[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124890-en":3,"doc-seo-124890-105":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":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},124890,137441390410,"Hazel","https://ap-avatar.wpscdn.com/avatar/2000252f4ab5702993?_k=1776741390130283984",8,"Research & Report","An ensemble framework for explainable learning models - geospatial machine learning","Analyzing spatially varying effects is essential in geographic analysis, yet capturing and interpreting this variability remains difficult because geospatial data grows complex and nonlinear. Recent work combining Geographically Weighted (GW) models with AI improves flexibility, but often prioritizes prediction over interpretability. A GeoShapley approach explains contributions using Shapley values, while not fully addressing nonlinear interactions among geographical features and explanatory variables. An ensemble framework is proposed to integrate local spatial weighting with explainable AI and machine learning, improving interpretability and predictive accuracy through experiments and comparisons. It supports reproducible analysis across weighting schemes and model choices and applies to both geographic regression and classification.","International Journal of Applied Earth Observation and Geoinformation 132 (2024) 104036  \nContents lists available at ScienceDirect  \nInternational Journal of Applied Earth Observation and Geoinformation  \njournal [homepage:](homepage: www.elsevier.com/locate/jag)[ www.elsevier.com/locate/jag](homepage: www.elsevier.com/locate/jag)  \n| An ensemble framework for explainable learning models |  |  | geospatial machine |  |\n| --- | --- | --- | --- | --- |\n| Lingbo Liua,b\u003Cbr>a Center for Geographic Analysis, Harvard University, Cambridge, MA 02138, USA b School of Urban Design, Wuhan University, Wuhan, Hubei 430072, China |  |  |  |  |\n| A R T I C L E I N F O |  | A B S T R A C T |  |  |\n| Keywords:\u003Cbr>Explainable Artificial Intelligence (XAI) GeoAI\u003Cbr>Machine Learning\u003Cbr>Spatially Varying Coefficient Geographically Weighted Models XGeoML |  | Analyzing spatially varying effects is pivotal in geographic analysis. However, accurately capturing and interpreting this variability is challenging due to the increasing complexity and non-linearity of geospatial data. Recent advancements in integrating Geographically Weighted (GW) models with artificial intelligence (AI) methodologies offer novel approaches. However, these methods often focus on single algorithms and emphasize prediction over interpretability. The recent GeoShapley method integrates machine learning (ML) with Shapley values to explain the contribution of geographical features, advancing the combination of geospatial ML and explainable AI (XAI). Yet, it lacks exploration of the nonlinear interactions between geographical features and explanatory variables. Herein, an ensemble framework is proposed to merge local spatial weighting scheme with XAI and ML technologies to bridge this gap. Through tests on synthetic datasets and comparisons with GWR, MGWR, and GeoShapley, this framework is verified to enhance interpretability and predictive accuracy by elucidating spatial variability. Reproducibility is explored through the comparison of spatial weighting schemesand various ML models, emphasizing the necessity of model reproducibility to address model and parameter uncertainty. This framework works in both geographic regression and classification, offering a novel approach to understanding complex spatial phenomena. |  |  |\n\n1. Introduction  \nThe relationships between phenomenon can vary significantly across different spatial or geographical contexts, manifesting in events such asthe disparate impacts of pandemics (Hammer, 2021); the dynamics of poverty distribution (Chaves, 2015), housing prices fluctuations (Liu, 2022), etc. Optimizing spatial analysis methods is crucial for exploring these diverse issues, as it enhances predictions accuracy, model interpretability, and the effectiveness of spatial decisions or interventions (Brunsdon et al., 1998). Nonetheless, the inherent complexity of spatial data and the potential for nonlinear relationships pose challenges to enhancing interpretability through traditional spatial analysis techniques (De Sabbata, et al., 2023).  \nFor models analyzing spatially varying effects, such as spatial filtering models (Oshan and Fotheringham, 2018; Griffth, 2003; Gorrand Olligschlaeger, 1994) and spatial Bayes models (Oshan, 2022); Geographically Weighted Regression (GWR) and Multiscale Geographically Weighted Regression (MGWR) stand out for their application of local spatial weighting schemes, which capture spatial features more accurately (Murakami, 2020; Fotheringham et al., 2017). These linear  \nregression-based approaches, however, encounter significant hurdles in decoding complex spatial phenomena (Fig. 1). Various Geographically Weighted (GW) models have been developed to tackle issues such as multicollinearity (Wheeler, 2009; Comber and Harris, 2018) and to extend the utility of GW models to classification tasks (Atkinson, 2003; Paez, 2006; Brunsdon et al., 2007; Jiang, 2012). The evolution of artificial intelligence (AI) methodologies, in","cbCaio0EucuXUauk","https://ap.wps.com/l/cbCaio0EucuXUauk","pdf",7608410,1,12,"English","en",105,"# Introduction\n## Spatially varying effects and interpretability challenges\n## Geographically Weighted models and AI integration\n## Motivation: nonlinear correlations and spatial mechanisms\n# Background and related methods","[{\"question\":\"Why is interpreting spatially varying effects difficult in geographic analysis?\",\"answer\":\"Spatial data becomes increasingly complex and nonlinear, making it hard to accurately capture and explain variability across locations.\"},{\"question\":\"What gap does the proposed ensemble framework address compared with GeoShapley?\",\"answer\":\"It aims to explore nonlinear interactions between geographical features and explanatory variables, which GeoShapley does not fully cover.\"},{\"question\":\"How does the framework improve both interpretability and predictive performance?\",\"answer\":\"It merges a local spatial weighting scheme with XAI and machine learning, and its effectiveness is validated through tests on synthetic datasets and comparisons with GWR, MGWR, and GeoShapley.\"}]","An ensemble framework for explainable learning models - geospatial machine learning | PDF",1785895240,30,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"an-ensemble-framework-for-explainable-learning-models-geospatial-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"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":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/an-ensemble-framework-for-explainable-learning-models-geospatial-machine-learning/124890/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is interpreting spatially varying effects difficult in geographic analysis?","Question",{"text":75,"@type":76},"Spatial data becomes increasingly complex and nonlinear, making it hard to accurately capture and explain variability across locations.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What gap does the proposed ensemble framework address compared with GeoShapley?",{"text":80,"@type":76},"It aims to explore nonlinear interactions between geographical features and explanatory variables, which GeoShapley does not fully cover.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the framework improve both interpretability and predictive performance?",{"text":84,"@type":76},"It merges a local spatial weighting scheme with XAI and machine learning, and its effectiveness is validated through tests on synthetic datasets and comparisons with GWR, MGWR, and GeoShapley.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,122,127,130,134],{"id":20,"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":53,"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":29,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]