eavg\u003c/sub\u003e, and Rainfall. Three metrics are used: R\u0026sup2; Score, MAE (Mean Absolute Error), and RMSE (Root Mean Square Error). The best-performing model is Random Forest in predicting T\u003csub\u003emax\u003c/sub\u003e, with an R\u0026sup2; score of 0.8512, the MAE of 0.7921, and RMSE of 1.0180. Similarly, Random Forest also excels in predicting Rainfall, achieving the highest R\u0026sup2; score (0.6253), the MAE (94.3346), and the RMSE (149.2662). On the other hand, XGBoosting leads for T\u003csub\u003eavg\u003c/sub\u003e dataset, with an R\u0026sup2; score of 0.9559, the MAE (0.5479), and RMSE of 0.7316. XGBoosting shows superior performance in T\u003csub\u003emin\u003c/sub\u003e prediction, achieving the best balance across metrics with an R\u0026sup2; score of 0.9702, an MAE of 0.5120, and RMSE of 0.7316.\u003c/p\u003e\u003cp\u003eThe XGBoosting model performed best for T\u003csub\u003emin\u003c/sub\u003e and T\u003csub\u003eavg\u003c/sub\u003e due to the consistency in these datasets. These datasets exhibit stable patterns, allowing XGBoost's gradient boosting approach to effectively capture and predict the underlying relationships with high precision. Its ability to handle non-linear relationships and outliers and fine-tune its performance through regularization further contributes to its success. The Random Forest Regressor excelled in predicting T\u003csub\u003emax\u003c/sub\u003e and Rainfall, despite the dataset's random variability. Random Forest's ensemble approach, which combines predictions from multiple decision trees, effectively handles random variations and avoids overfitting. This robustness makes it ideal for datasets with less predictable patterns.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eComparison between Actual and Predicted Scenario under Different Conditions\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"10\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c10\" colnum=\"10\"\u003e\u003c/div\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003eSeason\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003ePhase\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c4\" namest=\"c3\"\u003e\u003cp\u003eRainfall\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c6\" namest=\"c5\"\u003e\u003cp\u003eT\u003csub\u003eavg\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c8\" namest=\"c7\"\u003e\u003cp\u003eT\u003csub\u003emin\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c10\" namest=\"c9\"\u003e\u003cp\u003eT\u003csub\u003emax\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eActual\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003ePredicted\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eActual\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003ePredicted\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eActual\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003ePredicted\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eActual\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003ePredicted\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"6\" rowspan=\"7\"\u003e\u003cp\u003eWinter\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eEl Nino - El Nino\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eBoth\u003csup\u003e3\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eIncrease\u003csup\u003e2\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eDecrease\u003csup\u003e1\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eEl Nino - Neutral\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eNeutral - Neutral\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eNeutral - La Nina\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLa Nina - La Nina\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLa Nina - Neutral\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eNeutral - El Nino\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"6\" rowspan=\"7\"\u003e\u003cp\u003ePre Monsoon\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eEl Nino - El Nino\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eEl Nino - Neutral\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eNeutral - Neutral\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eNeutral - La Nina\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLa Nina - La Nina\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLa Nina - Neutral\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eNeutral - El Nino\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"6\" rowspan=\"7\"\u003e\u003cp\u003eMonsoon\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eEl Nino - El Nino\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eEl Nino - Neutral\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eNeutral - Neutral\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eNeutral - La Nina\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLa Nina - La Nina\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLa Nina - Neutral\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eNeutral - El Nino\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"6\" rowspan=\"7\"\u003e\u003cp\u003ePost Monsoon\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eEl Nino - El Nino\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eEl Nino - Neutral\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eNeutral - Neutral\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eNeutral - La Nina\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLa Nina - La Nina\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eBoth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLa Nina - Neutral\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eNeutral - El Nino\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eDecrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eIncrease\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"10\"\u003e\u003csup\u003e\u003cb\u003e1\u003c/b\u003e\u003c/sup\u003e\u003cb\u003eDecrease\u003c/b\u003e = The probability is higher for the case where the actual or predicted value of the output parameters (Rainfall, T\u003csub\u003eavg\u003c/sub\u003e, T\u003csub\u003emin\u003c/sub\u003e, T\u003csub\u003emax\u003c/sub\u003e) is smaller than the respective 10-year average value during the respective season\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd colspan=\"10\"\u003e\u003csup\u003e\u003cb\u003e2\u003c/b\u003e\u003c/sup\u003e\u003cb\u003eIncrease\u003c/b\u003e = The probability is higher for the case where the actual or predicted value of the output parameters (Rainfall, T\u003csub\u003eavg\u003c/sub\u003e, T\u003csub\u003emin\u003c/sub\u003e, T\u003csub\u003emax\u003c/sub\u003e) is greater than the respective 10-year average value during the respective season\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd colspan=\"10\"\u003e\u003csup\u003e\u003cb\u003e3\u003c/b\u003e\u003c/sup\u003e\u003cb\u003eBoth\u003c/b\u003e = The probability is almost same for both cases\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003eThe Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e presents a comparative analysis between actual observations and Random Forest model predictions of key climate variables, Rainfall, Average Temperature (T\u003csub\u003eavg\u003c/sub\u003e), Minimum Temperature (T\u003csub\u003emin\u003c/sub\u003e), and Maximum Temperature (T\u003csub\u003emax\u003c/sub\u003e), across different ENSO (El Ni\u0026ntilde;o\u0026ndash;Southern Oscillation) phases and four seasonal periods: Winter, Pre-Monsoon, Monsoon, and Post-Monsoon. The changes are evaluated relative to the average of the preceding ten years, with classifications as \"Increase\", \"Decrease\", or \"Both\" (indicating uncertainty or variability).\u003c/p\u003e\u003cp\u003eCritically, the model demonstrates moderate alignment with actual trends, particularly for temperature variables (T\u003csub\u003eavg\u003c/sub\u003e, T\u003csub\u003emin\u003c/sub\u003e, T\u003csub\u003emax\u003c/sub\u003e), where the predicted direction often matches the observed change. However, prediction accuracy appears more varied for rainfall, which shows several mismatches or uncertain classifications (\"Both\"), reflecting the complex and nonlinear nature of precipitation dynamics. Some combinations (e.g., La Nina \u0026ndash; El Nino in Pre-Monsoon) show high concordance across all variables, while others (e.g., Neutral \u0026ndash; Neutral in Post-Monsoon) reflect greater ambiguity.\u003c/p\u003e\u003c/div\u003e"},{"header":"4. Conclusion","content":"\u003cp\u003eThis study investigated the intricate connections between ENSO indices and seasonal weather patterns across Bangladesh, leveraging supervised machine learning models to predict rainfall and temperature variations. By integrating historical climate data from 29 meteorological stations and nine ENSO-related indices over 45 years (1977\u0026ndash;2022), the research provides robust insights into the impact of large-scale ocean-atmosphere phenomena on local climate variability. Univariate and bivariate analyses revealed that La Nina events occurred more frequently, while Neutral phases dominated in terms of intensity. The multivariate correlation analysis across different ENSO phases and seasonal datasets underscored significant associations, particularly during strong El Nino and La Nina events. Variables like NINO 3.4 SST, SOI, PDO, and TNI exhibited consistent correlations with rainfall and temperature parameters, revealing their influence on regional climate anomalies. Six machine learning models were evaluated using R\u0026sup2;, MAE, and RMSE metrics for four key climate datasets: T\u003csub\u003emax\u003c/sub\u003e, T\u003csub\u003emin\u003c/sub\u003e, T\u003csub\u003eavg\u003c/sub\u003e, and Rainfall. Among them, XGBoost demonstrated the highest accuracy for T\u003csub\u003emin\u003c/sub\u003e (R\u0026sup2; = 0.9702) and T\u003csub\u003eavg\u003c/sub\u003e (R\u0026sup2; = 0.9559), whereas Random Forest was most effective for T\u003csub\u003emax\u003c/sub\u003e (R\u0026sup2; = 0.8512) and Rainfall (R\u0026sup2; = 0.6253).\u003c/p\u003e\u003cp\u003eA comparative analysis between actual observations and Random Forest model predictions across ENSO phases and seasonal periods further validated the model's effectiveness. The predictions showed strong alignment with actual trends for temperature variables (T\u003csub\u003eavg\u003c/sub\u003e, T\u003csub\u003emin\u003c/sub\u003e, T\u003csub\u003emax\u003c/sub\u003e), while rainfall predictions were more uncertain due to their inherent variability. In the winter season, predictions show a decrease in the average temperature across all the ENSO phases. T\u003csub\u003emin\u003c/sub\u003e, and T\u003csub\u003emax\u003c/sub\u003e are forecasted to decline during transitions like Neutral\u0026ndash;La Nina, La Nina\u0026ndash;Neutral, and Neutral\u0026ndash;El Nino phases. Rainfall is forecasted to increase in the El Nino\u0026ndash;El Nino, and El Nino\u0026ndash;Neutral phases. These forecasts suggest that colder and drier conditions are expected in the winter season during ENSO transitions involving La Nina. Moving into the pre-monsoon season, the forecasts predict a consistent increase in the average temperature across all the ENSO phases. Rainfall predictions are more varied, but generally follow an increasing trend during transitions such as Neutral\u0026ndash;La Nina, and Neutral\u0026ndash;El Nino. This suggests that pre-monsoon conditions are likely to be hotter and wetter, especially when the ENSO phase shifts away from neutrality. In the monsoon season, seasonal forecasts indicate continued warming, particularly in T\u003csub\u003eavg\u003c/sub\u003e and T\u003csub\u003emin\u003c/sub\u003e, which are predicted to increase under almost every ENSO phases, T\u003csub\u003emax\u003c/sub\u003e is mostly predicted to decrease, pointing to a possible narrowing of the daily temperature range. During the post-monsoon season, predicted patterns are more mixed. Transitions like Neutral\u0026ndash;El Nino show a consistent increase in all parameters, suggesting a warmer and wetter late season. In contrast, phases such as El Nino\u0026ndash;Neutral, Neutral\u0026ndash;La Nina, and La Nina\u0026ndash;Neutral are predicted to bring decreases in rainfall and temperature, indicating a return to cooler, drier conditions.\u003c/p\u003e\u003cp\u003eIn summary, temperature trends are consistently forecasted, with T\u003csub\u003eavg\u003c/sub\u003e and T\u003csub\u003emin\u003c/sub\u003e increasing in most seasons and transitions. Rainfall predictions are more variable, but tend to rise during La Nina-related transitions and decline during shifts involving El Nino. This highlights both the model\u0026rsquo;s strengths in capturing temperature dynamics and its limitations in handling nonlinear rainfall patterns. Besides, these forecasted trends demonstrate the usefulness of seasonal weather forecasting in anticipating climate-driven variations, supporting informed planning in agriculture, infrastructure, and disaster preparedness in Bangladesh. Reliable seasonal forecasts can guide farmers in crop planning, assist policymakers in developing early warning systems, and support infrastructure development to mitigate climate risks. Conducted with the goal of enhancing climate resilience and promoting evidence-based decision-making, this study offers valuable insights for meteorologists, researchers, government agencies, and disaster management authorities. Looking ahead, future research should focus on incorporating satellite and remote sensing data, expanding the scope of climate indices, applying advanced deep learning models such as LSTM or hybrid networks, and simulating extreme weather scenarios like droughts and floods. These improvements will further strengthen model performance and contribute to the development of robust strategies for mitigating the socio-economic impacts of climate variability in Bangladesh and other ENSO-prone regions.\u003c/p\u003e\u003cp\u003e\u003cb\u003eAuthor Contributions Statement\u003c/b\u003e:\u003c/p\u003e\u003cp\u003e\u003cem\u003eM.M.: Conceptualization, Data sourcing \u0026amp; collection, Data processing, Analysis, Validation, Visualization, Result interpretation, Design, Writing \u0026ndash; original draft, Writing \u0026ndash; review \u0026amp; editing\u003c/em\u003e\u003c/p\u003e\u003cp\u003e\u003cem\u003eT.G.: Conceptualization, Data sourcing \u0026amp; collection, Data processing, Analysis, Validation, Visualization, Result interpretation, Design, Writing \u0026ndash; original draft, Writing \u0026ndash; review \u0026amp; editing\u003c/em\u003e\u003c/p\u003e\u003cp\u003e\u003cem\u003eF.A.: Conceptualization, Data sourcing \u0026amp; collection, Design, Writing \u0026ndash; original draft, Writing \u0026ndash; review \u0026amp; editing\u003c/em\u003e\u003c/p\u003e\u003cp\u003e\u003cem\u003eS.S: Conceptualization, Data sourcing \u0026amp; collection, Design, Writing \u0026ndash; original draft, Writing \u0026ndash; review \u0026amp; editing\u003c/em\u003e\u003c/p\u003e\u003cp\u003e\u003cem\u003eM.R.A.M.: Conceptualization, Supervision, Writing \u0026ndash; review \u0026amp; editing\u003c/em\u003e\u003c/p\u003e"},{"header":"Declarations","content":"\u003ch3\u003e\u003cstrong\u003eAuthor Contributions Statement:\u003c/strong\u003e\u003c/h3\u003e\n\u003cp\u003e\u003cem\u003eM.M.: Conceptualization, Data sourcing \u0026amp; collection, Data processing, Analysis, Validation, Visualization, Result interpretation, Design, Writing \u0026ndash; original draft, Writing \u0026ndash; review \u0026amp; editing\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eT.G.: Conceptualization, Data sourcing \u0026amp; collection, Data processing, Analysis, Validation, Visualization, Result interpretation, Design, Writing \u0026ndash; original draft, Writing \u0026ndash; review \u0026amp; editing\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eF.A.: Conceptualization, Data sourcing \u0026amp; collection, Design, Writing \u0026ndash; original draft, Writing \u0026ndash; review \u0026amp; editing \u0026nbsp;\u0026nbsp;\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eS.S:\u0026nbsp;\u003c/em\u003e\u003cem\u003eConceptualization, Data sourcing \u0026amp; collection, Design, Writing \u0026ndash; original draft, Writing \u0026ndash; review \u0026amp; editing \u0026nbsp;\u0026nbsp;\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eM.R.A.M.: Conceptualization, Supervision, Writing \u0026ndash; review \u0026amp; editing\u003c/em\u003e\u003c/p\u003e\n\u003ch3\u003e\u003cstrong\u003eFunding Statement:\u003c/strong\u003e\u003c/h3\u003e\n\u003cp\u003e\u003cem\u003eThe authors declare that no funds, grants, or other support were received during the preparation of this manuscript.\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData Availability:\u003cbr\u003e\u003c/strong\u003e\u003cem\u003eThe datasets analyzed during the current study are not publicly available due to confidentiality agreements and institutional data-sharing restrictions, but are available from the corresponding author on reasonable request.\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent to Publish declaration:\u003c/strong\u003e \u003cem\u003eNot applicable.\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent to Participate declaration:\u003c/strong\u003e \u003cem\u003eNot applicable\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthics declaration:\u003c/strong\u003e \u003cem\u003eNot applicable\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCompeting Interests:\u0026nbsp;\u003c/strong\u003e\u003cem\u003eThe authors have no relevant financial or non-financial interests to disclose\u003c/em\u003e.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eAhmed R, Kim IK. Patterns of Daily Rainfall in Bangladesh During the Summer Monsoon Season: Case Studies at Three Stations. Phys Geogr. 2003;24(4):295\u0026ndash;318. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.2747/0272-3646.24.4.295\u003c/span\u003e\u003cspan address=\"10.2747/0272-3646.24.4.295\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eAmin A, Mourshed M. Weather and climate data for energy applications. Renew Sustain Energy Rev. 2024;192:114247. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/J.RSER.2023.114247\u003c/span\u003e\u003cspan address=\"10.1016/J.RSER.2023.114247\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eBarnston AG, Tippett MK, Ranganathan M, L\u0026rsquo;Heureux ML. Deterministic skill of ENSO predictions from the North American Multimodel Ensemble. Clim Dyn. 2019;53(12):7215\u0026ndash;34. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s00382-017-3603-3\u003c/span\u003e\u003cspan address=\"10.1007/s00382-017-3603-3\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eBiau G, Fr GB. (2012). Analysis of a Random Forests Model. In J Mach Learn Res (13).\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eCapotondi A, Wittenberg AT, Newman M, Di Lorenzo E, Yu JY, Braconnot P, Cole J, Dewitte B, Giese B, Guilyardi E, Jin FF, Karnauskas K, Kirtman B, Lee T, Schneider N, Xue Y, Yeh SW. Understanding enso diversity. Bull Am Meteorol Soc. 2015;96(6):921\u0026ndash;38. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1175/BAMS-D-13-00117.1\u003c/span\u003e\u003cspan address=\"10.1175/BAMS-D-13-00117.1\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eChen S, Chen W, Xie SP, Yu B, Wu R, Wang Z, Lan X, Graf HF. Strengthened impact of boreal winter North Pacific Oscillation on ENSO development in warming climate. Npj Clim Atmospheric Sci. 2024;7(1). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1038/s41612-024-00615-3\u003c/span\u003e\u003cspan address=\"10.1038/s41612-024-00615-3\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003e\u003cem\u003eClimate Variability: Pacific\u0026ndash;North American Pattern | NOAA Climate.gov\u003c/em\u003e. (n.d.). Retrieved August 31, 2024, from \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.climate.gov/news-features/understanding-climate/climate-variability-pacific-north-american-pattern\u003c/span\u003e\u003cspan address=\"https://www.climate.gov/news-features/understanding-climate/climate-variability-pacific-north-american-pattern\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eDouglass MJJ. (2020). Book Review: Hands-on Machine Learning with Scikit-Learn, Keras, and Tensorflow, 2nd edition by Aur\u0026eacute;lien G\u0026eacute;ron. \u003cem\u003ePhysical and Engineering Sciences in Medicine\u003c/em\u003e, \u003cem\u003e43\u003c/em\u003e(3), 1135\u0026ndash;1136. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s13246-020-00913-z\u003c/span\u003e\u003cspan address=\"10.1007/s13246-020-00913-z\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eDuan W, Wei C. The spring predictability barrier for ENSO predictions and its possible mechanism: Results from a fully coupled model. Int J Climatol. 2013;33(5):1280\u0026ndash;92. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1002/joc.3513\u003c/span\u003e\u003cspan address=\"10.1002/joc.3513\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eEhsan MA, Tippett MK, Robertson AW, Singh B, Rahman MA. The ENSO Fingerprint on Bangladesh Summer Monsoon Rainfall. Earth Syst Environ. 2023a;7(3):617\u0026ndash;27. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s41748-023-00347-z\u003c/span\u003e\u003cspan address=\"10.1007/s41748-023-00347-z\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eEhsan MA, Tippett MK, Robertson AW, Singh B, Rahman MA. The ENSO Fingerprint on Bangladesh Summer Monsoon Rainfall. Earth Syst Environ. 2023b;7(3):617\u0026ndash;27. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/S41748-023-00347-Z/FIGURES/6\u003c/span\u003e\u003cspan address=\"10.1007/S41748-023-00347-Z/FIGURES/6\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eFang W, Sha Y, Sheng VS. Survey on the Application of Artificial Intelligence in ENSO Forecasting. Math 2022. 2022;10(20):3793. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3390/MATH10203793\u003c/span\u003e\u003cspan address=\"10.3390/MATH10203793\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. \u003cem\u003e10\u003c/em\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eForootan E, Khandu, Awange JL, Schumacher M, Anyah RO, van Dijk A, I. J. M, Kusche J. Quantifying the impacts of ENSO and IOD on rain gauge and remotely sensed precipitation products over Australia. Remote Sens Environ. 2016;172:50\u0026ndash;66. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/J.RSE.2015.10.027\u003c/span\u003e\u003cspan address=\"10.1016/J.RSE.2015.10.027\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHalder RK, Uddin MN, Uddin MA, Aryal S, Khraisat A. Enhancing K-nearest neighbor algorithm: a comprehensive review and performance analysis of modifications. J Big Data. 2024;11(1). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1186/s40537-024-00973-y\u003c/span\u003e\u003cspan address=\"10.1186/s40537-024-00973-y\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eIbebuchi CC, Richman MB. Deep learning with autoencoders and LSTM for ENSO forecasting. Clim Dyn. 2024. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s00382-024-07180-8\u003c/span\u003e\u003cspan address=\"10.1007/s00382-024-07180-8\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eIslam T, Saha S, Evan AA, Halder N, Dey SC. Monthly Weather Forecasting through ANN Model: A Case Study in Barisal, Bangladesh. IJARCCE. 2016;5(6):1\u0026ndash;6. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.17148/ijarcce.2016.5601\u003c/span\u003e\u003cspan address=\"10.17148/ijarcce.2016.5601\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eJaroszewicz S, Mariani MC, Tweneboah OK, Beccar-Varela MP. Multifractal analysis of the Southern Oscillation Index. J Atmos Solar Terr Phys. 2024;254:106161. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/J.JASTP.2023.106161\u003c/span\u003e\u003cspan address=\"10.1016/J.JASTP.2023.106161\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eKao HY, Yu JY. Contrasting Eastern-Pacific and Central-Pacific types of ENSO. J Clim. 2009;22(3):615\u0026ndash;32. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1175/2008JCLI2309.1\u003c/span\u003e\u003cspan address=\"10.1175/2008JCLI2309.1\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eKuthuru A. Semantic Data Contracts: A New Integration Paradigm for Enterprise AI and Database Systems. Eur J Comput Sci Inform Technol. 2025;13(31):1\u0026ndash;9. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.37745/ejcsit.2013/vol13n3119\u003c/span\u003e\u003cspan address=\"10.37745/ejcsit.2013/vol13n3119\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLatif M, Barnett TP, Cane MA, Fl\u0026uuml;gel M, Graham NE, von Storch H, Xu JS, Zebiak SE. A review of ENSO prediction studies. Clim Dyn. 1994;9(4\u0026ndash;5):167\u0026ndash;79. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/BF00208250/METRICS\u003c/span\u003e\u003cspan address=\"10.1007/BF00208250/METRICS\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLi X, Hu ZZ, Liang P, Zhu J. Contrastive Influence of ENSO and PNA on Variability and Predictability of North American Winter Precipitation. J Clim. 2019;32(19):6271\u0026ndash;84. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1175/JCLI-D-19-0033.1\u003c/span\u003e\u003cspan address=\"10.1175/JCLI-D-19-0033.1\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLiu Z. Leo. (2025). Decision Trees. Artif Intell Eng, 115\u0026ndash;28. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/978-3-031-75953-6_4\u003c/span\u003e\u003cspan address=\"10.1007/978-3-031-75953-6_4\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMir S, Arbab MA, Rehman Sur. ENSO dataset \u0026amp; comparison of deep learning models for ENSO forecasting. Earth Sci Inf. 2024;17(3):2623\u0026ndash;8. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s12145-024-01295-6\u003c/span\u003e\u003cspan address=\"10.1007/s12145-024-01295-6\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eNewman M, Compo GP, Alexander MA. ENSO-Forced Variability of the Pacific Decadal Oscillation. J Clim. 2003;16(23):3853\u0026ndash;7. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1175/1520-0442(2003)016%3C3853:EVOTPD%3E2.0.CO;2\u003c/span\u003e\u003cspan address=\"10.1175/1520-0442(2003)016%3C3853:EVOTPD%3E2.0.CO;2\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eNti IK, Nyarko-Boateng O, Aning J. Performance of Machine Learning Algorithms with Different K Values in K-fold CrossValidation. Int J Inform Technol Comput Sci. 2021;13(6):61\u0026ndash;71. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.5815/ijitcs.2021.06.05\u003c/span\u003e\u003cspan address=\"10.5815/ijitcs.2021.06.05\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003e\u003cem\u003ePacific North American Index (PNA)\u003c/em\u003e. (n.d.). Retrieved August 31, 2024, from \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.daculaweather.com/4_pna_index.php\u003c/span\u003e\u003cspan address=\"https://www.daculaweather.com/4_pna_index.php\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ePinheiro E, Ouarda TBMJ. (2025). An interpretable machine learning model for seasonal precipitation forecasting. \u003cem\u003eCommunications Earth \u0026amp; Environment 2025 6:1\u003c/em\u003e, \u003cem\u003e6\u003c/em\u003e(1), 1\u0026ndash;14. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1038/s43247-025-02207-2\u003c/span\u003e\u003cspan address=\"10.1038/s43247-025-02207-2\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ePower SB, Kociuba G. The impact of global warming on the Southern Oscillation Index. Clim Dyn. 2011;37(9\u0026ndash;10):1745\u0026ndash;54. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/S00382-010-0951-7/FIGURES/5\u003c/span\u003e\u003cspan address=\"10.1007/S00382-010-0951-7/FIGURES/5\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSaleh MA, Rasel HM. (2024). \u003cem\u003ePerformance evaluation of Machine Learning based regression models for rainfall forecasting\u003c/em\u003e. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.21203/RS.3.RS-3856741/V1\u003c/span\u003e\u003cspan address=\"10.21203/RS.3.RS-3856741/V1\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSarker IH. Machine Learning: Algorithms, Real-World Applications and Research Directions. SN Comput Sci. 2021;2(3):1\u0026ndash;21. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/S42979-021-00592-X/METRICS\u003c/span\u003e\u003cspan address=\"10.1007/S42979-021-00592-X/METRICS\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSattar MA, Mia S, Shanta AA, Ahad Biswas A, A. K. M., Ludwig F. Remote impacts from el ni\u0026ntilde;o and la ni\u0026ntilde;a on climate variables and major crops production in coastal bangladesh. Atmosphere. 2021;12(11). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3390/atmos12111449\u003c/span\u003e\u003cspan address=\"10.3390/atmos12111449\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSong WJ, Yu JY, Lian T. The efficacy of tropical and extratropical predictors for long-lead El Ni\u0026ntilde;o-Southern Oscillation prediction: A study using a machine learning algorithm. Int J Climatol. 2023;43(14):6887\u0026ndash;99. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1002/joc.8241\u003c/span\u003e\u003cspan address=\"10.1002/joc.8241\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eStarbuck C. (2023). Linear Regression. In \u003cem\u003eThe Fundamentals of People Analytics\u003c/em\u003e (pp. 181\u0026ndash;206). Springer International Publishing. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/978-3-031-28674-2_10\u003c/span\u003e\u003cspan address=\"10.1007/978-3-031-28674-2_10\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eTareq WZT. (2024). Deep learning. \u003cem\u003eDecision-Making Models: A Perspective of Fuzzy Logic and Machine Learning\u003c/em\u003e, 317\u0026ndash;327. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/B978-0-443-16147-6.00016-5\u003c/span\u003e\u003cspan address=\"10.1016/B978-0-443-16147-6.00016-5\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eWei L. Summary of Commonly Used ENSO Indices. Highlights Sci Eng Technol. 2024;88:687\u0026ndash;94. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.54097/VNDV3190\u003c/span\u003e\u003cspan address=\"10.54097/VNDV3190\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eWu Q, Vos P. Inference and Prediction. Handb Stat. 2018;38:111\u0026ndash;72. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/BS.HOST.2018.06.004\u003c/span\u003e\u003cspan address=\"10.1016/BS.HOST.2018.06.004\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eYeh SW, Kirtman BP. ENSO amplitude changes due to climate change projections in different coupled models. J Clim. 2007;20(2):203\u0026ndash;17. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1175/JCLI4001.1\u003c/span\u003e\u003cspan address=\"10.1175/JCLI4001.1\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"discover-environment","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Discover Environment](https://www.springer.com/44274/)","snPcode":"44274","submissionUrl":"https://submission.nature.com/new-submission/44274/3","title":"Discover Environment","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Seasonal weather patterns prediction, ENSO, Supervised machine learning, Temperature, Rainfall","lastPublishedDoi":"10.21203/rs.3.rs-7673222/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7673222/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe accurate prediction of seasonal weather patterns holds significant importance in supporting agriculture, disaster management, and economic planning in Bangladesh. However, the non-linear characteristics of weather and climatic patterns makes it quite challenging. Recently, the significant impact of El Nino-Southern Oscillation (ENSO) indices on regional climate variability have increasingly been recognized. This study investigates the correlation between nine ENSO indices and both temperature and rainfall patterns across Bangladesh and also evaluates the effectiveness of machine learning (ML) models in predicting these weather variables. Historical monthly data from 29 meteorological stations, spanning 1977 to 2022, were analyzed. Six supervised ML models\u0026mdash;Random Forest (RF), Decision Tree (DT), K-Fold Cross-Validation (KFCV), XGBoost (XGB), Linear Regression (LR), and K-Nearest Neighbors (KNN) were applied. Performance was evaluated using R\u0026sup2; score, Mean Absolute Error (MAE), and Root Mean Square Error (RMSE). Results revealed that ENSO indices have a notable impact on climate parameters in Bangladesh. Among these models, XGB achieved the highest R\u0026sup2; scores for temperature prediction, with values of 0.8824 (T\u003csub\u003emax\u003c/sub\u003e), 0.9706 (T\u003csub\u003emin\u003c/sub\u003e), and 0.9559 (T\u003csub\u003eavg\u003c/sub\u003e). RF and KFCV also showed strong performance, with RF achieving R\u0026sup2; values of 0.8770 (T\u003csub\u003emax\u003c/sub\u003e), 0.9699 (T\u003csub\u003emin\u003c/sub\u003e) and 0.9531 (T\u003csub\u003eavg\u003c/sub\u003e) and KFCV achieving R\u0026sup2; scores of 0.8606 (T\u003csub\u003emax\u003c/sub\u003e), 0.9619 (T\u003csub\u003emin\u003c/sub\u003e), and 0.9438 (T\u003csub\u003eavg\u003c/sub\u003e). Rainfall prediction, however, yielded lower accuracy, with RF recording the highest R\u0026sup2; of 0.6273. The study highlights the impact of ENSO indices and concludes that XGB, RF, and KFCV are highly effective in modeling seasonal climate patterns influenced by ENSO.\u003c/p\u003e","manuscriptTitle":"Seasonal Weather Pattern Prediction From Enso Indices Using Machine Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-17 12:22:51","doi":"10.21203/rs.3.rs-7673222/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-10-30T10:06:51+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-29T05:42:58+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"700560755351568037760096117344730173","date":"2025-10-22T09:24:25+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"318451670388125636134883915403293796782","date":"2025-10-11T14:55:34+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"66301654308891762925717387396703289622","date":"2025-10-09T07:24:24+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-09T02:28:36+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"276981419462992971585602343871203461865","date":"2025-10-08T18:17:53+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"60678728955294514388668320552556169062","date":"2025-10-07T14:47:00+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-10-06T14:45:56+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-10-06T07:35:36+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-26T14:28:22+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-26T14:27:06+00:00","index":"","fulltext":""},{"type":"submitted","content":"Discover Environment","date":"2025-09-22T09:37:41+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"discover-environment","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Discover Environment](https://www.springer.com/44274/)","snPcode":"44274","submissionUrl":"https://submission.nature.com/new-submission/44274/3","title":"Discover Environment","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"a4fd54ae-2967-433e-8840-447cd15ec889","owner":[],"postedDate":"October 17th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-01-13T06:53:59+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-17 12:22:51","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7673222","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7673222","identity":"rs-7673222","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}