[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-42024-en":3,"doc-seo-42024-105":30,"detail-sidebar-cat-0-en-105":91},{"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":13,"seo_description":14,"update_tm":28,"read_time":29},42024,1374391974468,"Eden","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","The Use of Hybrid Machine Learning Models for Improving the GALDIT Model for Coastal Aquifer Vulnerability Mapping","Study aims to enhance the GALDIT groundwater vulnerability model (groundwater occurrence, aquifer hydraulic conductivity, groundwater level above sea level, distance from shoreline, seawater intrusion impact, and aquifer thickness) through machine learning. Eight state-of-the-art methods, including naïve Bayes tree and logistic model tree, were assessed alone and combined with dagging, bagging, and random subspace strategies, then benchmarked against the original GALDIT model. Coastal Gharesoo-Gorgan Rood aquifer in North Iran used TDS samples from 53 wells (2017 for modeling, 2018 for validation). Highest predictive agreement was achieved by BA-LMT (r=0.931).","Environmental Earth Sciences (2022) 81:402  \n[https://doi.org/10.1007/s12665-022-10534-2](https://doi.org/10.1007/s12665-022-10534-2)  \nThe use of hybrid machine learning models for improving the GALDIT model for coastal aquifer vulnerability mapping  \nMojgan Bordbar1 · Khabat Khosravi2,3 · Dorina Murgulet4 · Frank T.‑C. Tsai5 · Ali Golkarian2  \nReceived: 13 November 2021 / Accepted: 16 July 2022 / Published online: 1 August 2022  \n© The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022  \nAbstract  \nThe objective of this study was to improve the predictability of the GALDIT (G: groundwater occurrence, A: aquifer hydraulic conductivity, L: level of groundwater above sea level, D: distance from the shoreline, I: impact of the seawater intrusion, and T: thickness of the aquifer) groundwater vulnerability model using machine leaning methods. This study evaluated eight state-of-the-art machine learning methods, including the naïve Bayes tree (NBT) and logistic model tree (LMT) methods, and their combinations with the dagging (DA), bagging (BA), and random subspace (RS) methods. The results of the machine leaning methods were compared against the benchmark GALDIT model. The coastal Gharesoo-Gorgan Rood aquifer, North Iran, was used as a case study for the proposed methodology. Two sets of total dissolved solids (TDS) samples from 53 wells were collected in 2017 and 2018 and used for the GALDIT modeling and validation purposes, respectively. Correlation coefficient (r) values were calculated for model validation and prediction accuracy by comparison with the TDS data. All eight machine learning models performed well in assessing the coastal aquifer vulnerability with respect to the GALDIT model. The best result was obtained by the BA-LMT model (r = 0.931), followed by the DA-LMT model (r = 0.911), the BA-NBT model (r = 0.904), the DA-NBT model (r = 0. 896), the RS-NBT model (r = 0. 882), the RS-LMT (r = 0. 873), the LMT (r = 0. 863), the NBT (r = 0. 850), and GALDIT model (r = 0.480) .  \nKeywords Groundwater · Vulnerability assessment · GALDIT index · Machine learning · Hybrid models  \nIntroduction  \nFreshwater is a highly valuable resource worldwide, especially in arid and semiarid regions like Iran (Nguyen et al. 2020) . Since 1990, 2.6 billion people in the world have  \n* Mojgan Bordbar [mojganbordbar1991@gmail.com](mojganbordbar1991@gmail.com); [mozhganbordbar70@gmail.com](mozhganbordbar70@gmail.com)  \n1 Department of Remote Sensing and GIS, Faculty of Natural Resources and Environment, Science and Research Branch, Islamic Azad University, Tehran, Iran  \n2 Department of Watershed Management Engineering, Ferdowsi University of Mashhad, Mashhad, Iran  \n3 Department of Earth and Environment, Florida International University, Miami, FL, USA  \n4 Department of Physical and Environmental Sciences, Center for Water Supply Studies, Texas A&M University-Corpus Christi, Corpus Christi, USA  \n5 Department of Civil and Environmental Engineering, Louisiana State University, Baton Rouge, LA, USA  \naccess to adequate drinking water, while 663 million still lack access to clean water (WHO/UNICEF 2015) . While worldwide groundwater provides one third of the drinking water (Arabgol et al. 2016), in arid and semiarid regions it provides almost 90% of the water supply (Magesh et al. 2012) . With growing population and urbanization and increasing industrial demands, it is expected that groundwater consumption will increase significantly (Pham et al. 2019), as will the threats to groundwater quality because of pollution. In coastal areas, overexploitation of groundwater has been found to cause seawater intrusion (Murgulet and Tick 2008; Sophiya and Syed 2013; Klassen and Allen 2017) . Seawater intrusion into freshwater aquifers deteriorates groundwater quality and quantity. This process can occur both due to natural (i.e. , sea level rise and climate change) and anthropogenic factors (i.e., groundwater ove","cbCaieF7JRmJKnvg","https://ap.wps.com/l/cbCaieF7JRmJKnvg","pdf",4563804,3,1,15,"English","en",105,"# Abstract\n# Introduction\n## Groundwater vulnerability and seawater intrusion\n## Existing assessment approaches (index methods and GALDIT)","[{\"question\":\"What does the GALDIT model represent in groundwater vulnerability mapping?\",\"answer\":\"GALDIT summarizes vulnerability using six components: groundwater occurrence, aquifer hydraulic conductivity, level above sea level, distance from the shoreline, impact of seawater intrusion, and aquifer thickness.\"},{\"question\":\"Which machine learning approaches were tested to improve the GALDIT model?\",\"answer\":\"Eight machine learning methods were evaluated, including naïve Bayes tree and logistic model tree, and combinations with dagging, bagging, and random subspace techniques.\"},{\"question\":\"How was the proposed methodology validated for the coastal aquifer case study?\",\"answer\":\"Total dissolved solids (TDS) samples from 53 wells were collected in 2017 and 2018, used respectively for GALDIT modeling and validation, with model performance assessed using the correlation coefficient (r) against TDS data.\"}]",1783344675,38,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"the-use-of-hybrid-machine-learning-models-for-improving-the-galdit-model-for-coastal-aquifer-vulnerability-mapping","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/the-use-of-hybrid-machine-learning-models-for-improving-the-galdit-model-for-coastal-aquifer-vulnerability-mapping/42024/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-13","2026-07-06",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What does the GALDIT model represent in groundwater vulnerability mapping?","Question",{"text":75,"@type":76},"GALDIT summarizes vulnerability using six components: groundwater occurrence, aquifer hydraulic conductivity, level above sea level, distance from the shoreline, impact of seawater intrusion, and aquifer thickness.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning approaches were tested to improve the GALDIT model?",{"text":80,"@type":76},"Eight machine learning methods were evaluated, including naïve Bayes tree and logistic model tree, and combinations with dagging, bagging, and random subspace techniques.",{"name":82,"@type":73,"acceptedAnswer":83},"How was the proposed methodology validated for the coastal aquifer case study?",{"text":84,"@type":76},"Total dissolved solids (TDS) samples from 53 wells were collected in 2017 and 2018, used respectively for GALDIT modeling and validation, with model performance assessed using the correlation coefficient (r) against TDS data.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]