[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128081-en":3,"doc-seo-128081-105":31,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},128081,5909887254083,"Miles","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Machine Learning Models for Predicting Spatiotemporal Dynamics of Groundwater Recharge","Groundwater management remains limited in many countries despite groundwater’s critical role and scarcity, making continuous monitoring and accurate spatiotemporal projections essential for sustainable development. This study builds machine learning prediction models (RF, XGBoost, AdaBoost, CatBoost, DT, Keras) and time-series forecasting models (CNN, LSTM and variants) using open remote sensing datasets. The merged datasets are organized for training, testing, and validation across 2002–2009, 2010–2015, and 2015–2020, and model outputs are compared for Morocco. RF and XGBoost deliver the best temporal predictions, while LSTM performs best for forecasting.","Journal of Renewable Energy and Sustainable Development (RESD) Volume 10, Issue 2, December 2024-ISSN 2356-8569  \n[http://dx.doi.org/10.21622/RESD.2024.10.2.933](http://dx.doi.org/10.21622/RESD.2024.10.2.933)  \nReceived on, 20 July 2024 Accepted on, 03 October 2024 Published on, 03 November 2024  \nMachine Learning Models for Predicting Spatiotemporal Dynamics of  \nGroundwater Recharge  \nAzeddine ElHassouny  \nENSIAS, Mohammed V University in Rabat, Morocco  \n[azeddine.elhassouny@ensias.um5.ac.ma](azeddine.elhassouny@ensias.um5.ac.ma)  \nABSTRACT  \nIn most of the world’s nations, groundwater management is infrequent despite its importance and scarcity. Continuous monitoring and precise projections of spatiotemporal groundwater recharge change can aid in sustainable development and effective groundwater resource management. Open public remote sensing datasets were used to develop machine learning prediction models (RF, XGBoost, AdaBoost, CatBoost, DT, Keras models) and time series forecasting models (CNN, LSTM, and its variants) for predicting and forecasting groundwater sheet recharge, respectively. The publicly available datasets are merged, processed, and organized into three parts for training, testing, and validation: 2002–2009, 2010–2015, and 2015–2020 . A comparison ofspatiotemporal prediction models’ estimates of groundwater recharge in Morocco revealed that RF and XGBoost were the more accurate methods for temporal (spatial) recharging, with MAE values of 4.7795 mm/month (1 .0227 mm/month) and 4.9936 mm/month (1 .3031 mm/ month), respectively. Regarding time series forecasting, the LSTM model performed better, with an MAE of 20.05 mm/month. The proposed models’ performances on validation datasets demonstrate the utility and scalability of the proposed combined remote sensing and artificial intelligence-based framework, opening up a new pathway for largescale groundwater management. The established workflow enables the study to be extended to any other site.  \nIndex-words: Groundwater recharge, Artificial intelligence, Remote sensing, Prediction, Forecasting, Time series, Tree vitality, Soil moisture.  \nI. INTRODUCTION  \nGROUNDWATER is one of the most important sectoral exposures to climate change [1] and a vital component of maintaining the world’s food supply. It is regarded as the primary source of fresh water and essential to preserving the planet ecological balance. Furthermore, it is a necessary component of the earth crust that prevents the earth from burning. Despite its significance and limited availability, it is hardly ever fully utilized and groundwater management is rarely done in most countries of the world [2].  \nThe public release of official remote sensing data portals in recent years has broadened the range of applications for remote sensing analysis and boosted the size of the remote sensing community. Examples of these portals include those of the NASS [3], CHC-UCSB, OpenlandMap [4], and CSIRO. etc. With the increased availability of gridded hydrometeorological data and digitalized hydrography data with high spectral resolution for large scale, a variety of hydrologic applications may  \nbe precisely established for a country size.  \nArtificial intelligence (AI) has become more frequently incorporated into remote sensing-based groundwater management [5], offering innovative perspectives and new tools for predicting and forecasting groundwater behavior, including the status of groundwater supplies, groundwater levels and depth, recharge and withdrawal rates, and other hydrological variables [2],[6]–[10].  \nData from remote sensing has been extensively analyzed using AI approaches for groundwater management. Machine learning (ML) including deep learning (DL) are algorithms that have the capacity to learn from vast amounts of data and produce predictions, forecasting, classifications, and so on. Support vector machines (SVM) [11], random forests (RF) [11], and artificial neural networks (ANN), among others,","cbCaioMxNbpxpAPv","https://ap.wps.com/l/cbCaioMxNbpxpAPv","pdf",5881262,4,1,26,"English","en",105,"# Abstract\n# Introduction\n# Related Work and Background\n# Methods and Data Strategy","[{\"question\":\"Why is predicting spatiotemporal groundwater recharge important?\",\"answer\":\"Accurate recharge projections support sustainable development and effective groundwater resource management, especially where groundwater is scarce and monitoring is limited.\"},{\"question\":\"Which models are used for prediction and forecasting in the study?\",\"answer\":\"Prediction uses machine learning models such as RF, XGBoost, AdaBoost, CatBoost, DT, and Keras, while forecasting uses time-series models including CNN and LSTM variants.\"},{\"question\":\"How are the remote sensing datasets prepared for training and evaluation?\",\"answer\":\"Open datasets are merged, processed, and split into training, testing, and validation sets covering 2002–2009, 2010–2015, and 2015–2020.\"}]","Machine Learning Models for Predicting Spatiotemporal Dynamics of Groundwater Recharge | PDF",1785944704,66,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"machine-learning-models-for-predicting-spatiotemporal-dynamics-of-groundwater-recharge","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":20},"https://docshare.wps.com/document/machine-learning-models-for-predicting-spatiotemporal-dynamics-of-groundwater-recharge/128081/",{"url":53,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-25","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why is predicting spatiotemporal groundwater recharge important?","Question",{"text":76,"@type":77},"Accurate recharge projections support sustainable development and effective groundwater resource management, especially where groundwater is scarce and monitoring is limited.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Which models are used for prediction and forecasting in the study?",{"text":81,"@type":77},"Prediction uses machine learning models such as RF, XGBoost, AdaBoost, CatBoost, DT, and Keras, while forecasting uses time-series models including CNN and LSTM variants.",{"name":83,"@type":74,"acceptedAnswer":84},"How are the remote sensing datasets prepared for training and evaluation?",{"text":85,"@type":77},"Open datasets are merged, processed, and split into training, testing, and validation sets covering 2002–2009, 2010–2015, and 2015–2020.","https://schema.org",{"og:url":53,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]