Predicting Suitable Habitats of Melia Azedarach L. Using Data Mining

Predicting Suitable Habitats of Melia Azedarach L. Using Data Mining | 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 Predicting Suitable Habitats of Melia Azedarach L. Using Data Mining Lei Feng, Xiangni Tian, Yousry A. El-Kassaby, Jian Qiu, Ze Feng, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-1004808/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 3 You are reading this latest preprint version Abstract Background : Melia azedarach L. is a globally distributed tree species of economic importance; however, it is unclear how the species distribution will respond to future climate changes. Methods: We aimed to select the most accurate one among seven data mining models to predict the species suitable contemporary and future habitats. These models include: maximum entropy (MaxEnt), support vector machine (SVM), generalized linear model (GLM), random forest (RF), naive bayesian model (NBM), extreme gradient boosting (XGBoost), and gradient boosting machine (GBM). A total of 906 M. azedarach locations were identified, and sixteen climate predictors were used for model building. The models’ validity was assessed using three measures (Area Under the Curves (AUC), kappa, and accuracy). Results: We found that the RF provided the most outstanding performance in prediction power and generalization capacity. The top climate factors affecting the species distribution were mean coldest month temperature (MCMT), followed by the number of frost-free days (NFFD), degree-days above 18°C (DD>18), temperature difference between MWMT and MCMT, or continentality (TD), mean annual precipitation (MAP), and degree-days below 18°C (DD<18). We projected that future suitable habitat of this species would increase under both the RCP4.5 and RCP8.5 scenarios for the 2020s, 2050s, and 2080s. Conclusion: Our findings are expected to assist in better understanding the impact of climate change on the species and provide scientific basis for its planting and conservation. Ecological Modeling Forestry Melia azedarach L. Climate change Habitat suitability Data mining models Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 1 Introduction Melia azedarach L., Meliaceae, is a fast-growing species with good timber attributes of multiple-use, such as construction and furniture, farm tools, boats, vehicles, and musical instruments manufacturing 1 . The species roots, bark, flowers, and fruits are of high medicinal values 2 , 3 . Additionally, its fruit and leaf extracts can control numerous agricultural pests and are commonly used as biological pesticides raw materials 4 . The species is an excellent urban greening tree that is resistant to smoke and dust and can absorb many toxic and harmful gases. At present, it is planted in more than 50 countries 5 , 6 . The species productivity is climate-dependent, and it is expected that climate change will reshape its future suitable habitat 7 . The intensification of global warming, accompanied by the frequent occurrence of extreme natural disturbances, such as wind storms, droughts, fires, and floods, will undoubtedly impact the global forest ecosystem 8 . Different tree species respond differently to climate change, with positive and negative effects in different areas. For example, climate change is expected to increase the suitable habitats of Mediterranean oaks in the western temperate areas 9 as well as the total suitable habitat for Cypripedium japonicum 10 . Conversely, eucalyptus species are expected to face future challenges due to their poor spread capability 11 , and Persian oak ( Quercus macranthera ) will experience a reduction in its contemporary range and is expected to move to higher altitudes 12 . Consequently, assessing the impact of climate change on the potential distribution of species and formulating sustainable forest management strategies are critical to maintaining forest ecosystems integrity. With climate change challenges, species distribution models (SDMs) have become essential tools for projecting plants adaptation to a changing climate 11 . At present, a variety of data mining techniques have been applied to model species distribution data. These include: 1) Generalize linear model (GLM), a common regression model first introduced by Austin et al. (1983), to simulate tree species distribution and subsequently was used to predict the spread of Emerald Ash Borer ( Agrilus planipennis ) in southern Ontario, Canada 13 ; 2) Gradient boosting machine (GBM), a machine-learning technology used to generate predictive models in the form of a collection of weak predictive models 14 and currently is being used to predict invasive plant species distribution, high-resolution, high-precision multi-type vegetation mapping, and species distribution models 15 , 16 ; 3) Random Forest (RF), a machine-learning technology through building a large number of decision trees during the program’s training phase 17 and presently is being used to predict invasive species range, classification of tree species based on hyperspectral information, and prediction of stands basal areas and the distribution of plantation forests 18 , 19 ; 4) Support Vector Machine (SVM), a supervised learning model used for data classification and regression analysis and is widely used to classify invasive species and detect the presence of farmland weeds 20 , 21 ; 5) Maximum Entropy (MaxEnt), a machine-learning technology by finding the maximum entropy of the probability distribution of the species through the species distribution and environmental data to estimate and predict future species distribution 22 , and mainly is being used in crop niches, plant diseases and insect pests, and species invasion prediction 23 , 24 ; 6) Extreme Gradient Boosting (XGBoost), an open-source software library algorithm effective in predicting species abundance and identifying critical environmental factors 25 , and is playing an essential role in designing new drugs to treat related diseases; and 7) Naive Bayesian Model (NBM), a series of simple probabilistic classifiers based on Bayes' theorem and independent assumptions between features 26 , and mainly is being applied in forestry for predicting the potential distribution areas of Taxus chinensis and identifying plant long non-coding RNA and predicting its functions 27 . Understanding the potential distribution of M. azedarach is of great significance to its cultivation and conservation. Studies conducted on M. azedarach were mainly focused on tree and stand productivity, extraction of active ingredients, and pest resistance potential 3 , 28 . Research on M. azedarach potential distribution as affected by climate change is lacking and thus, the present study is aimed at exploring the above-mentioned seven data mining techniques to establish climate-based distribution prediction models and select the best model in predictions of the species future suitable habitat. Our specific objectives were to: 1) compare the prediction accuracy of the seven modeling algorithms and select the one with the best performance; 2) determine the key climatic factors related to the species distribution; 3) develop current and future species suitable habitat maps highlighting the areas of change; and 4) assess the potential impact of future climate change on the species suitable habitat. 2 Material And Methods 2.1 Species location data Here, we used the Chinese presence and absence M. azedarach data to establish the prediction models. First, we found 1,432 presence data (data source: Global Biodiversity Information Facility (GBIF), https://www.gbif.org , and the Chinese Virtual Herbarium (CVH), http://www.cvh.ac.cn/ ). To avoid redundant sampling, we deleted those sample points with similar longitude and latitude 29 . Then a 0.01° mesh thinning was performed, and the actual distance corresponding to 0.01° was about 1km and only one distribution point was reserved in each grid so that the distance between sample points was more than 1 km 30 . Finally, a total of 906 samples were included for model building (Figure. 1). 2.2 Environment variables We established a GLM model with M. azedarach presence-absence data as dependent variables and 16 climatic factors derived from ClimateAP_v221 software ( http://ClimateAP.net ) as predictors (Table S1) 31 . Correlation analysis showed that there was strong data collinearity among the 16 climate variables. Then we used stepwise regression analysis to eliminate those variables causing the observed multicollinearity 32 and ultimately reduced the climate variable to ten 33 . 2.3 Model development and prediction We used seven models (Generalize Linear Model (GLM), Gradient Boosting Machine (GBM), Random Forest (RF), Support Vector Machine (SVM), Maximum Entropy (MaxEnt), Extreme Gradient Boosting (XGBoost), and Naive Bayesian Model (NBM)) to associate the distribution of M. azedarach with climate variables. Firstly, we used the “dismo” package in R to randomly generate 2,000 “pseudo-nonexistent” records in the study area. Models were established with species presence-absence data as the dependent variable and climate variable as the independent variables. In order to evaluate the models’ prediction accuracy, we randomly selected 70% data for training and the remaining 30% data for testing (validation). We used the “caret” package to train and adjust the parameters for all the seven models except Maxent, since it facilitates the process of building, evaluating, as well as selecting features. Then, ten cross-verifications were carried out, and each model was repeated three times. At the same time, the Maxent model was executed using the Maxent version 3.4.4 software in R-package. 2.4 Model validation To assess the performance of the seven predictive models, we compared their area under receiver operating character curve (AUC), Kappa, and accuracy. The AUC is the probability value, with evaluation criteria were: 0.5-0.6 = fails, 0.6-0.7 = poor, 0.7-0.8 = fair, 0.8-0.9 = good, 0.9-1.0 = excellent 34 . Kappa coefficient is an index to measure classification accuracy. The calculation result of kappa is -1 to 1, but usually, kappa falls between 0 and 1, which can be divided into five groups: 0.0-0.2 means very low consistency, 0.21-0.40 means general consistency, 0.41-0.60 means moderate consistency, 0.61-0.80 means high consistency, 0.81-1 means almost perfect 35 . Accuracy refers to the proximity of measured values to specific values, and it is reported as the average cross-validated accuracy 36 . 2.5 Habitat Classification Appropriate habitat evaluation index values were determined as follows: predicted values of 0-0.2, 0.2-0.4, 0.4-0.6, and >0.06 were deemed unsuitable, low-, medium-, and highly-suitable habitat, respectively 37 . 3 Results 3.1 Models performance evaluation Through the cross-validation evaluation of the tested models, Accuracy, Kappa, and AUC values were obtained for the training and testing portions of each model (Figure. 2). All models performed well (AUC>0.8, Kappa>0.5, and Accuracy>0.7). For the training data, the seven models AUC values varied from 0.8825 (NBM) to 1 (RF), Kappa values varied from 0.5754 (GLM) to 0.9988 (RF), and Accuracy values ranged from 0.7887 (NBM) to 0.9995 (RF). While the testing data produced AUC values varied from 0.8471 (NBM) to 0.9039 (RF), Kappa values varied from 0.5335 (SVM) to 0.5896 (MaxEnt), and Accuracy values ranged from 0.7678 (NBM) to 0.8138 (XGBoost). Overall, the three evaluation metrices all indicated that the Random Forest (RF) model provided the best predictive performance and while the Naive Bayesian Model (NBM) was the worst, thus, we selected the RF model to establish M. Azedarach distribution patterns. 3.2 Important climate variables and their response curves in Random Forest (RF) The top three climate variables contributing to the RF model include MCMT (189.24), NFFD (180.69), and DD>18 (104.77), followed by TD (72.82), MAP (69.43), DD5 (56.27), and AHM (54.88); and finally DD<0 (44.01) and PAS (28.54) also played some roles in the determining the potential distribution of M. azedarach (Table 1 ). Figure. 3 displayed the relationships between the top six climate variables and M. azedarach suitability according to the predictions of RF algorithms. The habitat suitable range was between -10 and -28℃ for MCMT (Figure. 3a), between 0 and 175 days for NFFD (Figure. 3b), between 0 and 250 for DD>18 (Figure. 3c), between 5 and 21℃ for TD (Figure. 3d), between 0 and 480 mm for MAP (Figure. 3e), and between 0 and 1750 for DD18 °C-days 104.77 TD °C 72.82 MAP mm 69.43 DD5 °C-days 56.27 AHM 54.88 DD<0 °C-days 44.01 PAS mm 28.54 1 see Table S1 for variables abbrivations. 3.3 RF model prediction of M. azedarach contemporary habitats distribution The spatial distributions of M. azedarach and areas of suitable habitats under current climatic conditions as predicted by the RF algorithm are shown Figure. 4. The overall suitable habitat was mainly distributed between 18 and 40°N (Figure. 4a). These habitats were classified as: 1) highly-suitable habitats (mainly scattered in Shandon (SD), Jiangsu (JS), Shanghai (SH), Zhejiang (ZJ), Guangdong (GD), Hunan (HN), Hainan (HI), South Jiangxi (JX), the junction of the three provinces of Hubei (HB), Anhui (AH), Jiangxi (JX), and the junction of Chongqing (CQ) and Sichuan (SC), covering 9.3 × 10 5 km 2 (9.6%; Figure. 4b); 2) medium-suitable habitats (scattered around the high-suitable habitats, covering 6.8 × 10 5 km 2 (7%; Figure. 4b) and specifically concentrated in eastern Sichuan (SC), northern and western Shandong (SD), and the junction of Hubei (HB) and Hunan (HN)); and 3) low-suitable habitats (slightly larger than the medium-suitable habitats, covering 7.1 × 10 5 km 2 (7.4%; Figure. 4b)), and it is distributed in Yunnan (YN), central Guangxi (GX), eastern and northern Guizhou (GZ), southern Shaanxi (SN), western and northern Henan (HA), and southern Hebei (HE)). 3.4 RF model prediction of M. azedarach projected suitable habitats future changes Future projections using the RF model with two different climate scenarios (RCP 8.5 and RCP 4.5) indicated a clear graphical expansion of M. azedarach in the future periods with an increasing magnitude over time (Figure. 5). The projected range increase was greatest under RCP 8.5 as compated to RCP 4.5 (Figure. 5). More specifically, the expanded area would increase by 562.6 × 10 3 km 2 and 584.5 × 10 3 km 2 by 2020s, 807.4 × 10 3 km 2 and 930.3 × 10 3 km 2 by 2050s, and 906.1 × 10 3 km 2 and 1486.3 × 10 3 km 2 by 2080s under the RCP4.5 and RCP8.5 scenarios, respectively (Figure. 5g). The main expanded area will be located in Yunnan (YN), Anhui (AH), Henan (HA), Shanxi (SX), Shaanxi (SN), central Guangxi (GX), central Jiangxi (JX), and northern Guizhou (GZ). Interestingly, based on the RCP8.5 climate scenario, Xinjiang (XJ) would see a larger magnitude of area expansion in 2080s (Figure. 5f). Additionally, the species stable range area showed the same change pattern as that of the expanded area (Figure. 5g). The main stable area included Guangdong (GD), Guangxi (GX), Guizhou (GZ), Hunan (HN), Chongqing (CQ), Fujian (FJ), Zhejiang (ZJ), Jiangsu (JS), southwestern Jiangxi (JX), and eastern Sichuan (SC) (Figure. 5a-f). Furthermore, the species area loss exhibited an opposite trend to that of expansion and stable range areas (Figure. 5f) and most of the loss area was mainly distributed in eastern coastal provinces near 30-38°N (e.g., Shandong (SD)) (Figure. 5). 4 Discussion 4.1 Model performance Here, we used the Area Under the Curves (AUC), Kappa statistic, and Accuracy to evaluate the performance of seven species range prediction models (Generalized Linear Models (GLM), Gradient Boosting Machine (GBM), Maximum Entropy (MaxEnt), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), Naive Bayesian Model (NBM), and Random Forest (RF)) to predict M. azedarach contemporary and future ranges under two climate scenarios (RCP 8.5 and RCP 4.5). The results showed that Random Forest (RF) and Extreme Gradient Boosting (XGBoost) were the top-performing models with RF being the best, while Naive Bayesian Model (NBM) and Generalized Linear Models (GLM) were the low-performing with the NBM being the worst. Multiple lines of evidence support the superiority of the RF algorithm 38 . The RF is an ensemble machine-learning model that could handle data with multi-dimensional, non-linear relationships, high-order correlations, and missing values 39 . Additionally, the RF model is capable of avoiding the accuracy reduction problem caused by missing and noisy data in the training sample when predicting the relationship between a large number of predictor variables and the response variable 40 , attributes supporting the present study results. In contrast, while the NBM like RF is also a machine learning algorithm, it was proven to be not very sensitive to missing data, and the algorithm is relatively simple 41 . Studies have demonstrated that more complex species distributions models provided better predictive performance demonstrating the suitability of the RF model in processing complex high-dimensional data such as the data used in the present study 42 . Moreover, the NBM is a linear classifier and similar to the traditional linear statistical methods, all are insufficient in revealing the complex relationship among environmental variables 43 . In our case, the two linear models, GBM and GLM, demonstrated this with their poor predictive power. Additionally, we observed that the prediction accuracy of the Extreme Gradient Boosting (XGBoost) was very close to that of RF as the XGBoost has good generalization performance 44 . Although, previous studies have shown that Maximum Entropy (MaxEnt), Support Vector Machine (SVM), and Gradient Boosting Machine (GBM) models performed well in simulating species suitability distribution 45 , 46 , our results have shown that the prediction accuracy of these models was intermediate relative to the performance of the seven tested models. These phenomena may indicate that species characteristics and sample size also have influence on the accuracy of species distribution models 47 . 4.2 The importance of climate variables Our study along with several others 48 – 50 were based on the assumption that species distribution is mainly determined by climate 51 , 52 . It is well documented that climatic factors are key elements for most species’ population regeneration 53 . Here, our results indicated that temperature-associated climate factors have greater influence on M. azedarach suitable habitats than precipitation factors. Specifically, the top three temperature-related climate variables included mean coldest month temperature (MCMT), the number of frost-free days (NFFD), and degree-days below 18°C (DD>18)), with MCMT contributing the most. This shows that low temperature was the main climatic factor that restricted M. azedarach distribution, which is consistent with previous studies, as low-temperature stress imparted a negative impact on plant physiological and biochemical responses (e.g., plant membrane system disorder, photosynthetic rate decline, harmful active oxygen increased, and osmotic adjustment substances increase) 54 . M. azedarach is known to prefer warm and humid climates, suitable temperature and abundant precipitation were conducive to the species growth and biomass accumulation. Research has demonstrated that M. azedarach ground diameter shown increasing trend with precipitation increase 55 . The extension of the number of frost-free days (NFFD) was beneficial to increasing M. azedarach seed size and quality 56 . 4.3 Range shift in response to climate change Our study showed that M. azedarach would benefit from the anticipated climate change. More specifically, we found the RCP 8.5 scenario to be more favorable for the species habitat suitability expansion as compared to the RCP 4.5 scenario (Figure. 5g). The RCP 8.5 scenario predicted a greater increase in future temperature warming and precipitation, providing climatic conditions favorable to the species growth 56 . From the species geographic range change point of view, it is expected that the future suitable habitat distribution to expand north- and west-ward. Compared with the RCP4.5 scenario, the predicted trend of suitable habitats changes of the RCP8.5 scenario was more significant in the plateau area near 40 °N (Figure. 5), including the Xinjiang Tarim Basin (RCP8.5) (Figure. 5f). Under the RCP4.5 and RCP8.5 scenarios, the future temperature is envisaged to rise by 1.4 - 1.8 and 2.0 - 3.7°C, respectively, making high latitude areas warmer, resulting in a contemplated rise of mountains tree line, which would ultimately provide the species with a potential of geographic range expansion 57 . At the same time, we noted that the suitable habitat in the Shandong region would experience substantial range loss (Figure. 5), caused by a drastic change in climatic conditions from mainly dry continental airflow with little precipitation to a future warmer climate associated with intensified precipitation reduction 58 . Additionally, the impact of subtropical high pressure could not be overlooked as the Shandong is often affected by sinking air currents with long periods of high temperature and low precipitation. This subtropical high pressure is expected to gradually moved northward, followed by anticipated clear trend of northward movement associated with precipitation pattern change in the Shandong 59 . To a certain extent, the contemplated climate changes are expected to exacerbate the dryland climate in the Shandong, creating predominantly drought conditions that is unsuitable for the drought-intolerant M. azedarach 60 . 4.4 Management strategies Rapid climate change causes most tree populations to exist in unsuitable environmental conditions, threatening their growth and survival and even leading to population extinction 61 . Some tree species adapted to the new climatic conditions by migrating to the same environmental gradient or evolving 62 ; however, other tree species would benefit from climate change 63 . M. azedarach belongs to those species who would benefit from future climate change leading to anticipated range expansion. The wide distribution of M. azedarach harbours abundant phenotypic variation and most of the species phenotypic diversity is mainly distributed in the southwest and south regions and to a lesser extent in other regions 64 . It is worth noting that if a widely distributed species could not track the changing climate due to long-term local adaptation, they would become more vulnerable 65 . Therefore, to prevent this uncertainty, we suggest taking proactive in-situ conservation measures for Yunnan, Guizhou, Sichuan, Guangdong, and Guangxi regions, as they are rich in phenotypic diversity which will help in coping with future environmental uncertainty 66 . Assisted migration initiatives should applied to presently unsuitable habitats that are expected to be suitable in the future. For example, the northern regions of Jiangxi, Hubei, Anhui, Henan, and areas near 40°N are reasonable targets for assisted migration conservation measures 67 . We recommend for areas that would be negatively affected by future climate as Shandong, taking ex-situ measures through establishing botanical gardens and seed banks in suitable habitats to protect their resources. Therefore, analyzing the ex-situ target areas’ climate ecology could provide reference for breeding programs and seed transfer guidelines/polices. At the same time, we suggest that other biological factors along with climate should also be considered in the species future research, such as species interaction (allelopathy, soil nutrient competition), land-use change (bio-energy farmland expansion), and the influence of human activities 68 , 69 , these factors collectively affect the contemporary and future distribution of M. azedarach . 5 Conclusion Here, we used three common model accuracy evaluation indicators to compare the suitability of seven data mining techniques for predicting M. azedarach distribution. The RF model, with its strong robustness and stability, provided the highest accuracy in establishing a climate niche model. Based on this model, maps of contemporary and future suitable habitats were developed. The RF prediction results indicated that M. azedarach would benefit from future climate change through range expansion and this has tendency towards north- and west-ward expansion. In order to maximize the species protection and development, we recommend taking a proactive in-situ conservation measures to conserve genetic variation for adaptation to uncertainties and ex situ conservation to protect genetic resources under risk, and assisted migration to better use the areas with good potential in future climates. Declarations Author Contributions: L.F., Y.E., W.G., and T.W. participated in the data analysis, and wrote the paper. X.T., J.Q., Z.F., and J.S. participated in the data preparation and processing. W.G. and T.W. designed the study. and T.W. also provided the paper editing. All the authors read and approved the final manuscript. Funding: This work was jointly funded by the National Key Research and Development Program of China (No. 2017YFD0600700), and the Special Admission for Postgraduate Study Abroad Program by China Scholarship Council (No. 202008320472). Conflicts of Interest: The authors declare no conflict of interest. References Chen, L. et al. Geographic variation in traits of fruit stones and seeds of Melia azedarach. Journal of Beijing Forestry University , 36 , 15–20 (2014). Angamuthu, D., Purushothaman, I., Kothandan, S. & Swaminathan, R. Antiviral study on Punica granatum L., Momordica charantia L., Andrographis paniculata Nees, and Melia azedarach L., to human herpes virus-3. Eur. J. Integr. Med , 28 , 98–108 https://doi.org/10.1016/j.eujim.2019.04.008 (2019). Wang, N. et al. Selective ERK1/2 agonists isolated from Melia azedarach with potent anti-leukemic activity. BMC Cancer , 19 , 1–9 https://doi.org/10.1186/s12885-019-5914-8 (2019). Khoshraftar, Z., Safekordi, A., Shamel, A. & Zaefizadeh, M. Evaluation of insecticidal activity of nanoformulation of Melia azedarach (leaf) extract as a safe environmental insecticide. International Journal of Environmental Science and Technology , 17 , 1159–1170 https://doi.org/10.1007/s13762-019-02448-7 (2020). Al-Rubae, A. Y. The potential uses of Melia azedarach L. as pesticidal and medicinal plant, review. American-Eurasian Journal of Sustainable Agriculture , 3 , 185–194 (2009). Nakatani, M. et al. Three new antifeeding meliacarpinins from Chinese Melia azedarach Linn., 51 , 11731–11736 https://doi.org/10.1016/0040-4020(95)00724-M (1995). Wu, L., Kaewmano, A., Fu, P., Wang, W. & Fan, Z. Intra-annual Radial Growth of Melia azedarach in a TropicalMoist Seasonal Forest and its Response to Environmental Factors in Xishuangbanna,Southwest China Acta Ecol. Sin , 40 , 6831–6840 https://doi.org/10.5846/stxb202003120508 (2020). Hoegh-Guldberg, O. et al. The human imperative of stabilizing global climate change at 1.5 C. Science 365 ; https://doi.org/10.1126/science.aaw6974 (2019). López-Tirado, J., Vessella, F., Schirone, B. & Hidalgo, P. J. Trends in evergreen oak suitability from assembled species distribution models: assessing climate change in south-western Europe. New For , 49 , 471–487 https://doi.org/10.1007/s11056-018-9629-5 (2018). Xu, Y. et al. Modelling the Effects of Climate Change on the Distribution of Endangered Cypripedium japonicum in China. Forests 12, 429; https://doi.org10.3390/f12040429(2021). Booth, T. H. Species distribution modelling tools and databases to assist managing forests under climate change. For. Ecol. Manag , 430 , 196–203 https://doi.org/10.1016/j.foreco.2018.08.019 (2018). Dyderski, M. K., Paź, S., Frelich, L. E. & Jagodziński, A. M. How much does climate change threaten European forest tree species distributions? Global change biology , 24 , 1150–1163 https://doi.org/10.1111/gcb.13925 (2018). Zhong, Y. et al. A Generalized Linear Mixed Model Approach to Assess Emerald Ash Borer Diffusion. ISPRS International Journal of Geo-Information , 9 , 414 https://doi.org/10.3390/ijgi9070414 (2020). Cho, G., Yim, J., Choi, Y., Ko, J. & Lee, S. H. Review of machine learning algorithms for diagnosing mental illness. Psychiatry investigation , 16 , 262 https://doi.org/10.30773/pi.2018.12.21.2 (2019). Brun, P. et al. Model complexity affects species distribution projections under climate change. J. Biogeogr , 47 , 130–142 https://doi.org/10.1111/jbi.13734 (2020). Shiferaw, H., Bewket, W. & Eckert, S. Performances of machine learning algorithms for mapping fractional cover of an invasive plant species in a dryland ecosystem. Ecology and evolution , 9 , 2562–2574 https://doi.org/10.1002/ece3.4919 (2019). Ho, T. K. The random subspace method for constructing decision forests. IEEE transactions on pattern analysis and machine intelligence , 20 , 832–844 https://doi.org/10.1109/34.709601 (1998). Sothe, C. et al. Comparative performance of convolutional neural network, weighted and conventional support vector machine and random forest for classifying tree species using hyperspectral and photogrammetric data. GIScience & Remote Sensing , 57 , 369–394 https://doi.org/10.1080/15481603.2020.1712102 (2020). Sung, S., Kwon, Y. S., Lee, D. K. & Cho, Y. Predicting the potential distribution of an invasive species, Solenopsis invicta Buren (Hymenoptera: Formicidae), under climate change using species distribution models. Entomol. Res , 48 , 505–513 https://doi.org/10.1111/1748-5967.12325 (2018). Chen, Y., Wu, Z., Zhao, B., Fan, C. & Shi, S. Weed and Corn Seedling Detection in Field Based on Multi Feature Fusion and Support Vector Machine. Sensors , 21 , 212 https://doi.org/10.3390/s21010212 (2021). Sabat-Tomala, A., Raczko, E. & Zagajewski, B. Comparison of support vector machine and random forest algorithms for invasive and expansive species classification using airborne hyperspectral data. Remote Sensing , 12 , 516 https://doi.org/10.3390/rs12030516 (2020). Phillips, S. J., Anderson, R. P. & Schapire, R. E. Maximum entropy modeling of species geographic distributions. Ecol. Model , 190 , 231–259 https://doi.org/10.1016/j.ecolmodel.2005.03.026 (2006). Tang, X., Yuan, Y., Li, X. & Zhang, J. Maximum entropy modeling to predict the impact of climate change on pine wilt disease in China. Frontiers in Plant Science , 12 , 764 https://doi.org/10.3389/fpls.2021.652500 (2021). Chhogyel, N., Kumar, L., Bajgai, Y. & Jayasinghe, L. S. Prediction of Bhutan's ecological distribution of rice (Oryza sativa L.) under the impact of climate change through maximum entropy modelling. The Journal of Agricultural Science , 158 , 25–37 https://doi.org/10.1017/S0021859620000350 (2020). Smith, E. H. Using extreme gradient boosting (XGBoost) to evaluate the importance of a suite of environmental variables and to predict recruitment of young-of-the-year spotted seatrout in Florida. bioRxiv , 543181; https://doi.org/10.1101/543181 (2019). Do, B. H., Langlotz, C. & Beaulieu, C. F. Bone tumor diagnosis using a naïve Bayesian model of demographic and radiographic features. J. Digit. Imaging , 30 , 640–647 https://doi.org/10.1007/s10278-017-0001-7 (2017). Chang, Z., Meng, J., Shi, Y. & Mo, F. Lnc RNA recognition by fusing multiple features and its function prediction. CAAI Transactions on Intelligent Systems , 13 , 928–934 https://doi.org/10.11992/tis.201806008 (2018). Ahmad, Z. et al. Melia Azedarach impregnated Co and Ni zero-valent metal nanoparticles for organic pollutants degradation: validation of experiments through statistical analysis. J. Mater. Sci.: Mater. Electron , 31 , 16938–16950 https://doi.org/10.1007/s10854-020-04250-5 (2020). Hijmans, R. J., Huaccho, L. & Zhang, D. in I International Conference on Sweetpotato. Food and Health for the Future 583. 41-49. Luo, M., Wang, H. & Lyu, Z. Evaluating the performance of species distribution models Biomod2 and MaxEnt using the giant panda distribution data. The journal of applied ecology , 28 , 4001–4006 https://doi.org/10.13287/j.1001-9332.201712.011 (2017). Wang, T., Wang, G., Innes, J. L., Seely, B. & Chen, B. ClimateAP: An application for dynamic local downscaling of historical and future climate data in Asia Pacific. Frontiers of Agricultural Science and Engineering , 4 , 448–458 (2017). Yang, X. Q., Kushwaha, S., Saran, S., Xu, J. & Roy, P. Maxent modeling for predicting the potential distribution of medicinal plant, Justicia adhatoda L. in Lesser Himalayan foothills. Ecological engineering , 51 , 83–87 https://doi.org/10.1016/j.ecoleng.2012.12.004 (2013). Ravisankar, P., Navya, C. N., Pravallika, D. & Sri, D. N. A review on step-by-step analytical method validation. IOSR J Pharm , 5 , 7–19 (2015). https://www.researchgate.net/publication/338166852 Pepe, M. S., Cai, T. & Longton, G. Combining predictors for classification using the area under the receiver operating characteristic curve., 62 , 221–229 https://doi.org/10.1111/j.1541-0420.2005.00420.x (2006). McHugh, M. L. Interrater reliability: the kappa statistic. Biochemia medica , 22 , 276–282 (2012). Powers, D. M. What the F-measure doesn't measure: Features, Flaws, Fallacies and Fixes. arXiv preprint arXiv:1503.06410(2015). Lu, C. Y., Gu, W., Dai, A. H. & Wei, H. Y. Assessing habitat suitability based on geographic information system (GIS) and fuzzy: a case study of Schisandra sphenanthera Rehd. et Wils. in Qinling Mountains, China. Ecol. Model , 242 , 105–115 https://doi.org/10.1016/j.ecolmodel.2012.06.002 (2012). Zhang, L. et al. The basic principle of random forest and its applications in ecology: A case study of Pinus yunnanensis. Acta Ecol. Sin , 34 , 650–659 (2014). Lin, H. Y. et al. Climate-based approach for modeling the distribution of montane forest vegetation in Taiwan. Appl. Veg. Sci , 23 , 239–253 https://doi.org/10.1111/avsc.12485 (2020). Zhang, L. et al. Consensus forecasting of species distributions: The effects of niche model performance and niche properties. PLoS ONE , 10 , e0120056 https://doi.org/10.1371/journal.pone.0120056 (2015). Zhang, H. The optimality of naive Bayes. American Association for Artificial Intelligence , 1 , 3 (2004). Wang, Q., Nguyen, T. T., Huang, J. Z. & Nguyen, T. T. An efficient random forests algorithm for high dimensional data classification. Advances in Data Analysis and Classification , 12 , 953–972 https://doi.org/10.1007/s11634-018-0318-1 (2018). Zheng-tao, Y., Bin, D., Bo, H. & Lu, H. Jian-yi, G. Word Sense Disambiguation Based on Bayes Model and Information Gain. the Proceedings of the International Journal of Advanced Science and Technology 3(2009). Yu, B. et al. SubMito-XGBoost: predicting protein submitochondrial localization by fusing multiple feature information and eXtreme gradient boosting., 36 , 1074–1081 https://doi.org/10.1093/bioinformatics/btz734 (2020). Hailu, B. T., Siljander, M., Maeda, E. E. & Pellikka, P. Assessing spatial distribution of Coffea arabica L. in Ethiopia's highlands using species distribution models and geospatial analysis methods. Ecological Informatics , 42 , 79–89 https://doi.org/10.1016/j.ecoinf.2017.10.001 (2017). Ramirez-Reyes, C. et al. Embracing Ensemble Species Distribution Models to Inform At-Risk Species Status Assessments. Journal of Fish and Wildlife Management , 12 , 98–111 https://doi.org/10.3996/JFWM-20-072 (2021). Wisz, M. S. et al. Effects of sample size on the performance of species distribution models. Divers. Distrib , 14 , 763–773 https://doi.org/10.1111/j.1472-4642.2008.00482.x (2008). Feng, L., Sun, J., Shi, Y., Wang, G. & Wang, T. Predicting Suitable Habitats of Camptotheca acuminata Considering Both Climatic and Soil Variables. Forests , 11 , 891 https://doi.org/10.3390/f11080891 (2020). Wang, T., Campbell, E. M., O’Neill, G. A. & Aitken, S. N. Projecting future distributions of ecosystem climate niches: uncertainties and management applications. For. Ecol. Manag , 279 , 128–140 https://doi.org/10.1016/j.foreco.2012.05.034 (2012). Wang, T., Hamann, A., Spittlehouse, D. L. & Murdock, T. Q. ClimateWNA—high-resolution spatial climate data for western North America. Journal of Applied Meteorology and Climatology , 51 , 16–29 https://doi.org/10.1175/JAMC-D-11-043.1 (2012). Feng, L. et al. Predicting suitable habitats of Ginkgo biloba L. fruit forests in China. Climate Risk Management , 100364 https://doi.org/10.1016/j.crm.2021.100364 (2021). Wang, T., Hamann, A., Spittlehouse, D. & Carroll, C. Locally downscaled and spatially customizable climate data for historical and future periods for North America. PLoS ONE , 11 , e0156720 https://doi.org/10.1371/journal.pone.0156720 (2016). Guo, Y. et al. Spatial prediction and delineation of Ginkgo biloba production areas under current and future climatic conditions. Industrial Crops and Products , 166 , 113444 https://doi.org/10.1016/j.indcrop.2021.113444 (2021). Jiao, C., Lan, G., Sun, Y., Wang, G. & Sun, Y. Dopamine Alleviates Chilling Stress in Watermelon Seedlings via Modulation of Proline Content, Antioxidant Enzyme Activity, and Polyamine Metabolism. J. Plant Growth Regul. 40 (2021). Xu, L. et al. Effect of salt stress on growth and physiology in Melia azedarach seedlings of six provenances. International Journal of Agriculture and Biology , 20 , 471–480 https://doi.org/10.17957/IJAB/15.0618 (2018). Thakur, S., Thakur, I. & Sankanur, M. Assessment of Genetic Diversity in Drek (Melia azedarach) Using Molecular Markers. Journal of Tree Sciences , 36 , 78–85 https://doi.org/10.5958/2455-7129.2017.00011.5 (2017). Lenoir, J., Gégout, J. C., Marquet, P., De Ruffray, P. & Brisse, H. A significant upward shift in plant species optimum elevation during the 20th century. Science ; https://doi.org/10.1126/science.1156831 (2008). Ou-Yang, C. F. et al. Impact of equatorial and continental airflow on primary greenhouse gases in the northern South China Sea. Environmental Research Letters , 10 , 065005 https://doi.org/10.1088/1748-9326/10/6/065005 (2015). Liu, B., Zhu, C., Su, J., Ma, S. & Xu, K. Record-breaking northward shift of the western North Pacific subtropical high in July 2018. Journal of the Meteorological Society of Japan. Ser. II , https://doi.org/10.2151/jmsj.2019-047 (2019). Huang, J. et al. Dryland climate change: Recent progress and challenges. Reviews of Geophysics , 55 , 719–778 https://doi.org/10.1002/2016RG000550 (2017). Thuiller, W., Lavorel, S., Araújo, M. B., Sykes, M. T. & Prentice, I. C. Climate change threats to plant diversity in Europe. Proceedings of the National Academy of Sciences 102 , 8245-8250; https://doi.org/10.1073/pnas.0409902102 (2005). Waldvogel, A. M. et al. Evolutionary genomics can improve prediction of species’ responses to climate change. Evolution Letters , 4 , 4–18 https://doi.org/10.1002/evl3.154 (2020). Vilà-Cabrera, A., Coll, L., Martínez-Vilalta, J. & Retana, J. Forest management for adaptation to climate change in the Mediterranean basin: A synthesis of evidence. For. Ecol. Manag , 407 , 16–22 https://doi.org/10.1016/j.foreco.2017.10.021 (2018). He, X., Li, J., Wang, F., Zhang, J. & Chen, X. Variation and selection of Melia azedarach provenances and families. Journal of Northeast Forestry University , 47 , 1–7 https://doi.org/10.13332/j.1000-1522.20170321 (2019). Smith, A. B., Alsdurf, J., Knapp, M., Baer, S. G. & Johnson, L. C. Phenotypic distribution models corroborate species distribution models: A shift in the role and prevalence of a dominant prairie grass in response to climate change. Glob. Change Biol , 23 , 4365–4375 https://doi.org/10.1111/gcb.13666 (2017). Bellon, M. R., Dulloo, E., Sardos, J., Thormann, I. & Burdon, J. J. In situ conservation—harnessing natural and human-derived evolutionary forces to ensure future crop adaptation. Evolutionary applications , 10 , 965–977 https://doi.org/10.1111/eva.12521 (2017). Bidak, L. M., Heneidy, S. Z., Halmy, M. W. A. & El-Kenany, E. T. Sustainability potential for Ginkgo biloba L. plantations under climate change uncertainty: An ex-situ conservation perspective. Acta Ecol. Sin , https://doi.org/10.1016/j.chnaes.2021.09.012 (2021). Qin, F., Liu, S. & Yu, S. Effects of allelopathy and competition for water and nutrients on survival and growth of tree species in Eucalyptus urophylla plantations. For. Ecol. Manag , 424 , 387–395 https://doi.org/10.1016/j.foreco.2018.05.017 (2018). Zabel, F. et al. Global impacts of future cropland expansion and intensification on agricultural markets and biodiversity. Nat. Commun , 10 , 1–10 https://doi.org/10.1038/s41467-019-10775-z (2019). Additional Declarations No competing interests reported. Supplementary Files AttachmentTableS1.docx Cite Share Download PDF Status: Under Review Version 1 posted Editor invited by journal 26 Oct, 2021 Submission checks completed at journal 25 Oct, 2021 First submitted to journal 21 Oct, 2021 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-1004808","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":59043346,"identity":"bf899cd6-5adf-44f1-bbe6-291d322c4f0d","order_by":0,"name":"Lei Feng","email":"","orcid":"","institution":"Nanjing Forestry University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Lei","middleName":"","lastName":"Feng","suffix":""},{"id":59043348,"identity":"65d27aec-912d-4cc5-aee5-3fdcda27a2d0","order_by":1,"name":"Xiangni Tian","email":"","orcid":"","institution":"Yunnan University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Xiangni","middleName":"","lastName":"Tian","suffix":""},{"id":59043349,"identity":"9b4ce8b9-17ad-444e-8935-233b31ddada7","order_by":2,"name":"Yousry A. El-Kassaby","email":"","orcid":"","institution":"University of British Columbia","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Yousry","middleName":"A.","lastName":"El-Kassaby","suffix":""},{"id":59043350,"identity":"3fe0a343-efe3-4d6e-a6ec-ab20412b9edf","order_by":3,"name":"Jian Qiu","email":"","orcid":"","institution":"Nanjing Forestry University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Jian","middleName":"","lastName":"Qiu","suffix":""},{"id":59043351,"identity":"d93fba64-1c2f-4e83-92f8-8a1c28cd3772","order_by":4,"name":"Ze Feng","email":"","orcid":"","institution":"Kangda College of Nanjing Medical University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Ze","middleName":"","lastName":"Feng","suffix":""},{"id":59043352,"identity":"08b19c7a-84cc-46df-9580-fd66ba8fdefb","order_by":5,"name":"Jiejie Sun","email":"","orcid":"","institution":"University of British Columbia","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Jiejie","middleName":"","lastName":"Sun","suffix":""},{"id":59043353,"identity":"b294a401-8d23-4933-bc5e-99847a181afb","order_by":6,"name":"Guibin Wang","email":"","orcid":"","institution":"Nanjing Forestry University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Guibin","middleName":"","lastName":"Wang","suffix":""},{"id":59043354,"identity":"add868a2-35bb-41ea-b27a-953ef38badbd","order_by":7,"name":"Tongli Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA0klEQVRIiWNgGAWjYLCCBwZgivEBYwMRqnlARAJEC7MBCVogbDYJorTYs/cefpFQwJDYP7v9WjXvDjsG/vYDBGzhOZdmAXRY4ow7Z8pu855JZpA4k0BAi0SOmQFQS27DjZy027xtBxgMGIjVMh+opRishf8BQS3GD0BaNtxIP8YM1iJByJYzZ8yAgSxRv/FGDrPk3DPJPBI3CNjC3t5j/OHDHxtjuRvpDz+83WEnx99PwBYGUHQwMEiALARHKA9B9UDA/AFqIQEHjYJRMApGwYgFAC5rQYQ6RuDPAAAAAElFTkSuQmCC","orcid":"","institution":"University of British Columbia","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Tongli","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2021-10-21 16:29:09","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-1004808/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-1004808/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":14949591,"identity":"b4f39838-5bac-40b7-9648-c73c59a0d407","added_by":"auto","created_at":"2021-10-27 14:53:10","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":197659,"visible":true,"origin":"","legend":"Distributions of the 906 M. azedarach occurrence records.","description":"","filename":"fig1.png","url":"https://assets-eu.researchsquare.com/files/rs-1004808/v1/42a6b3e1092874bf73ac343c.png"},{"id":14949594,"identity":"90d5304d-9bb4-409c-9304-31baa3de6bc0","added_by":"auto","created_at":"2021-10-27 14:53:10","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":62815,"visible":true,"origin":"","legend":"Bubble diagram of evaluation metrics for both the training and testing data, where small bubble represents the training and big bubble represents the testing. Different color bubbles represent different models.","description":"","filename":"fig2.png","url":"https://assets-eu.researchsquare.com/files/rs-1004808/v1/5c2c778112dafc899e261dc3.png"},{"id":14949940,"identity":"bfda40f3-b4cf-4f26-ad54-f636fa7e5bd8","added_by":"auto","created_at":"2021-10-27 14:59:10","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":282002,"visible":true,"origin":"","legend":"Response curves of the top six important climate variables (a-f) in the RF model. When the logical output \u003e 0.5, the probability of species presence under this condition is higher than that under a typical condition, indicating that the condition is suitable for tree species.","description":"","filename":"fig3.png","url":"https://assets-eu.researchsquare.com/files/rs-1004808/v1/bb3631eb592c9fe07e30dc90.png"},{"id":14949596,"identity":"f64953aa-3697-46cc-be43-f238bd002bae","added_by":"auto","created_at":"2021-10-27 14:53:11","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":416523,"visible":true,"origin":"","legend":"(a) M. azedarach contemporary suitable habitats distributions (1960 –1990) and (b) their percentage representations.","description":"","filename":"fig4.png","url":"https://assets-eu.researchsquare.com/files/rs-1004808/v1/d9ccc161be9b9f197e688319.png"},{"id":14949595,"identity":"ea9e6654-ae67-4cad-a81c-62a535c5f80e","added_by":"auto","created_at":"2021-10-27 14:53:10","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":299479,"visible":true,"origin":"","legend":"RF projected range changes for M. azedarach under RCP 8.5 and RCP 4.5 climate change scenarios (a-f) (g shows areas of habitat change).","description":"","filename":"fig5.png","url":"https://assets-eu.researchsquare.com/files/rs-1004808/v1/928d04cc9f82942fd119a6a1.png"},{"id":15675905,"identity":"b67b20d7-f48f-4921-85f2-0faebc26847a","added_by":"auto","created_at":"2021-11-18 14:30:32","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1632107,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-1004808/v1/fe8debc2-a2ab-4ebe-a1e2-5cd050fcb3c5.pdf"},{"id":14949834,"identity":"7c028b01-e524-48c5-b043-82197520e38c","added_by":"auto","created_at":"2021-10-27 14:56:10","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":25318,"visible":true,"origin":"","legend":"","description":"","filename":"AttachmentTableS1.docx","url":"https://assets-eu.researchsquare.com/files/rs-1004808/v1/d32d792f79ef7785494ce731.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003ePredicting Suitable Habitats of \u003cem\u003eMelia Azedarach\u003c/em\u003e L. Using Data Mining\u003c/p\u003e","fulltext":[{"header":"1 Introduction","content":"\u003cp\u003e \u003cem\u003eMelia azedarach\u003c/em\u003e L., Meliaceae, is a fast-growing species with good timber attributes of multiple-use, such as construction and furniture, farm tools, boats, vehicles, and musical instruments manufacturing\u003csup\u003e\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e\u003c/sup\u003e. The species roots, bark, flowers, and fruits are of high medicinal values\u003csup\u003e\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e,\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e\u003c/sup\u003e. Additionally, its fruit and leaf extracts can control numerous agricultural pests and are commonly used as biological pesticides raw materials\u003csup\u003e\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e\u003c/sup\u003e. The species is an excellent urban greening tree that is resistant to smoke and dust and can absorb many toxic and harmful gases. At present, it is planted in more than 50 countries\u003csup\u003e\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e,\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e\u003c/sup\u003e. The species productivity is climate-dependent, and it is expected that climate change will reshape its future suitable habitat\u003csup\u003e\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eThe intensification of global warming, accompanied by the frequent occurrence of extreme natural disturbances, such as wind storms, droughts, fires, and floods, will undoubtedly impact the global forest ecosystem\u003csup\u003e\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e\u003c/sup\u003e. Different tree species respond differently to climate change, with positive and negative effects in different areas. For example, climate change is expected to increase the suitable habitats of Mediterranean oaks in the western temperate areas\u003csup\u003e\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e\u003c/sup\u003e as well as the total suitable habitat for \u003cem\u003eCypripedium japonicum\u003c/em\u003e\u003csup\u003e\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e\u003c/sup\u003e. Conversely, eucalyptus species are expected to face future challenges due to their poor spread capability\u003csup\u003e\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e\u003c/sup\u003e, and Persian oak (\u003cem\u003eQuercus macranthera\u003c/em\u003e) will experience a reduction in its contemporary range and is expected to move to higher altitudes\u003csup\u003e\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e\u003c/sup\u003e. Consequently, assessing the impact of climate change on the potential distribution of species and formulating sustainable forest management strategies are critical to maintaining forest ecosystems integrity.\u003c/p\u003e \u003cp\u003eWith climate change challenges, species distribution models (SDMs) have become essential tools for projecting plants adaptation to a changing climate\u003csup\u003e\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e\u003c/sup\u003e. At present, a variety of data mining techniques have been applied to model species distribution data. These include: 1) Generalize linear model (GLM), a common regression model first introduced by Austin et al. (1983), to simulate tree species distribution and subsequently was used to predict the spread of Emerald Ash Borer (\u003cem\u003eAgrilus planipennis\u003c/em\u003e) in southern Ontario, Canada\u003csup\u003e\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e\u003c/sup\u003e; 2) Gradient boosting machine (GBM), a machine-learning technology used to generate predictive models in the form of a collection of weak predictive models\u003csup\u003e\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e\u003c/sup\u003e and currently is being used to predict invasive plant species distribution, high-resolution, high-precision multi-type vegetation mapping, and species distribution models\u003csup\u003e\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e,\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e\u003c/sup\u003e; 3) Random Forest (RF), a machine-learning technology through building a large number of decision trees during the program\u0026rsquo;s training phase\u003csup\u003e\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e\u003c/sup\u003e and presently is being used to predict invasive species range, classification of tree species based on hyperspectral information, and prediction of stands basal areas and the distribution of plantation forests\u003csup\u003e\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e,\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e\u003c/sup\u003e; 4) Support Vector Machine (SVM), a supervised learning model used for data classification and regression analysis and is widely used to classify invasive species and detect the presence of farmland weeds\u003csup\u003e\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e,\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e\u003c/sup\u003e; 5) Maximum Entropy (MaxEnt), a machine-learning technology by finding the maximum entropy of the probability distribution of the species through the species distribution and environmental data to estimate and predict future species distribution\u003csup\u003e\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e\u003c/sup\u003e, and mainly is being used in crop niches, plant diseases and insect pests, and species invasion prediction\u003csup\u003e\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e,\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e\u003c/sup\u003e; 6) Extreme Gradient Boosting (XGBoost), an open-source software library algorithm effective in predicting species abundance and identifying critical environmental factors\u003csup\u003e\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e\u003c/sup\u003e, and is playing an essential role in designing new drugs to treat related diseases; and 7) Naive Bayesian Model (NBM), a series of simple probabilistic classifiers based on Bayes' theorem and independent assumptions between features\u003csup\u003e\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e\u003c/sup\u003e, and mainly is being applied in forestry for predicting the potential distribution areas of \u003cem\u003eTaxus chinensis\u003c/em\u003e and identifying plant long non-coding RNA and predicting its functions\u003csup\u003e\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eUnderstanding the potential distribution of \u003cem\u003eM. azedarach\u003c/em\u003e is of great significance to its cultivation and conservation. Studies conducted on \u003cem\u003eM. azedarach\u003c/em\u003e were mainly focused on tree and stand productivity, extraction of active ingredients, and pest resistance potential\u003csup\u003e\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e,\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e\u003c/sup\u003e. Research on \u003cem\u003eM. azedarach\u003c/em\u003e potential distribution as affected by climate change is lacking and thus, the present study is aimed at exploring the above-mentioned seven data mining techniques to establish climate-based distribution prediction models and select the best model in predictions of the species future suitable habitat. Our specific objectives were to: 1) compare the prediction accuracy of the seven modeling algorithms and select the one with the best performance; 2) determine the key climatic factors related to the species distribution; 3) develop current and future species suitable habitat maps highlighting the areas of change; and 4) assess the potential impact of future climate change on the species suitable habitat.\u003c/p\u003e"},{"header":"2 Material And Methods","content":"\u003cdiv class=\"Section2\" id=\"Sec3\"\u003e\n \u003ch2\u003e2.1 Species location data\u003c/h2\u003e\n \u003cp\u003eHere, we used the Chinese presence and absence \u003cem\u003eM. azedarach\u003c/em\u003e data to establish the prediction models. First, we found 1,432 presence data (data source: Global Biodiversity Information Facility (GBIF), \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.gbif.org\u003c/span\u003e\u003c/span\u003e, and the Chinese Virtual Herbarium (CVH), \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttp://www.cvh.ac.cn/\u003c/span\u003e\u003c/span\u003e). To avoid redundant sampling, we deleted those sample points with similar longitude and latitude\u003csup\u003e\u003cspan class=\"CitationRef\"\u003e29\u003c/span\u003e\u003c/sup\u003e. Then a 0.01\u0026deg; mesh thinning was performed, and the actual distance corresponding to 0.01\u0026deg; was about 1km and only one distribution point was reserved in each grid so that the distance between sample points was more than 1 km\u003csup\u003e\u003cspan class=\"CitationRef\"\u003e30\u003c/span\u003e\u003c/sup\u003e. Finally, a total of 906 samples were included for model building (Figure. 1).\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv class=\"Section2\" id=\"Sec4\"\u003e\n \u003ch2\u003e2.2 Environment variables\u003c/h2\u003e\n \u003cp\u003eWe established a GLM model with M. azedarach presence-absence data as dependent variables and 16 climatic factors derived from ClimateAP_v221 software (\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttp://ClimateAP.net\u003c/span\u003e\u003c/span\u003e) as predictors (Table S1)\u003csup\u003e\u003cspan class=\"CitationRef\"\u003e31\u003c/span\u003e\u003c/sup\u003e. Correlation analysis showed that there was strong data collinearity among the 16 climate variables. Then we used stepwise regression analysis to eliminate those variables causing the observed multicollinearity\u003csup\u003e\u003cspan class=\"CitationRef\"\u003e32\u003c/span\u003e\u003c/sup\u003e and ultimately reduced the climate variable to ten\u003csup\u003e\u003cspan class=\"CitationRef\"\u003e33\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv class=\"Section2\" id=\"Sec5\"\u003e\n \u003ch2\u003e2.3 Model development and prediction\u003c/h2\u003e\n \u003cp\u003eWe used seven models (Generalize Linear Model (GLM), Gradient Boosting Machine (GBM), Random Forest (RF), Support Vector Machine (SVM), Maximum Entropy (MaxEnt), Extreme Gradient Boosting (XGBoost), and Naive Bayesian Model (NBM)) to associate the distribution of \u003cem\u003eM. azedarach\u003c/em\u003e with climate variables. Firstly, we used the \u0026ldquo;dismo\u0026rdquo; package in R to randomly generate 2,000 \u0026ldquo;pseudo-nonexistent\u0026rdquo; records in the study area. Models were established with species presence-absence data as the dependent variable and climate variable as the independent variables. In order to evaluate the models\u0026rsquo; prediction accuracy, we randomly selected 70% data for training and the remaining 30% data for testing (validation). We used the \u0026ldquo;caret\u0026rdquo; package to train and adjust the parameters for all the seven models except Maxent, since it facilitates the process of building, evaluating, as well as selecting features. Then, ten cross-verifications were carried out, and each model was repeated three times. At the same time, the Maxent model was executed using the Maxent version 3.4.4 software in R-package.\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv class=\"Section2\" id=\"Sec6\"\u003e\n \u003ch2\u003e2.4 Model validation\u003c/h2\u003e\n \u003cp\u003eTo assess the performance of the seven predictive models, we compared their area under receiver operating character curve (AUC), Kappa, and accuracy. The AUC is the probability value, with evaluation criteria were: 0.5-0.6 = fails, 0.6-0.7 = poor, 0.7-0.8 = fair, 0.8-0.9 = good, 0.9-1.0 = excellent\u003csup\u003e34\u003c/sup\u003e. Kappa coefficient is an index to measure classification accuracy. The calculation result of kappa is -1 to 1, but usually, kappa falls between 0 and 1, which can be divided into five groups: 0.0-0.2 means very low consistency, 0.21-0.40 means general consistency, 0.41-0.60 means moderate consistency, 0.61-0.80 means high consistency, 0.81-1 means almost perfect\u003csup\u003e\u003cspan class=\"CitationRef\"\u003e35\u003c/span\u003e\u003c/sup\u003e. Accuracy refers to the proximity of measured values to specific values, and it is reported as the average cross-validated accuracy\u003csup\u003e\u003cspan class=\"CitationRef\"\u003e36\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv class=\"Section2\" id=\"Sec7\"\u003e\n \u003ch2\u003e2.5 Habitat Classification\u003c/h2\u003e\n \u003cp\u003eAppropriate habitat evaluation index values were determined as follows: predicted values of 0-0.2, 0.2-0.4, 0.4-0.6, and \u0026gt;0.06 were deemed unsuitable, low-, medium-, and highly-suitable habitat, respectively\u003csup\u003e\u003cspan class=\"CitationRef\"\u003e37\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e\n\u003c/div\u003e"},{"header":"3 Results","content":"\u003cdiv class=\"Section2\" id=\"Sec9\"\u003e\n \u003ch2\u003e3.1 Models performance evaluation\u003c/h2\u003e\n \u003cp\u003eThrough the cross-validation evaluation of the tested models, Accuracy, Kappa, and AUC values were obtained for the training and testing portions of each model (Figure. 2). All models performed well (AUC\u0026gt;0.8, Kappa\u0026gt;0.5, and Accuracy\u0026gt;0.7). For the training data, the seven models AUC values varied from 0.8825 (NBM) to 1 (RF), Kappa values varied from 0.5754 (GLM) to 0.9988 (RF), and Accuracy values ranged from 0.7887 (NBM) to 0.9995 (RF). While the testing data produced AUC values varied from 0.8471 (NBM) to 0.9039 (RF), Kappa values varied from 0.5335 (SVM) to 0.5896 (MaxEnt), and Accuracy values ranged from 0.7678 (NBM) to 0.8138 (XGBoost). Overall, the three evaluation metrices all indicated that the Random Forest (RF) model provided the best predictive performance and while the Naive Bayesian Model (NBM) was the worst, thus, we selected the RF model to establish \u003cem\u003eM. Azedarach\u003c/em\u003e distribution patterns.\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv class=\"Section2\" id=\"Sec10\"\u003e\n \u003ch2\u003e3.2 Important climate variables and their response curves in Random Forest (RF)\u003c/h2\u003e\n \u003cp\u003eThe top three climate variables contributing to the RF model include MCMT (189.24), NFFD (180.69), and DD\u0026gt;18 (104.77), followed by TD (72.82), MAP (69.43), DD\u0026lt;18 (64.12), DD\u0026gt;5 (56.27), and AHM (54.88); and finally DD\u0026lt;0 (44.01) and PAS (28.54) also played some roles in the determining the potential distribution of \u003cem\u003eM. azedarach\u003c/em\u003e (Table \u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e).\u003c/p\u003e\n \u003cp\u003eFigure. 3 displayed the relationships between the top six climate variables and \u003cem\u003eM. azedarach\u003c/em\u003e suitability according to the predictions of RF algorithms. The habitat suitable range was between -10 and -28℃ for MCMT (Figure. 3a), between 0 and 175 days for NFFD (Figure. 3b), between 0 and 250 for DD\u0026gt;18 (Figure. 3c), between 5 and 21℃ for TD (Figure. 3d), between 0 and 480 mm for MAP (Figure. 3e), and between 0 and 1750 for DD\u0026lt;18 (Figure. 3f).\u003c/p\u003e\n \u003cdiv class=\"gridtable\"\u003e\u003ctable border=\"1\" id=\"Tab1\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eContributions of the most influencing climate variables to the M. Azedarach Random Forest (RF) model\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003ccolgroup cols=\"3\"\u003e\u003c/colgroup\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eVariable\u003csup\u003e\u003cspan class=\"CitationRef\"\u003e1\u003c/span\u003e\u003c/sup\u003e\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eUnits\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eOverall contribution\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMCMT\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u0026deg;C\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e189.24\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNFFD\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eday\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e180.69\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDD\u0026gt;18\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u0026deg;C-days\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e104.77\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eTD\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u0026deg;C\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e72.82\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMAP\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003emm\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e69.43\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDD\u0026lt;18\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u0026deg;C-days\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e64.12\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDD\u0026gt;5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u0026deg;C-days\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e56.27\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAHM\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e54.88\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDD\u0026lt;0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u0026deg;C-days\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e44.01\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePAS\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003emm\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e28.54\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003ctfoot\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"3\"\u003e\u003csup\u003e1\u003c/sup\u003esee Table S1 for variables abbrivations.\u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tfoot\u003e\n \u003c/table\u003e\n \u003c/div\u003e\n\u003c/div\u003e\n\u003cdiv class=\"Section2\" id=\"Sec11\"\u003e\n \u003ch2\u003e3.3 RF model prediction of \u003cem\u003eM. azedarach\u003c/em\u003e contemporary habitats distribution\u003c/h2\u003e\n \u003cp\u003eThe spatial distributions of \u003cem\u003eM. azedarach\u003c/em\u003e and areas of suitable habitats under current climatic conditions as predicted by the RF algorithm are shown Figure. 4. The overall suitable habitat was mainly distributed between 18 and 40\u0026deg;N (Figure. 4a). These habitats were classified as: 1) highly-suitable habitats (mainly scattered in Shandon (SD), Jiangsu (JS), Shanghai (SH), Zhejiang (ZJ), Guangdong (GD), Hunan (HN), Hainan (HI), South Jiangxi (JX), the junction of the three provinces of Hubei (HB), Anhui (AH), Jiangxi (JX), and the junction of Chongqing (CQ) and Sichuan (SC), covering 9.3 \u0026times; 10\u003csup\u003e5\u003c/sup\u003e km\u003csup\u003e\u003cspan class=\"CitationRef\"\u003e2\u003c/span\u003e\u003c/sup\u003e (9.6%; Figure. 4b); 2) medium-suitable habitats (scattered around the high-suitable habitats, covering 6.8 \u0026times; 10\u003csup\u003e5\u003c/sup\u003e km\u003csup\u003e\u003cspan class=\"CitationRef\"\u003e2\u003c/span\u003e\u003c/sup\u003e (7%; Figure. 4b) and specifically concentrated in eastern Sichuan (SC), northern and western Shandong (SD), and the junction of Hubei (HB) and Hunan (HN)); and 3) low-suitable habitats (slightly larger than the medium-suitable habitats, covering 7.1 \u0026times; 10\u003csup\u003e5\u003c/sup\u003e km\u003csup\u003e\u003cspan class=\"CitationRef\"\u003e2\u003c/span\u003e\u003c/sup\u003e (7.4%; Figure. 4b)), and it is distributed in Yunnan (YN), central Guangxi (GX), eastern and northern Guizhou (GZ), southern Shaanxi (SN), western and northern Henan (HA), and southern Hebei (HE)).\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv class=\"Section2\" id=\"Sec12\"\u003e\n \u003ch2\u003e3.4 RF model prediction of \u003cem\u003eM. azedarach\u003c/em\u003e projected suitable habitats future changes\u003c/h2\u003e\n \u003cp\u003eFuture projections using the RF model with two different climate scenarios (RCP 8.5 and RCP 4.5) indicated a clear graphical expansion of \u003cem\u003eM. azedarach\u003c/em\u003e in the future periods with an increasing magnitude over time (Figure. 5). The projected range increase was greatest under RCP 8.5 as compated to RCP 4.5 (Figure. 5). More specifically, the expanded area would increase by 562.6 \u0026times; 10\u003csup\u003e3\u003c/sup\u003e km\u003csup\u003e2\u003c/sup\u003e and 584.5 \u0026times; 10\u003csup\u003e3\u003c/sup\u003e km\u003csup\u003e\u003cspan class=\"CitationRef\"\u003e2\u003c/span\u003e\u003c/sup\u003e by 2020s, 807.4 \u0026times; 10\u003csup\u003e3\u003c/sup\u003e km\u003csup\u003e2\u003c/sup\u003e and 930.3 \u0026times; 10\u003csup\u003e3\u003c/sup\u003e km\u003csup\u003e\u003cspan class=\"CitationRef\"\u003e2\u003c/span\u003e\u003c/sup\u003e by 2050s, and 906.1 \u0026times; 10\u003csup\u003e3\u003c/sup\u003e km\u003csup\u003e2\u003c/sup\u003e and 1486.3 \u0026times; 10\u003csup\u003e3\u003c/sup\u003e km\u003csup\u003e\u003cspan class=\"CitationRef\"\u003e2\u003c/span\u003e\u003c/sup\u003e by 2080s under the RCP4.5 and RCP8.5 scenarios, respectively (Figure. 5g). The main expanded area will be located in Yunnan (YN), Anhui (AH), Henan (HA), Shanxi (SX), Shaanxi (SN), central Guangxi (GX), central Jiangxi (JX), and northern Guizhou (GZ). Interestingly, based on the RCP8.5 climate scenario, Xinjiang (XJ) would see a larger magnitude of area expansion in 2080s (Figure. 5f). Additionally, the species stable range area showed the same change pattern as that of the expanded area (Figure. 5g). The main stable area included Guangdong (GD), Guangxi (GX), Guizhou (GZ), Hunan (HN), Chongqing (CQ), Fujian (FJ), Zhejiang (ZJ), Jiangsu (JS), southwestern Jiangxi (JX), and eastern Sichuan (SC) (Figure. 5a-f). Furthermore, the species area loss exhibited an opposite trend to that of expansion and stable range areas (Figure. 5f) and most of the loss area was mainly distributed in eastern coastal provinces near 30-38\u0026deg;N (e.g., Shandong (SD)) (Figure. 5).\u003c/p\u003e\n\u003c/div\u003e"},{"header":"4 Discussion","content":"\u003cdiv id=\"Sec14\" class=\"Section2\"\u003e \u003ch2\u003e4.1 Model performance\u003c/h2\u003e \u003cp\u003eHere, we used the Area Under the Curves (AUC), Kappa statistic, and Accuracy to evaluate the performance of seven species range prediction models (Generalized Linear Models (GLM), Gradient Boosting Machine (GBM), Maximum Entropy (MaxEnt), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), Naive Bayesian Model (NBM), and Random Forest (RF)) to predict \u003cem\u003eM. azedarach\u003c/em\u003e contemporary and future ranges under two climate scenarios (RCP 8.5 and RCP 4.5). The results showed that Random Forest (RF) and Extreme Gradient Boosting (XGBoost) were the top-performing models with RF being the best, while Naive Bayesian Model (NBM) and Generalized Linear Models (GLM) were the low-performing with the NBM being the worst. Multiple lines of evidence support the superiority of the RF algorithm\u003csup\u003e\u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e\u003c/sup\u003e. The RF is an ensemble machine-learning model that could handle data with multi-dimensional, non-linear relationships, high-order correlations, and missing values\u003csup\u003e\u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e39\u003c/span\u003e\u003c/sup\u003e. Additionally, the RF model is capable of avoiding the accuracy reduction problem caused by missing and noisy data in the training sample when predicting the relationship between a large number of predictor variables and the response variable\u003csup\u003e\u003cspan citationid=\"CR40\" class=\"CitationRef\"\u003e40\u003c/span\u003e\u003c/sup\u003e, attributes supporting the present study results. In contrast, while the NBM like RF is also a machine learning algorithm, it was proven to be not very sensitive to missing data, and the algorithm is relatively simple\u003csup\u003e\u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e41\u003c/span\u003e\u003c/sup\u003e. Studies have demonstrated that more complex species distributions models provided better predictive performance demonstrating the suitability of the RF model in processing complex high-dimensional data such as the data used in the present study\u003csup\u003e\u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e42\u003c/span\u003e\u003c/sup\u003e. Moreover, the NBM is a linear classifier and similar to the traditional linear statistical methods, all are insufficient in revealing the complex relationship among environmental variables\u003csup\u003e\u003cspan citationid=\"CR43\" class=\"CitationRef\"\u003e43\u003c/span\u003e\u003c/sup\u003e. In our case, the two linear models, GBM and GLM, demonstrated this with their poor predictive power. Additionally, we observed that the prediction accuracy of the Extreme Gradient Boosting (XGBoost) was very close to that of RF as the XGBoost has good generalization performance\u003csup\u003e\u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e\u003c/sup\u003e. Although, previous studies have shown that Maximum Entropy (MaxEnt), Support Vector Machine (SVM), and Gradient Boosting Machine (GBM) models performed well in simulating species suitability distribution\u003csup\u003e\u003cspan citationid=\"CR45\" class=\"CitationRef\"\u003e45\u003c/span\u003e,\u003cspan citationid=\"CR46\" class=\"CitationRef\"\u003e46\u003c/span\u003e\u003c/sup\u003e, our results have shown that the prediction accuracy of these models was intermediate relative to the performance of the seven tested models. These phenomena may indicate that species characteristics and sample size also have influence on the accuracy of species distribution models\u003csup\u003e\u003cspan citationid=\"CR47\" class=\"CitationRef\"\u003e47\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec15\" class=\"Section2\"\u003e \u003ch2\u003e4.2 The importance of climate variables\u003c/h2\u003e \u003cp\u003eOur study along with several others\u003csup\u003e\u003cspan additionalcitationids=\"CR49\" citationid=\"CR48\" class=\"CitationRef\"\u003e48\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR50\" class=\"CitationRef\"\u003e50\u003c/span\u003e\u003c/sup\u003e were based on the assumption that species distribution is mainly determined by climate\u003csup\u003e\u003cspan citationid=\"CR51\" class=\"CitationRef\"\u003e51\u003c/span\u003e,\u003cspan citationid=\"CR52\" class=\"CitationRef\"\u003e52\u003c/span\u003e\u003c/sup\u003e. It is well documented that climatic factors are key elements for most species\u0026rsquo; population regeneration\u003csup\u003e\u003cspan citationid=\"CR53\" class=\"CitationRef\"\u003e53\u003c/span\u003e\u003c/sup\u003e. Here, our results indicated that temperature-associated climate factors have greater influence on \u003cem\u003eM. azedarach\u003c/em\u003e suitable habitats than precipitation factors. Specifically, the top three temperature-related climate variables included mean coldest month temperature (MCMT), the number of frost-free days (NFFD), and degree-days below 18\u0026deg;C (DD\u0026gt;18)), with MCMT contributing the most. This shows that low temperature was the main climatic factor that restricted \u003cem\u003eM. azedarach\u003c/em\u003e distribution, which is consistent with previous studies, as low-temperature stress imparted a negative impact on plant physiological and biochemical responses (e.g., plant membrane system disorder, photosynthetic rate decline, harmful active oxygen increased, and osmotic adjustment substances increase)\u003csup\u003e\u003cspan citationid=\"CR54\" class=\"CitationRef\"\u003e54\u003c/span\u003e\u003c/sup\u003e. \u003cem\u003eM. azedarach\u003c/em\u003e is known to prefer warm and humid climates, suitable temperature and abundant precipitation were conducive to the species growth and biomass accumulation. Research has demonstrated that \u003cem\u003eM. azedarach\u003c/em\u003e ground diameter shown increasing trend with precipitation increase\u003csup\u003e\u003cspan citationid=\"CR55\" class=\"CitationRef\"\u003e55\u003c/span\u003e\u003c/sup\u003e. The extension of the number of frost-free days (NFFD) was beneficial to increasing \u003cem\u003eM. azedarach\u003c/em\u003e seed size and quality\u003csup\u003e\u003cspan citationid=\"CR56\" class=\"CitationRef\"\u003e56\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec16\" class=\"Section2\"\u003e \u003ch2\u003e4.3 Range shift in response to climate change\u003c/h2\u003e \u003cp\u003eOur study showed that \u003cem\u003eM. azedarach\u003c/em\u003e would benefit from the anticipated climate change. More specifically, we found the RCP 8.5 scenario to be more favorable for the species habitat suitability expansion as compared to the RCP 4.5 scenario (Figure. 5g). The RCP 8.5 scenario predicted a greater increase in future temperature warming and precipitation, providing climatic conditions favorable to the species growth\u003csup\u003e\u003cspan citationid=\"CR56\" class=\"CitationRef\"\u003e56\u003c/span\u003e\u003c/sup\u003e. From the species geographic range change point of view, it is expected that the future suitable habitat distribution to expand north- and west-ward. Compared with the RCP4.5 scenario, the predicted trend of suitable habitats changes of the RCP8.5 scenario was more significant in the plateau area near 40 \u0026deg;N (Figure. 5), including the Xinjiang Tarim Basin (RCP8.5) (Figure. 5f). Under the RCP4.5 and RCP8.5 scenarios, the future temperature is envisaged to rise by 1.4 - 1.8 and 2.0 - 3.7\u0026deg;C, respectively, making high latitude areas warmer, resulting in a contemplated rise of mountains tree line, which would ultimately provide the species with a potential of geographic range expansion\u003csup\u003e\u003cspan citationid=\"CR57\" class=\"CitationRef\"\u003e57\u003c/span\u003e\u003c/sup\u003e. At the same time, we noted that the suitable habitat in the Shandong region would experience substantial range loss (Figure. 5), caused by a drastic change in climatic conditions from mainly dry continental airflow with little precipitation to a future warmer climate associated with intensified precipitation reduction\u003csup\u003e\u003cspan citationid=\"CR58\" class=\"CitationRef\"\u003e58\u003c/span\u003e\u003c/sup\u003e. Additionally, the impact of subtropical high pressure could not be overlooked as the Shandong is often affected by sinking air currents with long periods of high temperature and low precipitation. This subtropical high pressure is expected to gradually moved northward, followed by anticipated clear trend of northward movement associated with precipitation pattern change in the Shandong\u003csup\u003e\u003cspan citationid=\"CR59\" class=\"CitationRef\"\u003e59\u003c/span\u003e\u003c/sup\u003e. To a certain extent, the contemplated climate changes are expected to exacerbate the dryland climate in the Shandong, creating predominantly drought conditions that is unsuitable for the drought-intolerant \u003cem\u003eM. azedarach\u003c/em\u003e\u003csup\u003e\u003cspan citationid=\"CR60\" class=\"CitationRef\"\u003e60\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec17\" class=\"Section2\"\u003e \u003ch2\u003e4.4 Management strategies\u003c/h2\u003e \u003cp\u003eRapid climate change causes most tree populations to exist in unsuitable environmental conditions, threatening their growth and survival and even leading to population extinction\u003csup\u003e\u003cspan citationid=\"CR61\" class=\"CitationRef\"\u003e61\u003c/span\u003e\u003c/sup\u003e. Some tree species adapted to the new climatic conditions by migrating to the same environmental gradient or evolving\u003csup\u003e\u003cspan citationid=\"CR62\" class=\"CitationRef\"\u003e62\u003c/span\u003e\u003c/sup\u003e; however, other tree species would benefit from climate change\u003csup\u003e\u003cspan citationid=\"CR63\" class=\"CitationRef\"\u003e63\u003c/span\u003e\u003c/sup\u003e. \u003cem\u003eM. azedarach\u003c/em\u003e belongs to those species who would benefit from future climate change leading to anticipated range expansion. The wide distribution of \u003cem\u003eM. azedarach\u003c/em\u003e harbours abundant phenotypic variation and most of the species phenotypic diversity is mainly distributed in the southwest and south regions and to a lesser extent in other regions\u003csup\u003e\u003cspan citationid=\"CR64\" class=\"CitationRef\"\u003e64\u003c/span\u003e\u003c/sup\u003e. It is worth noting that if a widely distributed species could not track the changing climate due to long-term local adaptation, they would become more vulnerable\u003csup\u003e\u003cspan citationid=\"CR65\" class=\"CitationRef\"\u003e65\u003c/span\u003e\u003c/sup\u003e. Therefore, to prevent this uncertainty, we suggest taking proactive \u003cem\u003ein-situ\u003c/em\u003e conservation measures for Yunnan, Guizhou, Sichuan, Guangdong, and Guangxi regions, as they are rich in phenotypic diversity which will help in coping with future environmental uncertainty\u003csup\u003e\u003cspan citationid=\"CR66\" class=\"CitationRef\"\u003e66\u003c/span\u003e\u003c/sup\u003e. Assisted migration initiatives should applied to presently unsuitable habitats that are expected to be suitable in the future. For example, the northern regions of Jiangxi, Hubei, Anhui, Henan, and areas near 40\u0026deg;N are reasonable targets for assisted migration conservation measures\u003csup\u003e\u003cspan citationid=\"CR67\" class=\"CitationRef\"\u003e67\u003c/span\u003e\u003c/sup\u003e. We recommend for areas that would be negatively affected by future climate as Shandong, taking \u003cem\u003eex-situ\u003c/em\u003e measures through establishing botanical gardens and seed banks in suitable habitats to protect their resources. Therefore, analyzing the \u003cem\u003eex-situ\u003c/em\u003e target areas\u0026rsquo; climate ecology could provide reference for breeding programs and seed transfer guidelines/polices. At the same time, we suggest that other biological factors along with climate should also be considered in the species future research, such as species interaction (allelopathy, soil nutrient competition), land-use change (bio-energy farmland expansion), and the influence of human activities\u003csup\u003e\u003cspan citationid=\"CR68\" class=\"CitationRef\"\u003e68\u003c/span\u003e,\u003cspan citationid=\"CR69\" class=\"CitationRef\"\u003e69\u003c/span\u003e\u003c/sup\u003e, these factors collectively affect the contemporary and future distribution of \u003cem\u003eM. azedarach\u003c/em\u003e.\u003c/p\u003e \u003c/div\u003e"},{"header":"5 Conclusion","content":"\u003cp\u003eHere, we used three common model accuracy evaluation indicators to compare the suitability of seven data mining techniques for predicting \u003cem\u003eM. azedarach\u003c/em\u003e distribution. The RF model, with its strong robustness and stability, provided the highest accuracy in establishing a climate niche model. Based on this model, maps of contemporary and future suitable habitats were developed. The RF prediction results indicated that \u003cem\u003eM. azedarach\u003c/em\u003e would benefit from future climate change through range expansion and this has tendency towards north- and west-ward expansion. In order to maximize the species protection and development, we recommend taking a proactive \u003cem\u003ein-situ\u003c/em\u003e conservation measures to conserve genetic variation for adaptation to uncertainties and \u003cem\u003eex situ\u003c/em\u003e conservation to protect genetic resources under risk, and assisted migration to better use the areas with good potential in future climates.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003eAuthor Contributions: L.F., Y.E., W.G., and T.W. participated in the data analysis, and\u0026nbsp;wrote the paper. X.T., J.Q., Z.F., and J.S. participated in the data preparation and processing. W.G. and T.W. designed the study. and T.W. also provided the paper editing. All the authors read and approved the final manuscript.\u003c/p\u003e\n\u003cp\u003eFunding: This work was jointly funded by the National Key Research and Development Program of China (No. 2017YFD0600700), and the Special Admission for Postgraduate Study Abroad Program by China Scholarship Council (No. 202008320472).\u003c/p\u003e\n\u003cp\u003eConflicts of Interest: The authors declare no conflict of interest.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n \u003cli\u003e\u003cspan\u003eChen, L. \u003cem\u003eet al.\u003c/em\u003e Geographic variation in traits of fruit stones and seeds of Melia azedarach. \u003cem\u003eJournal of Beijing Forestry University\u003c/em\u003e, \u003cstrong\u003e36\u003c/strong\u003e, 15\u0026ndash;20 (2014).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eAngamuthu, D., Purushothaman, I., Kothandan, S. \u0026amp; Swaminathan, R. Antiviral study on Punica granatum L., Momordica charantia L., Andrographis paniculata Nees, and Melia azedarach L., to human herpes virus-3. \u003cem\u003eEur. J. Integr. Med\u003c/em\u003e, \u003cstrong\u003e28\u003c/strong\u003e, 98\u0026ndash;108 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.eujim.2019.04.008\u003c/span\u003e\u003c/span\u003e (2019).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eWang, N. \u003cem\u003eet al.\u003c/em\u003e Selective ERK1/2 agonists isolated from Melia azedarach with potent anti-leukemic activity. \u003cem\u003eBMC Cancer\u003c/em\u003e, \u003cstrong\u003e19\u003c/strong\u003e, 1\u0026ndash;9 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1186/s12885-019-5914-8\u003c/span\u003e\u003c/span\u003e (2019).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eKhoshraftar, Z., Safekordi, A., Shamel, A. \u0026amp; Zaefizadeh, M. Evaluation of insecticidal activity of nanoformulation of Melia azedarach (leaf) extract as a safe environmental insecticide. \u003cem\u003eInternational Journal of Environmental Science and Technology\u003c/em\u003e, \u003cstrong\u003e17\u003c/strong\u003e, 1159\u0026ndash;1170 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s13762-019-02448-7\u003c/span\u003e\u003c/span\u003e (2020).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eAl-Rubae, A. Y. The potential uses of Melia azedarach L. as pesticidal and medicinal plant, review. \u003cem\u003eAmerican-Eurasian Journal of Sustainable Agriculture\u003c/em\u003e, \u003cstrong\u003e3\u003c/strong\u003e, 185\u0026ndash;194 (2009).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eNakatani, M. \u003cem\u003eet al.\u003c/em\u003e Three new antifeeding meliacarpinins from Chinese Melia azedarach Linn., \u003cstrong\u003e51\u003c/strong\u003e, 11731\u0026ndash;11736 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/0040-4020(95)00724-M\u003c/span\u003e\u003c/span\u003e (1995).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eWu, L., Kaewmano, A., Fu, P., Wang, W. \u0026amp; Fan, Z. Intra-annual Radial Growth of \u003cem\u003eMelia azedarach\u003c/em\u003e in a TropicalMoist Seasonal Forest and its Response to Environmental Factors in Xishuangbanna,Southwest\u0026nbsp;\u003c/span\u003e\u003cspan\u003eChina \u003cem\u003eActa Ecol. Sin\u003c/em\u003e, \u003cstrong\u003e40\u003c/strong\u003e, 6831\u0026ndash;6840 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.5846/stxb202003120508\u003c/span\u003e\u003c/span\u003e (2020).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eHoegh-Guldberg, O. \u003cem\u003eet al.\u003c/em\u003e The human imperative of stabilizing global climate change at 1.5 C. \u003cem\u003eScience\u003c/em\u003e \u003cstrong\u003e365\u003c/strong\u003e; \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1126/science.aaw6974\u003c/span\u003e\u003c/span\u003e (2019).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eL\u0026oacute;pez-Tirado, J., Vessella, F., Schirone, B. \u0026amp; Hidalgo, P. J. Trends in evergreen oak suitability from assembled species distribution models: assessing climate change in south-western Europe. \u003cem\u003eNew For\u003c/em\u003e, \u003cstrong\u003e49\u003c/strong\u003e, 471\u0026ndash;487 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s11056-018-9629-5\u003c/span\u003e\u003c/span\u003e (2018).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eXu, Y. \u003cem\u003eet al.\u003c/em\u003e Modelling the Effects of Climate Change on the Distribution of Endangered Cypripedium japonicum in China. Forests 12, 429; https://doi.org10.3390/f12040429(2021).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eBooth, T. H. Species distribution modelling tools and databases to assist managing forests under climate change. \u003cem\u003eFor. Ecol. Manag\u003c/em\u003e, \u003cstrong\u003e430\u003c/strong\u003e, 196\u0026ndash;203 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.foreco.2018.08.019\u003c/span\u003e\u003c/span\u003e (2018).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eDyderski, M. K., Paź, S., Frelich, L. E. \u0026amp; Jagodziński, A. M. How much does climate change threaten European forest tree species distributions? \u003cem\u003eGlobal change biology\u003c/em\u003e, \u003cstrong\u003e24\u003c/strong\u003e, 1150\u0026ndash;1163 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1111/gcb.13925\u003c/span\u003e\u003c/span\u003e (2018).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eZhong, Y. \u003cem\u003eet al.\u003c/em\u003e A Generalized Linear Mixed Model Approach to Assess Emerald Ash Borer Diffusion. \u003cem\u003eISPRS International Journal of Geo-Information\u003c/em\u003e, \u003cstrong\u003e9\u003c/strong\u003e, 414 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3390/ijgi9070414\u003c/span\u003e\u003c/span\u003e (2020).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eCho, G., Yim, J., Choi, Y., Ko, J. \u0026amp; Lee, S. H. Review of machine learning algorithms for diagnosing mental illness. \u003cem\u003ePsychiatry investigation\u003c/em\u003e, \u003cstrong\u003e16\u003c/strong\u003e, 262 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.30773/pi.2018.12.21.2\u003c/span\u003e\u003c/span\u003e (2019).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eBrun, P. \u003cem\u003eet al.\u003c/em\u003e Model complexity affects species distribution projections under climate change. \u003cem\u003eJ. Biogeogr\u003c/em\u003e, \u003cstrong\u003e47\u003c/strong\u003e, 130\u0026ndash;142 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1111/jbi.13734\u003c/span\u003e\u003c/span\u003e (2020).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eShiferaw, H., Bewket, W. \u0026amp; Eckert, S. Performances of machine learning algorithms for mapping fractional cover of an invasive plant species in a dryland ecosystem. \u003cem\u003eEcology and evolution\u003c/em\u003e, \u003cstrong\u003e9\u003c/strong\u003e, 2562\u0026ndash;2574 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1002/ece3.4919\u003c/span\u003e\u003c/span\u003e (2019).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eHo, T. K. The random subspace method for constructing decision forests. \u003cem\u003eIEEE transactions on pattern analysis and machine intelligence\u003c/em\u003e, \u003cstrong\u003e20\u003c/strong\u003e, 832\u0026ndash;844 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1109/34.709601\u003c/span\u003e\u003c/span\u003e (1998).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eSothe, C. \u003cem\u003eet al.\u003c/em\u003e Comparative performance of convolutional neural network, weighted and conventional support vector machine and random forest for classifying tree species using hyperspectral and photogrammetric data. \u003cem\u003eGIScience \u0026amp; Remote Sensing\u003c/em\u003e, \u003cstrong\u003e57\u003c/strong\u003e, 369\u0026ndash;394 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1080/15481603.2020.1712102\u003c/span\u003e\u003c/span\u003e (2020).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eSung, S., Kwon, Y. S., Lee, D. K. \u0026amp; Cho, Y. Predicting the potential distribution of an invasive species, Solenopsis invicta Buren (Hymenoptera: Formicidae), under climate change using species distribution models. \u003cem\u003eEntomol. Res\u003c/em\u003e, \u003cstrong\u003e48\u003c/strong\u003e, 505\u0026ndash;513 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1111/1748-5967.12325\u003c/span\u003e\u003c/span\u003e (2018).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eChen, Y., Wu, Z., Zhao, B., Fan, C. \u0026amp; Shi, S. Weed and Corn Seedling Detection in Field Based on Multi Feature Fusion and Support Vector Machine. \u003cem\u003eSensors\u003c/em\u003e, \u003cstrong\u003e21\u003c/strong\u003e, 212 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3390/s21010212\u003c/span\u003e\u003c/span\u003e (2021).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eSabat-Tomala, A., Raczko, E. \u0026amp; Zagajewski, B. Comparison of support vector machine and random forest algorithms for invasive and expansive species classification using airborne hyperspectral data. \u003cem\u003eRemote Sensing\u003c/em\u003e, \u003cstrong\u003e12\u003c/strong\u003e, 516 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3390/rs12030516\u003c/span\u003e\u003c/span\u003e (2020).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003ePhillips, S. J., Anderson, R. P. \u0026amp; Schapire, R. E. Maximum entropy modeling of species geographic distributions. \u003cem\u003eEcol. Model\u003c/em\u003e, \u003cstrong\u003e190\u003c/strong\u003e, 231\u0026ndash;259 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.ecolmodel.2005.03.026\u003c/span\u003e\u003c/span\u003e (2006).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eTang, X., Yuan, Y., Li, X. \u0026amp; Zhang, J. Maximum entropy modeling to predict the impact of climate change on pine wilt disease in China. \u003cem\u003eFrontiers in Plant Science\u003c/em\u003e, \u003cstrong\u003e12\u003c/strong\u003e, 764 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3389/fpls.2021.652500\u003c/span\u003e\u003c/span\u003e (2021).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eChhogyel, N., Kumar, L., Bajgai, Y. \u0026amp; Jayasinghe, L. S. Prediction of Bhutan\u0026apos;s ecological distribution of rice (Oryza sativa L.) under the impact of climate change through maximum entropy modelling. \u003cem\u003eThe Journal of Agricultural Science\u003c/em\u003e, \u003cstrong\u003e158\u003c/strong\u003e, 25\u0026ndash;37 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1017/S0021859620000350\u003c/span\u003e\u003c/span\u003e (2020).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eSmith, E. H. Using extreme gradient boosting (XGBoost) to evaluate the importance of a suite of environmental variables and to predict recruitment of young-of-the-year spotted seatrout in Florida. \u003cem\u003ebioRxiv\u003c/em\u003e, 543181; \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1101/543181\u003c/span\u003e\u003c/span\u003e (2019).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eDo, B. H., Langlotz, C. \u0026amp; Beaulieu, C. F. Bone tumor diagnosis using a na\u0026iuml;ve Bayesian model of demographic and radiographic features. \u003cem\u003eJ. Digit. Imaging\u003c/em\u003e, \u003cstrong\u003e30\u003c/strong\u003e, 640\u0026ndash;647 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s10278-017-0001-7\u003c/span\u003e\u003c/span\u003e (2017).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eChang, Z., Meng, J., Shi, Y. \u0026amp; Mo, F. Lnc RNA recognition by fusing multiple features and its function prediction. \u003cem\u003eCAAI Transactions on Intelligent Systems\u003c/em\u003e, \u003cstrong\u003e13\u003c/strong\u003e, 928\u0026ndash;934 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.11992/tis.201806008\u003c/span\u003e\u003c/span\u003e (2018).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eAhmad, Z. \u003cem\u003eet al.\u003c/em\u003e Melia Azedarach impregnated Co and Ni zero-valent metal nanoparticles for organic pollutants degradation: validation of experiments through statistical analysis. \u003cem\u003eJ. Mater. Sci.: Mater. Electron\u003c/em\u003e, \u003cstrong\u003e31\u003c/strong\u003e, 16938\u0026ndash;16950 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s10854-020-04250-5\u003c/span\u003e\u003c/span\u003e (2020).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eHijmans, R. J., Huaccho, L. \u0026amp; Zhang, D. in \u003cem\u003eI International Conference on Sweetpotato. Food and Health for the Future 583.\u003c/em\u003e 41-49.\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eLuo, M., Wang, H. \u0026amp; Lyu, Z. Evaluating the performance of species distribution models Biomod2 and MaxEnt using the giant panda distribution data. \u003cem\u003eThe journal of applied ecology\u003c/em\u003e, \u003cstrong\u003e28\u003c/strong\u003e, 4001\u0026ndash;4006 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.13287/j.1001-9332.201712.011\u003c/span\u003e\u003c/span\u003e (2017).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eWang, T., Wang, G., Innes, J. L., Seely, B. \u0026amp; Chen, B. ClimateAP: An application for dynamic local downscaling of historical and future climate data in Asia Pacific. \u003cem\u003eFrontiers of Agricultural Science and Engineering\u003c/em\u003e, \u003cstrong\u003e4\u003c/strong\u003e, 448\u0026ndash;458 (2017).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eYang, X. Q., Kushwaha, S., Saran, S., Xu, J. \u0026amp; Roy, P. Maxent modeling for predicting the potential distribution of medicinal plant, Justicia adhatoda L. in Lesser Himalayan foothills. \u003cem\u003eEcological engineering\u003c/em\u003e, \u003cstrong\u003e51\u003c/strong\u003e, 83\u0026ndash;87 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.ecoleng.2012.12.004\u003c/span\u003e\u003c/span\u003e (2013).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eRavisankar, P., Navya, C. N., Pravallika, D. \u0026amp; Sri, D. N. A review on step-by-step analytical method validation. \u003cem\u003eIOSR J Pharm\u003c/em\u003e, \u003cstrong\u003e5\u003c/strong\u003e, 7\u0026ndash;19 (2015). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.researchgate.net/publication/338166852\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003ePepe, M. S., Cai, T. \u0026amp; Longton, G. Combining predictors for classification using the area under the receiver operating characteristic curve., \u003cstrong\u003e62\u003c/strong\u003e, 221\u0026ndash;229 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1111/j.1541-0420.2005.00420.x\u003c/span\u003e\u003c/span\u003e (2006).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eMcHugh, M. L. Interrater reliability: the kappa statistic. \u003cem\u003eBiochemia medica\u003c/em\u003e, \u003cstrong\u003e22\u003c/strong\u003e, 276\u0026ndash;282 (2012).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003ePowers, D. M. What the F-measure doesn\u0026apos;t measure: Features, Flaws, Fallacies and Fixes. arXiv preprint arXiv:1503.06410(2015).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eLu, C. Y., Gu, W., Dai, A. H. \u0026amp; Wei, H. Y. Assessing habitat suitability based on geographic information system (GIS) and fuzzy: a case study of Schisandra sphenanthera Rehd. et Wils. in Qinling Mountains, China. \u003cem\u003eEcol. Model\u003c/em\u003e, \u003cstrong\u003e242\u003c/strong\u003e, 105\u0026ndash;115 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.ecolmodel.2012.06.002\u003c/span\u003e\u003c/span\u003e (2012).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eZhang, L. \u003cem\u003eet al.\u003c/em\u003e The basic principle of random forest and its applications in ecology: A case study of Pinus yunnanensis. \u003cem\u003eActa Ecol. Sin\u003c/em\u003e, \u003cstrong\u003e34\u003c/strong\u003e, 650\u0026ndash;659 (2014).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eLin, H. Y. \u003cem\u003eet al.\u003c/em\u003e Climate-based approach for modeling the distribution of montane forest vegetation in Taiwan. \u003cem\u003eAppl. Veg. Sci\u003c/em\u003e, \u003cstrong\u003e23\u003c/strong\u003e, 239\u0026ndash;253 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1111/avsc.12485\u003c/span\u003e\u003c/span\u003e (2020).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eZhang, L. \u003cem\u003eet al.\u003c/em\u003e Consensus forecasting of species distributions: The effects of niche model performance and niche properties. \u003cem\u003ePLoS ONE\u003c/em\u003e, \u003cstrong\u003e10\u003c/strong\u003e, e0120056 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1371/journal.pone.0120056\u003c/span\u003e\u003c/span\u003e (2015).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eZhang, H. The optimality of naive Bayes. \u003cem\u003eAmerican Association for Artificial Intelligence\u003c/em\u003e, \u003cstrong\u003e1\u003c/strong\u003e, 3 (2004).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eWang, Q., Nguyen, T. T., Huang, J. Z. \u0026amp; Nguyen, T. T. An efficient random forests algorithm for high dimensional data classification. \u003cem\u003eAdvances in Data Analysis and Classification\u003c/em\u003e, \u003cstrong\u003e12\u003c/strong\u003e, 953\u0026ndash;972 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s11634-018-0318-1\u003c/span\u003e\u003c/span\u003e (2018).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eZheng-tao, Y., Bin, D., Bo, H. \u0026amp; Lu, H. Jian-yi, G. Word Sense Disambiguation Based on Bayes Model and Information Gain. the Proceedings of the International Journal of Advanced Science and Technology 3(2009).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eYu, B. \u003cem\u003eet al.\u003c/em\u003e SubMito-XGBoost: predicting protein submitochondrial localization by fusing multiple feature information and eXtreme gradient boosting., \u003cstrong\u003e36\u003c/strong\u003e, 1074\u0026ndash;1081 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1093/bioinformatics/btz734\u003c/span\u003e\u003c/span\u003e (2020).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eHailu, B. T., Siljander, M., Maeda, E. E. \u0026amp; Pellikka, P. Assessing spatial distribution of Coffea arabica L. in Ethiopia\u0026apos;s highlands using species distribution models and geospatial analysis methods. \u003cem\u003eEcological Informatics\u003c/em\u003e, \u003cstrong\u003e42\u003c/strong\u003e, 79\u0026ndash;89 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.ecoinf.2017.10.001\u003c/span\u003e\u003c/span\u003e (2017).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eRamirez-Reyes, C. \u003cem\u003eet al.\u003c/em\u003e Embracing Ensemble Species Distribution Models to Inform At-Risk Species Status Assessments. \u003cem\u003eJournal of Fish and Wildlife Management\u003c/em\u003e, \u003cstrong\u003e12\u003c/strong\u003e, 98\u0026ndash;111 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3996/JFWM-20-072\u003c/span\u003e\u003c/span\u003e (2021).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eWisz, M. S. \u003cem\u003eet al.\u003c/em\u003e Effects of sample size on the performance of species distribution models. \u003cem\u003eDivers. Distrib\u003c/em\u003e, \u003cstrong\u003e14\u003c/strong\u003e, 763\u0026ndash;773 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1111/j.1472-4642.2008.00482.x\u003c/span\u003e\u003c/span\u003e (2008).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eFeng, L., Sun, J., Shi, Y., Wang, G. \u0026amp; Wang, T. Predicting Suitable Habitats of Camptotheca acuminata Considering Both Climatic and Soil Variables. \u003cem\u003eForests\u003c/em\u003e, \u003cstrong\u003e11\u003c/strong\u003e, 891 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3390/f11080891\u003c/span\u003e\u003c/span\u003e (2020).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eWang, T., Campbell, E. M., O\u0026rsquo;Neill, G. A. \u0026amp; Aitken, S. N. Projecting future distributions of ecosystem climate niches: uncertainties and management applications. \u003cem\u003eFor. Ecol. Manag\u003c/em\u003e, \u003cstrong\u003e279\u003c/strong\u003e, 128\u0026ndash;140 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.foreco.2012.05.034\u003c/span\u003e\u003c/span\u003e (2012).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eWang, T., Hamann, A., Spittlehouse, D. L. \u0026amp; Murdock, T. Q. ClimateWNA\u0026mdash;high-resolution spatial climate data for western North America. \u003cem\u003eJournal of Applied Meteorology and Climatology\u003c/em\u003e, \u003cstrong\u003e51\u003c/strong\u003e, 16\u0026ndash;29 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1175/JAMC-D-11-043.1\u003c/span\u003e\u003c/span\u003e (2012).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eFeng, L. \u003cem\u003eet al.\u003c/em\u003e Predicting suitable habitats of Ginkgo biloba L. fruit forests in China. \u003cem\u003eClimate Risk Management\u003c/em\u003e, 100364 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.crm.2021.100364\u003c/span\u003e\u003c/span\u003e (2021).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eWang, T., Hamann, A., Spittlehouse, D. \u0026amp; Carroll, C. Locally downscaled and spatially customizable climate data for historical and future periods for North America. \u003cem\u003ePLoS ONE\u003c/em\u003e, \u003cstrong\u003e11\u003c/strong\u003e, e0156720 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1371/journal.pone.0156720\u003c/span\u003e\u003c/span\u003e (2016).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eGuo, Y. \u003cem\u003eet al.\u003c/em\u003e Spatial prediction and delineation of Ginkgo biloba production areas under current and future climatic conditions. \u003cem\u003eIndustrial Crops and Products\u003c/em\u003e, \u003cstrong\u003e166\u003c/strong\u003e, 113444 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.indcrop.2021.113444\u003c/span\u003e\u003c/span\u003e (2021).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eJiao, C., Lan, G., Sun, Y., Wang, G. \u0026amp; Sun, Y. Dopamine Alleviates Chilling Stress in Watermelon Seedlings via Modulation of Proline Content, Antioxidant Enzyme Activity, and Polyamine Metabolism.\u003cem\u003eJ. Plant Growth Regul.\u003c/em\u003e\u003cstrong\u003e40\u003c/strong\u003e (2021).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eXu, L. \u003cem\u003eet al.\u003c/em\u003e Effect of salt stress on growth and physiology in Melia azedarach seedlings of six provenances. \u003cem\u003eInternational Journal of Agriculture and Biology\u003c/em\u003e, \u003cstrong\u003e20\u003c/strong\u003e, 471\u0026ndash;480 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.17957/IJAB/15.0618\u003c/span\u003e\u003c/span\u003e (2018).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eThakur, S., Thakur, I. \u0026amp; Sankanur, M. Assessment of Genetic Diversity in Drek (Melia azedarach) Using Molecular Markers. \u003cem\u003eJournal of Tree Sciences\u003c/em\u003e, \u003cstrong\u003e36\u003c/strong\u003e, 78\u0026ndash;85 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.5958/2455-7129.2017.00011.5\u003c/span\u003e\u003c/span\u003e (2017).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eLenoir, J., G\u0026eacute;gout, J. C., Marquet, P., De Ruffray, P. \u0026amp; Brisse, H. A significant upward shift in plant species optimum elevation during the 20th century. \u003cem\u003eScience\u003c/em\u003e; \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1126/science.1156831\u003c/span\u003e\u003c/span\u003e (2008).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eOu-Yang, C. F. \u003cem\u003eet al.\u003c/em\u003e Impact of equatorial and continental airflow on primary greenhouse gases in the northern South China Sea. \u003cem\u003eEnvironmental Research Letters\u003c/em\u003e, \u003cstrong\u003e10\u003c/strong\u003e, 065005 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1088/1748-9326/10/6/065005\u003c/span\u003e\u003c/span\u003e (2015).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eLiu, B., Zhu, C., Su, J., Ma, S. \u0026amp; Xu, K. Record-breaking northward shift of the western North Pacific subtropical high in July 2018. \u003cem\u003eJournal of the Meteorological Society of Japan. Ser. II\u003c/em\u003e, \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.2151/jmsj.2019-047\u003c/span\u003e\u003c/span\u003e (2019).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eHuang, J. \u003cem\u003eet al.\u003c/em\u003e Dryland climate change: Recent progress and challenges. \u003cem\u003eReviews of Geophysics\u003c/em\u003e, \u003cstrong\u003e55\u003c/strong\u003e, 719\u0026ndash;778 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1002/2016RG000550\u003c/span\u003e\u003c/span\u003e (2017).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eThuiller, W., Lavorel, S., Ara\u0026uacute;jo, M. B., Sykes, M. T. \u0026amp; Prentice, I. C. Climate change threats to plant diversity in Europe. \u003cem\u003eProceedings of the National Academy of Sciences\u003c/em\u003e \u003cstrong\u003e102\u003c/strong\u003e, 8245-8250; \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1073/pnas.0409902102\u003c/span\u003e\u003c/span\u003e (2005).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eWaldvogel, A. M. \u003cem\u003eet al.\u003c/em\u003e Evolutionary genomics can improve prediction of species\u0026rsquo; responses to climate change. \u003cem\u003eEvolution Letters\u003c/em\u003e, \u003cstrong\u003e4\u003c/strong\u003e, 4\u0026ndash;18 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1002/evl3.154\u003c/span\u003e\u003c/span\u003e (2020).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eVil\u0026agrave;-Cabrera, A., Coll, L., Mart\u0026iacute;nez-Vilalta, J. \u0026amp; Retana, J. Forest management for adaptation to climate change in the Mediterranean basin: A synthesis of evidence. \u003cem\u003eFor. Ecol. Manag\u003c/em\u003e, \u003cstrong\u003e407\u003c/strong\u003e, 16\u0026ndash;22 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.foreco.2017.10.021\u003c/span\u003e\u003c/span\u003e (2018).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eHe, X., Li, J., Wang, F., Zhang, J. \u0026amp; Chen, X. Variation and selection of Melia azedarach provenances and families. \u003cem\u003eJournal of Northeast Forestry University\u003c/em\u003e, \u003cstrong\u003e47\u003c/strong\u003e, 1\u0026ndash;7 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.13332/j.1000-1522.20170321\u003c/span\u003e\u003c/span\u003e (2019).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eSmith, A. B., Alsdurf, J., Knapp, M., Baer, S. G. \u0026amp; Johnson, L. C. Phenotypic distribution models corroborate species distribution models: A shift in the role and prevalence of a dominant prairie grass in response to climate change. \u003cem\u003eGlob. Change Biol\u003c/em\u003e, \u003cstrong\u003e23\u003c/strong\u003e, 4365\u0026ndash;4375 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1111/gcb.13666\u003c/span\u003e\u003c/span\u003e (2017).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eBellon, M. R., Dulloo, E., Sardos, J., Thormann, I. \u0026amp; Burdon, J. J. In situ conservation\u0026mdash;harnessing natural and human-derived evolutionary forces to ensure future crop adaptation. \u003cem\u003eEvolutionary applications\u003c/em\u003e, \u003cstrong\u003e10\u003c/strong\u003e, 965\u0026ndash;977 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1111/eva.12521\u003c/span\u003e\u003c/span\u003e (2017).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eBidak, L. M., Heneidy, S. Z., Halmy, M. W. A. \u0026amp; El-Kenany, E. T. Sustainability potential for Ginkgo biloba L. plantations under climate change uncertainty: An ex-situ conservation perspective. \u003cem\u003eActa Ecol. Sin\u003c/em\u003e, \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.chnaes.2021.09.012\u003c/span\u003e\u003c/span\u003e (2021).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eQin, F., Liu, S. \u0026amp; Yu, S. Effects of allelopathy and competition for water and nutrients on survival and growth of tree species in Eucalyptus urophylla plantations. \u003cem\u003eFor. Ecol. Manag\u003c/em\u003e, \u003cstrong\u003e424\u003c/strong\u003e, 387\u0026ndash;395 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.foreco.2018.05.017\u003c/span\u003e\u003c/span\u003e (2018).\u003c/span\u003e\u003c/li\u003e\n \u003cli\u003e\u003cspan\u003eZabel, F. \u003cem\u003eet al.\u003c/em\u003e Global impacts of future cropland expansion and intensification on agricultural markets and biodiversity. \u003cem\u003eNat. Commun\u003c/em\u003e, \u003cstrong\u003e10\u003c/strong\u003e, 1\u0026ndash;10 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1038/s41467-019-10775-z\u003c/span\u003e\u003c/span\u003e (2019).\u003c/span\u003e\u003c/li\u003e\n\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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Melia azedarach L., Climate change, Habitat suitability, Data mining models ","lastPublishedDoi":"10.21203/rs.3.rs-1004808/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-1004808/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003e\u003cem\u003eBackground\u003c/em\u003e\u003c/strong\u003e\u003cem\u003e: Melia azedarach\u003c/em\u003e L. is a globally distributed tree species of economic importance; however, it is unclear how the species distribution will respond to future climate changes.\u003c/p\u003e\u003cp\u003e\u003cstrong\u003e\u003cem\u003eMethods:\u003c/em\u003e\u003c/strong\u003e We aimed to select the most accurate one among seven data mining models to predict the species suitable contemporary and future habitats. These models include: maximum entropy (MaxEnt), support vector machine (SVM), generalized linear model (GLM), random forest (RF), naive bayesian model (NBM), extreme gradient boosting (XGBoost), and gradient boosting machine (GBM). A total of 906 \u003cem\u003eM. azedarach\u003c/em\u003e locations were identified, and sixteen climate predictors were used for model building. The models’ validity was assessed using three measures (Area Under the Curves (AUC), kappa, and accuracy). \u003c/p\u003e\u003cp\u003e\u003cstrong\u003e\u003cem\u003eResults: \u003c/em\u003e\u003c/strong\u003eWe found that the RF provided the most outstanding performance in prediction power and generalization capacity. The top climate factors affecting the species distribution were mean coldest month temperature (MCMT), followed by the number of frost-free days (NFFD), degree-days above 18°C (DD\u0026gt;18), temperature difference between MWMT and MCMT, or continentality (TD), mean annual precipitation (MAP), and degree-days below 18°C (DD\u0026lt;18). We projected that future suitable habitat of this species would increase under both the RCP4.5 and RCP8.5 scenarios for the 2020s, 2050s, and 2080s.\u003c/p\u003e\u003cp\u003e\u003cstrong\u003e\u003cem\u003eConclusion: \u003c/em\u003e\u003c/strong\u003eOur findings are expected to assist in better understanding the impact of climate change on the species and provide scientific basis for its planting and conservation.\u003c/p\u003e","manuscriptTitle":"Predicting Suitable Habitats of Melia Azedarach L. Using Data Mining","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2021-10-27 14:53:09","doi":"10.21203/rs.3.rs-1004808/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvited","content":"","date":"2021-10-26T09:54:05+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2021-10-25T19:43:30+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2021-10-21T16:22:26+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"c7bdc7a8-5a82-40e5-a9c6-bc99f1dfb8d1","owner":[],"postedDate":"October 27th, 2021","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":8129905,"name":"Ecological Modeling"},{"id":8129906,"name":"Forestry"}],"tags":[],"updatedAt":"2022-07-12T06:59:13+00:00","versionOfRecord":[],"versionCreatedAt":"2021-10-27 14:53:09","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-1004808","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-1004808","identity":"rs-1004808","version":["v1"]},"buildId":"WrCJVZZCHTDjtuVLN7oU0","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}