[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127926-en":3,"doc-seo-127926-105":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},127926,687207024478,"Liam","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Introducing Spatial Heterogeneity via Regionalization Methods in Machine Learning Models for Geographical Prediction - Research Article","Study of spatially aware prediction addresses spatial heterogeneity, where attribute means shift across spatial units and challenge conventional models that expect uniformity. The work introduces regionalization in the preprocessing stage and proposes Regionalization Random Forest (RegRF), combining Random Forest with regionalization to form homogeneous regions that reflect local variation. Three questions compare regionalization choices and evaluate RegRF against spatial statistical baselines and spatially conscious machine learning, including GW-RF. Experiments across multiple dataset sizes show improved accuracy versus non-spatial RF with minimal extra computation, strong competitiveness with geographically weighted regression, and computational advantages for larger datasets.","The publication of the European Journal of Geography (EJG) is based on the European Association of Geographers’ goal to make European Geography a worldwide reference and standard. Thus, the scope of the EJG is to publish original and innovative papers that will substantially improve, in a theoretical, conceptual, or empirical way the quality of research, learning, teaching, and applying geography, as well as in promoting the significance of geography as a discipline. Submissions are encouraged to have a European dimension. The European Journal of Geography is a peer-reviewed open access journal and is published quarterly.  \nReceived: 29/07/2024  \nRevised: 10/10/2024  \nAccepted: 16/10/2024  \nPublished: 17/10/2024  \nAcademic Editor:  \nDr. Alexandros Bartzokas-Tsiompras  \nDOI: 10.48088/ejg. l. boe.15.4.244.255  \nISSN: 1792-1341  \nCopyright: © 2024 by the authors. Licensee European Association of Geographers (EUROGEO). This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license.  \nResearch Article  \nIntroducing Spatial Heterogeneity via Regionalization Methods in Machine Learning Models for Geographical Prediction: A Spatially Conscious Paradigm  \nLukas Boegl 1 &  Ourania Kounadi 1✉  \n1 Department of Geography and Regional Research, University of Vienna, Universitätsstraße 7, 1010 Vienna, Austria ✉ Correspondence: [ourania.kounadi@univie.ac.at](ourania.kounadi@univie.ac.at)  \nAbstract: This study addresses the challenge of incorporating spatial heterogeneity in predictive modeling by introducing regionalization methods in the preprocessing step of the modeling workflow. Spatial heterogeneity, where the mean of attribute values varies across spatial units, poses difficulties for traditional models. To tackle this, we propose a novel approach called Regionalization Random Forest (RegRF), which combines Random Forest with regionalization techniques to enhance predictive performance. Regionalization combines multiple spatial objects into homogeneous regions, which are incorporated into predictive models, allowing models to capture local variations. This research investigates three key questions: (1) How does the predictive performance of RegRF vary when constructed using different regionalization techniques? (2) How does RegRF compare to benchmark methods, including both spatial statistical approaches and spatially conscious machine learning models like Geographically Weighted Random Forest (GW-RF)? Five regionalization methods—WARD, AZP, Kmeans, SKATER, and Max-p—are tested on datasets of varying sizes. Results show that RegRF significantly improves performance over \"non-spatial\" Random Forest models with minimal additional computation time. While RegRF performs competitively with Geographically Weighted Regression, it requires much less computational effort. GW-RF was not outperformed on smaller datasets but failed to complete for larger datasets. These findings suggest that RegRF can enhance machine learning models by accounting for spatial phenomena, with potential for further optimization.  \nKeywords: spatial heterogeneity; regionalization; spatial clustering; geographical modelling; machine learning  \nHighlights:  \n● RegRF significantly increases the performance of the predictive models in comparison to \"non-spatial\" Random Forest models, while only taking a few seconds longer to compute.  \n● It competes the well-established Geographically Weighted Regression, while only requiring a fraction of the computational effort.  \n● It can be used for larger datasets while the Geographically Weighted Random Forest may not be able to finish computation.  \n1. Introduction  \nThis paper introduces and evaluates a novel method for incorporating spatial heterogeneity in geographical predictive modeling. Spatial heterogeneity describes spatial phenomena where attribute values vary across different spatial locations. This variation poses challenges for traditional models, ","cbCaiv0UjujdvTmG","https://ap.wps.com/l/cbCaiv0UjujdvTmG","pdf",1833386,2,1,12,"English","en",105,"# Abstract\n# Highlights\n# 1. Introduction\n## Spatial heterogeneity and prediction challenges\n## Spatial dependence and foundational geography\n## Spatial autocorrelation and geographically weighted approaches\n## Spatially conscious machine learning and GW-RF","[{\"question\":\"What problem does the study address in predictive modeling?\",\"answer\":\"It targets spatial heterogeneity, where attribute values vary across spatial units, making it difficult for traditional models that assume uniformity over the study area.\"},{\"question\":\"How does the proposed RegRF method incorporate spatial information?\",\"answer\":\"RegRF introduces regionalization during preprocessing, grouping spatial objects into homogeneous regions and feeding them into Random Forest so the model can capture local variations.\"},{\"question\":\"How does RegRF perform compared with non-spatial Random Forest and spatial benchmarks?\",\"answer\":\"Results show RegRF significantly improves performance over non-spatial Random Forest with only a few seconds of additional computation, competes with Geographically Weighted Regression, and is computationally cheaper than Geographically Weighted Random Forest on larger datasets.\"}]","Introducing Spatial Heterogeneity via Regionalization Methods in Machine Learning Models for Geographical Prediction - Research Article | PDF",1785943022,30,{"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},"introducing-spatial-heterogeneity-via-regionalization-methods-in-machine-learning-models-for-geographical-prediction-research-article","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,48,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":20},"https://docshare.wps.com/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/introducing-spatial-heterogeneity-via-regionalization-methods-in-machine-learning-models-for-geographical-prediction-research-article/127926/",4,{"url":52,"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","2026-08-28","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},"What problem does the study address in predictive modeling?","Question",{"text":76,"@type":77},"It targets spatial heterogeneity, where attribute values vary across spatial units, making it difficult for traditional models that assume uniformity over the study area.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the proposed RegRF method incorporate spatial information?",{"text":81,"@type":77},"RegRF introduces regionalization during preprocessing, grouping spatial objects into homogeneous regions and feeding them into Random Forest so the model can capture local variations.",{"name":83,"@type":74,"acceptedAnswer":84},"How does RegRF perform compared with non-spatial Random Forest and spatial benchmarks?",{"text":85,"@type":77},"Results show RegRF significantly improves performance over non-spatial Random Forest with only a few seconds of additional computation, competes with Geographically Weighted Regression, and is computationally cheaper than Geographically Weighted Random Forest on larger datasets.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"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":30,"slug":122},"research-report",{"id":124,"doc_module":4,"doc_module_name":47,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":47,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":47,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":47,"category_name":137,"show_sort_weight":107,"slug":138},19,"General","general"]