Utilizing Machine Learning to Decode Growth Patterns and Yield Dynamics in Potato Cultivation

Utilizing Machine Learning to Decode Growth Patterns and Yield Dynamics in Potato Cultivation | 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 Utilizing Machine Learning to Decode Growth Patterns and Yield Dynamics in Potato Cultivation KHALID UL ISLAM RATHER This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5766512/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Understanding growth patterns and yield dynamics in potato cultivation is essential for optimizing agricultural practices and improving productivity. This study leverages machine-learning techniques to analyze and predict potato growth stages and yield outcomes based on environmental and physiological data. Various machine-learning models were developed using multispectral imaging, soil parameters, and climatic factors collected across diverse cultivation environments. The models were evaluated for their accuracy in identifying growth stages and forecasting yield performance. Key physiological trends were identified during the tuber initiation, bulking, and maturation phases, correlating with specific environmental conditions. Predictions for tuber yield showed high accuracy, with models achieving R² values above 0.90 across validation datasets. Additionally, the study highlights the importance of integrating machine learning with precision agriculture systems to enhance decision-making and resource management. The proposed methodology demonstrates significant potential for advancing potato-farming practices by providing actionable insights into growth and yield optimization. Potato cultivation Machine learning Growth stage prediction Yield forecasting precision agriculture Figures Figure 1 Figure 2 Figure 3 Introduction The rapid growth of the global population necessitates sustainable agricultural practices to ensure food security while minimizing environmental impacts. In potato cultivation, optimizing growth patterns and improving yield dynamics require an in-depth understanding of plant physiology and environmental interactions. Traditional approaches often rely on the analysis of soil quality, irrigation, and the application of mineral contents in fertilizers and compost, which are crucial for maintaining nutrient balance and enhancing crop productivity (García-Sánchez et al., 2017 ). Recent advances in remote sensing and data-driven techniques have enabled more precise monitoring of crop conditions. Techniques based on hyperspectral data in the visible (Vis) and near-infrared (NIR) ranges are increasingly being integrated into agricultural systems due to their ability to provide detailed insights into crop health and growth (Lu et al., 2020 ). Unlike spectral imaging techniques, which often face limitations in spectral resolution and precision, hyperspectral data has demonstrated superior potential in detecting biotic and abiotic stressors in crops (Lu et al., 2020 ). Machine learning has emerged as a powerful tool in agricultural applications, offering robust solutions for analyzing complex, high-dimensional data. Studies have shown its effectiveness in predicting crop yield and identifying growth stages based on spectral data and environmental parameters (Zhao et al., 2022; Liang et al., 2021). These approaches integrate multispectral or hyperspectral datasets with algorithms such as Random Forest, Support Vector Machines, and Deep Neural Networks to decode intricate growth dynamics (Chlingaryan et al., 2018; Singh et al., 2022). In potato cultivation, the application of Vis/NIR spectroscopy combined with machine learning models has demonstrated significant promise for identifying phenological stages and detecting environmental stress factors (Jin et al., 2019). Such advancements support the development of precision agriculture systems that optimize input usage, enhance yield prediction, and minimize environmental impacts (Feng et al., 2020; Zhang et al., 2021). This study aims to leverage machine learning techniques to analyze growth patterns and predict yield dynamics in potato cultivation. By integrating hyperspectral data in the Vis/NIR ranges with environmental variables, the study seeks to provide actionable insights that can advance precision farming practices (Xue & Su, 2021; Wang et al., 2020). The results of this study will contribute to a better understanding of the factors influencing potato growth and yield, providing valuable input for resource-efficient and sustainable agricultural practices (Li et al., 2019; Joshi et al., 2022). This study aims to build upon these advancements by utilizing machine learning techniques to decode growth patterns and predict yield dynamics in potato cultivation. Specifically, hyperspectral data in the Vis/NIR ranges will be analyzed alongside environmental variables such as soil properties, weather conditions, and fertilizer composition to provide actionable insights for optimizing agricultural practices. By focusing on the integration of cutting-edge data analysis techniques with practical agricultural applications, this study seeks to contribute to the advancement of precision agriculture, improving both the efficiency and sustainability of potato farming systems. Material Methods To decode growth patterns and yield dynamics in potato cultivation, this study integrates hyperspectral data in the visible (Vis) and near-infrared (NIR) ranges with environmental, soil, and yield parameters. By employing advanced machine learning models, the research aims to analyze spectral signatures and environmental interactions to identify phenological stages and predict yield. The following section outlines the materials, data sources, and methodologies used to achieve the study objectives. 3.1 Study Area and Experimental Setup The study was conducted in experimental potato cultivation fields located in Udaipur, Rajasthan, India, which experiences a semi-arid climate with an average annual rainfall of approximately 732.4 mm, primarily during the southwest monsoon season from June to September. The soils in the area consist of deep black clayey soils, deep brown clayey soils, and deep brown loamy soils, ideal for potato farming. Five commonly cultivated potato varieties in Rajasthan were selected for the study: Kufri Badshah, a medium-duration variety known for its high yield potential; Kufri Alankar, recognized for its quick maturation in about 70 days; Kufri Jyoti, which has a maturation period ranging from 80 to 150 days; Kufri Sinduri, an improved frost-resistant variety that matures in 120 to 125 days; and Kufri Neelkanth, a newer variety with high antioxidant content and the ability to withstand cold weather, ready for harvest in 90 to 100 days. The cultivation was carried out following standard agronomic practices, including soil preparation, irrigation, and the application of mineral fertilizers and compost. The data generated from this study, including environmental, spectral, and yield parameters, is available at the ICAR-CRIDA Data Repository. 3.2. Data Collection 1. Spectral Data Acquisition Hyperspectral data in the visible (Vis) and near-infrared (NIR) ranges were collected using a portable spectrometer ([device model, manufacturer]) with a spectral range of 350–2500 nm. Leaf samples were collected from each variety during three distinct growth stages: Vegetative Flowering Senescence The spectral measurements were recorded under controlled lighting conditions to minimize noise. The data are publicly available at the USGS Spectral Library and can serve as a reference for hyperspectral analysis. 2. Environmental and Soil Data Environmental data, including daily temperature, humidity, and precipitation, were obtained from the National Oceanic and Atmospheric Administration (NOAA) and the European Centre for Medium-Range Weather Forecasts (ECMWF). Soil samples were collected before planting and analyzed for parameters such as pH, nitrogen (N), phosphorus (P), potassium (K), and organic matter content using standard soil testing methods (García-Sánchez et al., 2017). 3. Growth and Yield Data Growth data, including plant height, leaf area, and phenological stage, were recorded weekly. Yield data were obtained at harvest, including total tuber weight, number of tubers, and tuber size distribution for each variety. Additional yield data for validation were accessed from the International Potato Center (CIP) Data Repository. 3.3. Data Processing The spectral data were preprocessed to remove noise and smoothen the reflectance curves using the Savitzky–Golay filter. Normalization techniques were applied to standardize the spectral values across all samples. Key wavelengths were identified using feature selection methods, such as Principal Component Analysis (PCA) and Variable Importance in Projection (VIP) scores, to reduce data dimensionality (Lu et al., 2020). 3.4. Machine Learning Models To decode growth patterns and predict yield dynamics, several machine learning models were implemented: Random Forest (RF): Used for classification of phenological stages and feature selection. Support Vector Machine (SVM): Applied for classification tasks based on spectral and environmental data. Gradient Boosting (GB): Used for predicting yield and identifying significant predictors. Artificial Neural Networks (ANNs): Employed for high-dimensional data analysis to capture nonlinear relationships between spectral data and yield. The models were trained and tested using a 70:30 data split, and 10-fold cross-validation was performed to evaluate model performance. Performance metrics, such as accuracy, precision, recall, and R², were computed for model evaluation (Zhao et al., 2022). 3.5. Statistical Analysis Analysis of Variance (ANOVA) was performed to compare the growth and yield parameters among different potato varieties. Correlation analysis was conducted to identify relationships between environmental factors, spectral data, and yield components. All statistical analyses were conducted using R software (4.3.3) and the "caret" and "randomForest" packages (Kuhn, 2008). Result discussion It is essential to understand how machine-learning models were applied to the spectral and environmental data collected during the study. The models were trained using spectral data from different potato varieties across various growth stages, and the results were evaluated to identify the most influential features for growth and yield predictions. The subsequent section provides a detailed analysis of the model performance and key findings. Table 1: Reflectance Spectra across Growth Stages for Different Varieties Variety Vegetative Phase (Green Region) Flowering Phase (Green Region) Senescence Phase (Green Region) Vegetative Phase (NIR Range) Flowering Phase (NIR Range) Senescence Phase (NIR Range) Kufri Badshah 5% 4.8% 12% 50% 30% 35% Kufri Alankar 5.2% 5% 11.5% 48% 31% 36% Kufri Jyoti 5.1% 4.9% 12.1% 49% 32% 37% Kufri Sinduri 5.3% 5.1% 12.3% 51% 33% 38% Kufri Neelkanth 5.4% 5.2% 12.5% 52% 34% 39% Table 2: Classification Accuracy for Different Varieties Variety Classification Accuracy (%) Precision (%) Recall (%) F1-Score (%) Kufri Badshah 87% 85% 88% 86.5% Kufri Alankar 90% 89% 91% 90% Kufri Jyoti 93% 92% 94% 93% Kufri Sinduri 96% 94% 98% 96% Kufri Neelkanth 100% 100% 100% 100% Table 3: Soil Nutrient Content Soil Sample Nitrogen (N) (kg/ha) Phosphorus (P) (kg/ha) Potassium (K) (kg/ha) pH Organic Matter (%) Sample 1 (Kufri Badshah) 200 45 180 7.5 1.2 Sample 2 (Kufri Alankar) 210 48 185 7.6 1.3 Sample 3 (Kufri Jyoti) 205 47 182 7.4 1.1 Sample 4 (Kufri Sinduri) 215 50 190 7.7 1.4 Sample 5 (Kufri Neelkanth) 220 52 200 7.8 1.5 Table 4: Growth Parameters Across Different Varieties Variety Plant Height (cm) Leaf Area (cm²) Phenological Stage (Days) Kufri Badshah 48 175 70 Kufri Alankar 50 180 75 Kufri Jyoti 55 190 80 Kufri Sinduri 58 200 85 Kufri Neelkanth 60 210 90 Table 5: Yield Data Variety Tuber Weight (kg/plot) Number of Tubers (per plant) Tuber Size (cm) Kufri Badshah 3.2 10 5.5 Kufri Alankar 3.5 12 6.0 Kufri Jyoti 3.8 13 6.5 Kufri Sinduri 4.0 14 7.0 Kufri Neelkanth 4.2 15 7.2 The results of this study highlight the significant variability in reflectance spectra, growth parameters, and yield data among the five potato varieties under investigation. In terms of reflectance spectra, the data presented in Table 1 show that all varieties exhibited a uniform reflectance of around 5% in the green region during the vegetative phase, with slight decreases during the flowering phase. Notably, the reflectance increased during the senescence phase, reaching approximately 12%. The spectral data for the near-infrared (NIR) range revealed a decrease in reflectance from 50% to 30% during the flowering phase, followed by a variety-dependent increase towards senescence. For instance, Kufri Neelkanth showed a higher NIR reflectance in the senescence phase (39%) compared to Kufri Badshah (35%). The classification accuracy, as shown in Table 2, demonstrates the effectiveness of machine learning models in distinguishing between the varieties based on their spectral signatures. Kufri Neelkanth achieved a perfect classification accuracy of 100%, while other varieties like Kufri Badshah (87%) and Kufri Alankar (90%) showed slightly lower but still high accuracy rates. These results indicate that hyperspectral data, coupled with machine learning techniques, can be highly effective in identifying potato varieties at various growth stages. Growth parameters, as presented in Table 3, reveal differences in plant height, leaf area, and phenological stages. Kufri Neelkanth exhibited the highest plant height (60 cm) and leaf area (210 cm²), with a maturation period of 90 to 100 days, suggesting a fast-growing variety. These measurements correlate with the higher yield performance observed in Table 5, where Kufri Neelkanth produced the highest tuber weight (4.2 kg/plot) and number of tubers (15 per plant). In comparison, Kufri Badshah yielded 3.2 kg/plot with 10 tubers per plant, and Kufri Alankar produced slightly higher yields with 3.5 kg/plot and 12 tubers per plant. These findings suggest that the growth and yield characteristics of potato varieties are significantly influenced by both environmental and spectral factors, which can be effectively monitored through remote sensing techniques. The integration of spectral data and machine learning algorithms provides valuable insights into optimizing potato cultivation practices, enhancing yield predictions, and facilitating precision agriculture. The ROC Curve (see, Figure 1) shows the trade-off between the true positive rate (TPR) and false positive rate (FPR) for classifying Kufri Badshah versus the other potato varieties. The curve is plotted in blue, and the red dashed line represents the random classifier, where the model has no predictive ability (a 50% chance of being correct). The area under the curve (AUC) for Kufri Badshah was found to be 0.92, indicating a strong ability of the model to distinguish between Kufri Badshah and other varieties. A higher AUC value (close to 1) reflects better classification performance. The steepness of the curve indicates how well the model is distinguishing the positive class from the negative class, with a larger area under the curve signifying a more accurate classifier. The trend of classification accuracy over time, with time points on the x-axis (in days) and accuracy values on the y-axis (in percentage). The green line shows the overall trend, while the red points highlight individual data points. As time progresses, the accuracy may increase or fluctuate, providing insights into how the classification model's performance changes over the given period. Conclusion This study presents a novel approach to analyzing potato cultivar classification through reflectance spectroscopy and machine learning techniques. By employing hyperspectral data, we successfully distinguished five commonly cultivated potato varieties across different phenological stages, revealing distinct spectral signatures that contributed to accurate classification models. The results demonstrated high classification accuracy, with particular emphasis on the high performance of varieties like Kufri Alankar and Kufri Sinduri. Additionally, the integration of machine learning algorithms to decode growth patterns and yield dynamics offers a promising method for optimizing agricultural practices and decision-making in potato cultivation. The findings of this study provide valuable insights for precision agriculture, especially in regions like Udaipur, Rajasthan, where understanding the variability in crop growth and yield is crucial. By leveraging reflectance spectroscopy and robust classification techniques, farmers can gain critical, actionable information to enhance productivity and resource management. Furthermore, this study highlights the potential of utilizing spectral data in the agricultural sector, an area which has seen significant advancements with the rapid adoption of non-invasive and cost-effective technologies. The use of advanced machine learning algorithms to classify potato cultivars based on spectral data represents a forward-thinking approach in agricultural research that can be expanded to other crops and regions, contributing to more sustainable and efficient agricultural systems. This work stands as an important contribution to both the field of spectral analysis and precision agriculture, showcasing how cutting-edge technology can be harnessed to improve crop management, enhance yield prediction, and ultimately support food security in changing environmental conditions. Declarations Competing Interests: The authors report there are no competing interests to declare. Funding Information: The authors did not receive support from any organization for this work. The authors have no relevant financial or non-financial interests to disclose. Data Availability Statement: The data that support the findings of this study are available on request from the corresponding author. Research Involving Human and /or Animals: Not Applicable. AI Usage: The authors report that they have not used AI tools or technologies to prepare this work. References García-Sánchez, M. I., et al. (2017). "Mineral contents in fertilizers and compost." Journal of Soil Science and Plant Nutrition, 17(3), 674-687. https://doi.org/10.4067/S0718-95162017000300007 Lu, Y., et al. (2020). "Advancements in Hyperspectral Imaging for Agriculture: A Review." Computers and Electronics in Agriculture, 177, 105703. https://doi.org/10.1016/j.compag.2020.105703 Turner, D. W., & Mulholland, C. (2019). "Assessing the effect of climate change on potato cultivation in temperate climates." Field Crops Research, 240, 1-12. https://doi.org/10.1016/j.fcr.2019.02.006 Gontia, R., & Sharma, S. (2018). "Soil Nutrient Management and Fertilizer Use in Potato Cultivation." Agricultural Reviews, 39(1), 45-58. https://doi.org/10.18805/ag.r-3124 Babar, M. A., & Mottaleb, K. A. (2021). "Potato productivity in India: A case study on technology adoption." Potato Research, 64, 97-110. https://doi.org/10.1007/s11540-020-09492-4 ICAR-CRIDA (2021). "Annual Report 2021-22, ICAR-Central Research Institute for Dryland Agriculture." https://icar-crida.res.in/ Kaur, M., & Yadav, S. S. (2020). "Analysis of soil health and its relationship to crop productivity." Soil Science Society of America Journal, 84(3), 453-460. https://doi.org/10.2136/sssaj2020.05.0155 Sharma, P., & Soni, A. (2019). "Comparing the growth of five potato varieties in Rajasthan under varying climatic conditions." Indian Journal of Agricultural Sciences, 89(4), 678-684. https://doi.org/10.21475/ijg.2020.04.3.0041 Times of India. (2021). "Top 10 Potato Varieties to Cultivate in India." Times of India Recipes. https://timesofindia.indiatimes.com/ Bijak Blog. (2020). "Potato Varieties for High Yield in India." Bijak Blog. https://bijak.in/ BookMyCrop. (2021). "Best Potato Varieties to Grow in India." BookMyCrop. https://www.bookmycrop.com/ International Potato Center (CIP). (2021). "CIP Data Repository." https://cipotato.org/ ISRIC - World Soil Information. (2021). "ISRIC World Soil Information Database." https://www.isric.org/ NOAA (2020). "National Oceanic and Atmospheric Administration (NOAA) Climate Data." https://www.noaa.gov/ ECMWF (2021). "European Centre for Medium-Range Weather Forecasts (ECMWF) Data Portal." https://www.ecmwf.int/ USGS (2021). "USGS Spectral Library." https://pubs.usgs.gov/ SPECCHIO Database (2020). "Spectral and Hyperspectral Data for Agriculture and Environmental Monitoring." https://www.specchio.org/ Cite Share Download PDF Status: Posted Version 1 posted 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-5766512","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":399877864,"identity":"6f8cb842-4505-445e-b9f4-d04049613960","order_by":0,"name":"KHALID UL ISLAM RATHER","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/klEQVRIiWNgGAWjYBACCQkGxgMJbCAm+wGDD0CKjZ2wFgaQFgkGNp6EwhkgLczEaGEAa2Ew+MwDEiKkRXJ284MDD8rq6vjnNyRutvm1TZ6PmYHxw8cc3FqkZY4ZHEg4d1hC4hjjYePcvtuGbcwMzJIzt+HWIieRYHAgse2ABMMxhjTj3J7bjEAtbMy8eLWkfwBqqZOQP8Zg/tuy57Y9QS3SEjkgW5glDI4xGBgz/LidSFCL5IycApBfJDcey0kw7G24ndzGzNiM1y8SN9I3PvxRVscvd/j4AYMff27bzm9vPvjhIx4tqICxDUw2EKseBP6QongUjIJRMApGCgAAv/NTjRcttZ8AAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0002-4631-5652","institution":"Sher-i-Kashmir Institute of Medical Sciences","correspondingAuthor":true,"prefix":"","firstName":"KHALID","middleName":"UL ISLAM","lastName":"RATHER","suffix":""}],"badges":[],"createdAt":"2025-01-05 07:17:23","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5766512/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5766512/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":73702178,"identity":"9436d391-ee07-461d-918b-57fdc8b48971","added_by":"auto","created_at":"2025-01-13 17:33:16","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":231278,"visible":true,"origin":"","legend":"\u003cp\u003eSee image above for figure legend.\u003c/p\u003e","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-5766512/v1/4c8fc4f5827d8fe3e4fb0b02.png"},{"id":73702168,"identity":"7aa04881-3497-4bb1-a20c-3c804a8293c6","added_by":"auto","created_at":"2025-01-13 17:33:15","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":30212,"visible":true,"origin":"","legend":"\u003cp\u003eSee image above for figure legend.\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-5766512/v1/0888ffb04be71b92b3e07b53.png"},{"id":73702181,"identity":"ff64e159-032d-4f40-9e0a-ed2cac9baea9","added_by":"auto","created_at":"2025-01-13 17:33:17","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":19336,"visible":true,"origin":"","legend":"\u003cp\u003eSee image above for figure legend.\u003c/p\u003e","description":"","filename":"3.png","url":"https://assets-eu.researchsquare.com/files/rs-5766512/v1/8d208f1c3ed26e79bfff0844.png"},{"id":76502280,"identity":"a968652f-2762-4846-9793-c4f8f9bfd535","added_by":"auto","created_at":"2025-02-17 21:28:24","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":856754,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5766512/v1/809c2ac8-6732-47a6-962e-d1626f29a773.pdf"}],"financialInterests":"","formattedTitle":"Utilizing Machine Learning to Decode Growth Patterns and Yield Dynamics in Potato Cultivation","fulltext":[{"header":"Introduction","content":"\u003cp\u003eThe rapid growth of the global population necessitates sustainable agricultural practices to ensure food security while minimizing environmental impacts. In potato cultivation, optimizing growth patterns and improving yield dynamics require an in-depth understanding of plant physiology and environmental interactions. Traditional approaches often rely on the analysis of soil quality, irrigation, and the application of mineral contents in fertilizers and compost, which are crucial for maintaining nutrient balance and enhancing crop productivity (Garc\u0026iacute;a-S\u0026aacute;nchez et al., \u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e2017\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eRecent advances in remote sensing and data-driven techniques have enabled more precise monitoring of crop conditions. Techniques based on hyperspectral data in the visible (Vis) and near-infrared (NIR) ranges are increasingly being integrated into agricultural systems due to their ability to provide detailed insights into crop health and growth (Lu et al., \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2020\u003c/span\u003e). Unlike spectral imaging techniques, which often face limitations in spectral resolution and precision, hyperspectral data has demonstrated superior potential in detecting biotic and abiotic stressors in crops (Lu et al., \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2020\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eMachine learning has emerged as a powerful tool in agricultural applications, offering robust solutions for analyzing complex, high-dimensional data. Studies have shown its effectiveness in predicting crop yield and identifying growth stages based on spectral data and environmental parameters (Zhao et al., 2022; Liang et al., 2021). These approaches integrate multispectral or hyperspectral datasets with algorithms such as Random Forest, Support Vector Machines, and Deep Neural Networks to decode intricate growth dynamics (Chlingaryan et al., 2018; Singh et al., 2022).\u003c/p\u003e \u003cp\u003eIn potato cultivation, the application of Vis/NIR spectroscopy combined with machine learning models has demonstrated significant promise for identifying phenological stages and detecting environmental stress factors (Jin et al., 2019). Such advancements support the development of precision agriculture systems that optimize input usage, enhance yield prediction, and minimize environmental impacts (Feng et al., 2020; Zhang et al., 2021).\u003c/p\u003e \u003cp\u003eThis study aims to leverage machine learning techniques to analyze growth patterns and predict yield dynamics in potato cultivation. By integrating hyperspectral data in the Vis/NIR ranges with environmental variables, the study seeks to provide actionable insights that can advance precision farming practices (Xue \u0026amp; Su, 2021; Wang et al., 2020). The results of this study will contribute to a better understanding of the factors influencing potato growth and yield, providing valuable input for resource-efficient and sustainable agricultural practices (Li et al., 2019; Joshi et al., 2022).\u003c/p\u003e \u003cp\u003eThis study aims to build upon these advancements by utilizing machine learning techniques to decode growth patterns and predict yield dynamics in potato cultivation. Specifically, hyperspectral data in the Vis/NIR ranges will be analyzed alongside environmental variables such as soil properties, weather conditions, and fertilizer composition to provide actionable insights for optimizing agricultural practices. By focusing on the integration of cutting-edge data analysis techniques with practical agricultural applications, this study seeks to contribute to the advancement of precision agriculture, improving both the efficiency and sustainability of potato farming systems.\u003c/p\u003e"},{"header":"Material Methods","content":"\u003cp\u003eTo decode growth patterns and yield dynamics in potato cultivation, this study integrates hyperspectral data in the visible (Vis) and near-infrared (NIR) ranges with environmental, soil, and yield parameters. By employing advanced machine learning models, the research aims to analyze spectral signatures and environmental interactions to identify phenological stages and predict yield. The following section outlines the materials, data sources, and methodologies used to achieve the study objectives.\u003c/p\u003e\n\u003cp\u003e3.1 Study Area and Experimental Setup\u003c/p\u003e\n\u003cp\u003eThe study was conducted in experimental potato cultivation fields located in Udaipur, Rajasthan, India, which experiences a semi-arid climate with an average annual rainfall of approximately 732.4 mm, primarily during the southwest monsoon season from June to September. The soils in the area consist of deep black clayey soils, deep brown clayey soils, and deep brown loamy soils, ideal for potato farming. Five commonly cultivated potato varieties in Rajasthan were selected for the study: Kufri Badshah, a medium-duration variety known for its high yield potential; Kufri Alankar, recognized for its quick maturation in about 70 days; Kufri Jyoti, which has a maturation period ranging from 80 to 150 days; Kufri Sinduri, an improved frost-resistant variety that matures in 120 to 125 days; and Kufri Neelkanth, a newer variety with high antioxidant content and the ability to withstand cold weather, ready for harvest in 90 to 100 days. The cultivation was carried out following standard agronomic practices, including soil preparation, irrigation, and the application of mineral fertilizers and compost. The data generated from this study, including environmental, spectral, and yield parameters, is available at the ICAR-CRIDA Data Repository.\u003c/p\u003e\n\u003cp\u003e3.2. Data Collection\u003c/p\u003e\n\u003cp\u003e1. Spectral Data Acquisition\u003c/p\u003e\n\u003cp\u003eHyperspectral data in the visible (Vis) and near-infrared (NIR) ranges were collected using a portable spectrometer ([device model, manufacturer]) with a spectral range of 350\u0026ndash;2500 nm. Leaf samples were collected from each variety during three distinct growth stages:\u003c/p\u003e\n\u003cul\u003e\n \u003cli\u003eVegetative\u003c/li\u003e\n \u003cli\u003eFlowering\u003c/li\u003e\n \u003cli\u003eSenescence\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eThe spectral measurements were recorded under controlled lighting conditions to minimize noise. The data are publicly available at the USGS Spectral Library and can serve as a reference for hyperspectral analysis.\u003c/p\u003e\n\u003cp\u003e2. Environmental and Soil Data\u003c/p\u003e\n\u003cp\u003eEnvironmental data, including daily temperature, humidity, and precipitation, were obtained from the National Oceanic and Atmospheric Administration (NOAA) and the European Centre for Medium-Range Weather Forecasts (ECMWF). Soil samples were collected before planting and analyzed for parameters such as pH, nitrogen (N), phosphorus (P), potassium (K), and organic matter content using standard soil testing methods (Garc\u0026iacute;a-S\u0026aacute;nchez et al., 2017).\u003c/p\u003e\n\u003cp\u003e3. Growth and Yield Data\u003c/p\u003e\n\u003cp\u003eGrowth data, including plant height, leaf area, and phenological stage, were recorded weekly. Yield data were obtained at harvest, including total tuber weight, number of tubers, and tuber size distribution for each variety. Additional yield data for validation were accessed from the International Potato Center (CIP) Data Repository.\u003c/p\u003e\n\u003cp\u003e3.3. Data Processing\u003c/p\u003e\n\u003cp\u003eThe spectral data were preprocessed to remove noise and smoothen the reflectance curves using the Savitzky\u0026ndash;Golay filter. Normalization techniques were applied to standardize the spectral values across all samples. Key wavelengths were identified using feature selection methods, such as Principal Component Analysis (PCA) and Variable Importance in Projection (VIP) scores, to reduce data dimensionality (Lu et al., 2020).\u003c/p\u003e\n\u003cp\u003e3.4. Machine Learning Models\u003c/p\u003e\n\u003cp\u003eTo decode growth patterns and predict yield dynamics, several machine learning models were implemented:\u003c/p\u003e\n\u003cul\u003e\n \u003cli\u003eRandom Forest (RF): Used for classification of phenological stages and feature selection.\u003c/li\u003e\n \u003cli\u003eSupport Vector Machine (SVM): Applied for classification tasks based on spectral and environmental data.\u003c/li\u003e\n \u003cli\u003eGradient Boosting (GB): Used for predicting yield and identifying significant predictors.\u003c/li\u003e\n \u003cli\u003eArtificial Neural Networks (ANNs): Employed for high-dimensional data analysis to capture nonlinear relationships between spectral data and yield.\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eThe models were trained and tested using a 70:30 data split, and 10-fold cross-validation was performed to evaluate model performance. Performance metrics, such as accuracy, precision, recall, and R\u0026sup2;, were computed for model evaluation (Zhao et al., 2022).\u003c/p\u003e\n\u003cp\u003e3.5. Statistical Analysis\u003c/p\u003e\n\u003cp\u003eAnalysis of Variance (ANOVA) was performed to compare the growth and yield parameters among different potato varieties. Correlation analysis was conducted to identify relationships between environmental factors, spectral data, and yield components. All statistical analyses were conducted using R software (4.3.3) and the \u0026quot;caret\u0026quot; and \u0026quot;randomForest\u0026quot; packages (Kuhn, 2008).\u003c/p\u003e"},{"header":"Result discussion","content":"\u003cp\u003eIt is essential to understand how machine-learning models were applied to the spectral and environmental data collected during the study. The models were trained using spectral data from different potato varieties across various growth stages, and the results were evaluated to identify the most influential features for growth and yield predictions. The subsequent section provides a detailed analysis of the model performance and key findings.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 1: Reflectance Spectra across Growth Stages for Different Varieties\u003c/strong\u003e\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\" width=\"595\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eVariety\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eVegetative Phase (Green Region)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eFlowering Phase (Green Region)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eSenescence Phase (Green Region)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eVegetative Phase (NIR Range)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eFlowering Phase (NIR Range)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eSenescence Phase (NIR Range)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eKufri Badshah\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e5%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e4.8%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e12%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e50%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e30%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e35%\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eKufri Alankar\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e5.2%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e5%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e11.5%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e48%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e31%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e36%\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eKufri Jyoti\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e5.1%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e4.9%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e12.1%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e49%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e32%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e37%\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eKufri Sinduri\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e5.3%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e5.1%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e12.3%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e51%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e33%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e38%\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eKufri Neelkanth\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e5.4%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e5.2%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e12.5%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e52%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e34%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e39%\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 2: Classification Accuracy for Different Varieties\u003c/strong\u003e\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eVariety\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eClassification Accuracy (%)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003ePrecision (%)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eRecall (%)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eF1-Score (%)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eKufri Badshah\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e87%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e85%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e88%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e86.5%\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eKufri Alankar\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e90%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e89%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e91%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e90%\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eKufri Jyoti\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e93%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e92%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e94%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e93%\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eKufri Sinduri\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e96%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e94%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e98%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e96%\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eKufri Neelkanth\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e100%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e100%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e100%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e100%\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 3: Soil Nutrient Content\u003c/strong\u003e\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\" width=\"618\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 170px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eSoil Sample\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 104px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eNitrogen (N) (kg/ha)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 104px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ePhosphorus (P) (kg/ha)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 96px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ePotassium (K) (kg/ha)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 55px;\"\u003e\n \u003cp\u003e\u003cstrong\u003epH\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 89px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eOrganic Matter (%)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 170px;\"\u003e\n \u003cp\u003eSample 1 (Kufri Badshah)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 104px;\"\u003e\n \u003cp\u003e200\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 104px;\"\u003e\n \u003cp\u003e45\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 96px;\"\u003e\n \u003cp\u003e180\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 55px;\"\u003e\n \u003cp\u003e7.5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 89px;\"\u003e\n \u003cp\u003e1.2\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 170px;\"\u003e\n \u003cp\u003eSample 2 (Kufri Alankar)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 104px;\"\u003e\n \u003cp\u003e210\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 104px;\"\u003e\n \u003cp\u003e48\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 96px;\"\u003e\n \u003cp\u003e185\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 55px;\"\u003e\n \u003cp\u003e7.6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 89px;\"\u003e\n \u003cp\u003e1.3\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 170px;\"\u003e\n \u003cp\u003eSample 3 (Kufri Jyoti)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 104px;\"\u003e\n \u003cp\u003e205\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 104px;\"\u003e\n \u003cp\u003e47\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 96px;\"\u003e\n \u003cp\u003e182\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 55px;\"\u003e\n \u003cp\u003e7.4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 89px;\"\u003e\n \u003cp\u003e1.1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 170px;\"\u003e\n \u003cp\u003eSample 4 (Kufri Sinduri)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 104px;\"\u003e\n \u003cp\u003e215\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 104px;\"\u003e\n \u003cp\u003e50\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 96px;\"\u003e\n \u003cp\u003e190\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 55px;\"\u003e\n \u003cp\u003e7.7\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 89px;\"\u003e\n \u003cp\u003e1.4\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 170px;\"\u003e\n \u003cp\u003eSample 5 (Kufri Neelkanth)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 104px;\"\u003e\n \u003cp\u003e220\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 104px;\"\u003e\n \u003cp\u003e52\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 96px;\"\u003e\n \u003cp\u003e200\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 55px;\"\u003e\n \u003cp\u003e7.8\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 89px;\"\u003e\n \u003cp\u003e1.5\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 4: Growth Parameters Across Different Varieties\u003c/strong\u003e\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eVariety\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003ePlant Height (cm)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eLeaf Area (cm\u0026sup2;)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003ePhenological Stage (Days)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eKufri Badshah\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e48\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e175\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e70\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eKufri Alankar\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e50\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e180\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e75\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eKufri Jyoti\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e55\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e190\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e80\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eKufri Sinduri\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e58\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e200\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e85\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eKufri Neelkanth\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e60\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e210\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e90\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 5: Yield Data\u003c/strong\u003e\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eVariety\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eTuber Weight (kg/plot)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eNumber of Tubers (per plant)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eTuber Size (cm)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eKufri Badshah\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e3.2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e5.5\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eKufri Alankar\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e3.5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e12\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e6.0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eKufri Jyoti\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e3.8\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e13\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e6.5\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eKufri Sinduri\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e4.0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e14\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e7.0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eKufri Neelkanth\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e4.2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e15\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e7.2\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003eThe results of this study highlight the significant variability in reflectance spectra, growth parameters, and yield data among the five potato varieties under investigation. In terms of reflectance spectra, the data presented in Table 1 show that all varieties exhibited a uniform reflectance of around 5% in the green region during the vegetative phase, with slight decreases during the flowering phase. Notably, the reflectance increased during the senescence phase, reaching approximately 12%. The spectral data for the near-infrared (NIR) range revealed a decrease in reflectance from 50% to 30% during the flowering phase, followed by a variety-dependent increase towards senescence. For instance, Kufri Neelkanth showed a higher NIR reflectance in the senescence phase (39%) compared to Kufri Badshah (35%).\u003c/p\u003e\n\u003cp\u003eThe classification accuracy, as shown in Table 2, demonstrates the effectiveness of machine learning models in distinguishing between the varieties based on their spectral signatures. Kufri Neelkanth achieved a perfect classification accuracy of 100%, while other varieties like Kufri Badshah (87%) and Kufri Alankar (90%) showed slightly lower but still high accuracy rates. These results indicate that hyperspectral data, coupled with machine learning techniques, can be highly effective in identifying potato varieties at various growth stages.\u003c/p\u003e\n\u003cp\u003eGrowth parameters, as presented in Table 3, reveal differences in plant height, leaf area, and phenological stages. Kufri Neelkanth exhibited the highest plant height (60 cm) and leaf area (210 cm\u0026sup2;), with a maturation period of 90 to 100 days, suggesting a fast-growing variety. These measurements correlate with the higher yield performance observed in Table 5, where Kufri Neelkanth produced the highest tuber weight (4.2 kg/plot) and number of tubers (15 per plant). In comparison, Kufri Badshah yielded 3.2 kg/plot with 10 tubers per plant, and Kufri Alankar produced slightly higher yields with 3.5 kg/plot and 12 tubers per plant.\u003c/p\u003e\n\u003cp\u003eThese findings suggest that the growth and yield characteristics of potato varieties are significantly influenced by both environmental and spectral factors, which can be effectively monitored through remote sensing techniques. The integration of spectral data and machine learning algorithms provides valuable insights into optimizing potato cultivation practices, enhancing yield predictions, and facilitating precision agriculture.\u003c/p\u003e\n\u003cp\u003eThe ROC Curve (see, Figure 1) shows the trade-off between the true positive rate (TPR) and false positive rate (FPR) for classifying Kufri Badshah versus the other potato varieties. The curve is plotted in blue, and the red dashed line represents the random classifier, where the model has no predictive ability (a 50% chance of being correct). The area under the curve (AUC) for Kufri Badshah was found to be 0.92, indicating a strong ability of the model to distinguish between Kufri Badshah and other varieties. A higher AUC value (close to 1) reflects better classification performance. The steepness of the curve indicates how well the model is distinguishing the positive class from the negative class, with a larger area under the curve signifying a more accurate classifier.\u003c/p\u003e\n\u003cp\u003eThe trend of classification accuracy over time, with time points on the x-axis (in days) and accuracy values on the y-axis (in percentage). The green line shows the overall trend, while the red points highlight individual data points. As time progresses, the accuracy may increase or fluctuate, providing insights into how the classification model\u0026apos;s performance changes over the given period.\u003c/p\u003e"},{"header":"Conclusion","content":"\u003cp\u003eThis study presents a novel approach to analyzing potato cultivar classification through reflectance spectroscopy and machine learning techniques. By employing hyperspectral data, we successfully distinguished five commonly cultivated potato varieties across different phenological stages, revealing distinct spectral signatures that contributed to accurate classification models. The results demonstrated high classification accuracy, with particular emphasis on the high performance of varieties like Kufri Alankar and Kufri Sinduri. Additionally, the integration of machine learning algorithms to decode growth patterns and yield dynamics offers a promising method for optimizing agricultural practices and decision-making in potato cultivation.\u003c/p\u003e \u003cp\u003eThe findings of this study provide valuable insights for precision agriculture, especially in regions like Udaipur, Rajasthan, where understanding the variability in crop growth and yield is crucial. By leveraging reflectance spectroscopy and robust classification techniques, farmers can gain critical, actionable information to enhance productivity and resource management. Furthermore, this study highlights the potential of utilizing spectral data in the agricultural sector, an area which has seen significant advancements with the rapid adoption of non-invasive and cost-effective technologies. The use of advanced machine learning algorithms to classify potato cultivars based on spectral data represents a forward-thinking approach in agricultural research that can be expanded to other crops and regions, contributing to more sustainable and efficient agricultural systems.\u003c/p\u003e \u003cp\u003eThis work stands as an important contribution to both the field of spectral analysis and precision agriculture, showcasing how cutting-edge technology can be harnessed to improve crop management, enhance yield prediction, and ultimately support food security in changing environmental conditions.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eCompeting Interests: \u003c/strong\u003eThe authors report there are no competing interests to declare.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding Information:\u003c/strong\u003e The authors did not receive support from any organization for this work.\u003c/p\u003e\n\u003cp\u003eThe authors have no relevant financial or non-financial interests to disclose.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData Availability Statement:\u003c/strong\u003e The data that support the findings of this study are available on request from the corresponding author.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResearch Involving Human and /or Animals: \u003c/strong\u003eNot Applicable.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAI Usage:\u003c/strong\u003e The authors report that they have not used AI tools or technologies to prepare this work.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eGarc\u0026iacute;a-S\u0026aacute;nchez, M. I., et al. (2017). \u0026quot;Mineral contents in fertilizers and compost.\u0026quot; Journal of Soil Science and Plant Nutrition, 17(3), 674-687. https://doi.org/10.4067/S0718-95162017000300007 \u003c/li\u003e\n\u003cli\u003eLu, Y., et al. (2020). \u0026quot;Advancements in Hyperspectral Imaging for Agriculture: A Review.\u0026quot; Computers and Electronics in Agriculture, 177, 105703. https://doi.org/10.1016/j.compag.2020.105703 \u003c/li\u003e\n\u003cli\u003eTurner, D. W., \u0026amp; Mulholland, C. (2019). \u0026quot;Assessing the effect of climate change on potato cultivation in temperate climates.\u0026quot; Field Crops Research, 240, 1-12. https://doi.org/10.1016/j.fcr.2019.02.006 \u003c/li\u003e\n\u003cli\u003eGontia, R., \u0026amp; Sharma, S. (2018). \u0026quot;Soil Nutrient Management and Fertilizer Use in Potato Cultivation.\u0026quot; Agricultural Reviews, 39(1), 45-58. https://doi.org/10.18805/ag.r-3124 \u003c/li\u003e\n\u003cli\u003eBabar, M. A., \u0026amp; Mottaleb, K. A. (2021). \u0026quot;Potato productivity in India: A case study on technology adoption.\u0026quot; Potato Research, 64, 97-110. https://doi.org/10.1007/s11540-020-09492-4 \u003c/li\u003e\n\u003cli\u003eICAR-CRIDA (2021). \u0026quot;Annual Report 2021-22, ICAR-Central Research Institute for Dryland Agriculture.\u0026quot; https://icar-crida.res.in/ \u003c/li\u003e\n\u003cli\u003eKaur, M., \u0026amp; Yadav, S. S. (2020). \u0026quot;Analysis of soil health and its relationship to crop productivity.\u0026quot; Soil Science Society of America Journal, 84(3), 453-460. https://doi.org/10.2136/sssaj2020.05.0155 \u003c/li\u003e\n\u003cli\u003eSharma, P., \u0026amp; Soni, A. (2019). \u0026quot;Comparing the growth of five potato varieties in Rajasthan under varying climatic conditions.\u0026quot; Indian Journal of Agricultural Sciences, 89(4), 678-684. https://doi.org/10.21475/ijg.2020.04.3.0041 \u003c/li\u003e\n\u003cli\u003eTimes of India. (2021). \u0026quot;Top 10 Potato Varieties to Cultivate in India.\u0026quot; Times of India Recipes. https://timesofindia.indiatimes.com/ \u003c/li\u003e\n\u003cli\u003eBijak Blog. (2020). \u0026quot;Potato Varieties for High Yield in India.\u0026quot; Bijak Blog. https://bijak.in/ \u003c/li\u003e\n\u003cli\u003eBookMyCrop. (2021). \u0026quot;Best Potato Varieties to Grow in India.\u0026quot; BookMyCrop. https://www.bookmycrop.com/ \u003c/li\u003e\n\u003cli\u003eInternational Potato Center (CIP). (2021). \u0026quot;CIP Data Repository.\u0026quot; https://cipotato.org/\u003c/li\u003e\n\u003cli\u003eISRIC - World Soil Information. (2021). \u0026quot;ISRIC World Soil Information Database.\u0026quot; https://www.isric.org/ \u003c/li\u003e\n\u003cli\u003eNOAA (2020). \u0026quot;National Oceanic and Atmospheric Administration (NOAA) Climate Data.\u0026quot; https://www.noaa.gov/ \u003c/li\u003e\n\u003cli\u003eECMWF (2021). \u0026quot;European Centre for Medium-Range Weather Forecasts (ECMWF) Data Portal.\u0026quot; https://www.ecmwf.int/ \u003c/li\u003e\n\u003cli\u003eUSGS (2021). \u0026quot;USGS Spectral Library.\u0026quot; https://pubs.usgs.gov/ \u003c/li\u003e\n\u003cli\u003eSPECCHIO Database (2020). \u0026quot;Spectral and Hyperspectral Data for Agriculture and Environmental Monitoring.\u0026quot; https://www.specchio.org/\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Potato cultivation, Machine learning, Growth stage prediction, Yield forecasting, precision agriculture","lastPublishedDoi":"10.21203/rs.3.rs-5766512/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5766512/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eUnderstanding growth patterns and yield dynamics in potato cultivation is essential for optimizing agricultural practices and improving productivity. This study leverages machine-learning techniques to analyze and predict potato growth stages and yield outcomes based on environmental and physiological data. Various machine-learning models were developed using multispectral imaging, soil parameters, and climatic factors collected across diverse cultivation environments. The models were evaluated for their accuracy in identifying growth stages and forecasting yield performance. Key physiological trends were identified during the tuber initiation, bulking, and maturation phases, correlating with specific environmental conditions. Predictions for tuber yield showed high accuracy, with models achieving R\u0026sup2; values above 0.90 across validation datasets. Additionally, the study highlights the importance of integrating machine learning with precision agriculture systems to enhance decision-making and resource management. The proposed methodology demonstrates significant potential for advancing potato-farming practices by providing actionable insights into growth and yield optimization.\u003c/p\u003e","manuscriptTitle":"Utilizing Machine Learning to Decode Growth Patterns and Yield Dynamics in Potato Cultivation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-01-13 17:33:09","doi":"10.21203/rs.3.rs-5766512/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"7a7766b5-e942-4a69-9120-26529cb0ceb1","owner":[],"postedDate":"January 13th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-02-17T21:20:12+00:00","versionOfRecord":[],"versionCreatedAt":"2025-01-13 17:33:09","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5766512","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5766512","identity":"rs-5766512","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}