[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126478-en":3,"doc-seo-126478-105":30,"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":11,"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},126478,962084925290,"Ophelia","https://ap-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","On the use of adversarial validation for quantifying dissimilarity in geospatial machine learning prediction","Recent geospatial machine learning studies show that model evaluation results from cross-validation are strongly influenced by dissimilarity between sample data and prediction locations. This paper introduces a feature-space approach that quantifies that dissimilarity on a 0–100% scale. The method, dissimilarity quantification by adversarial validation (DAV), uses adversarial validation with a binary classifier to test separability. Experiments on synthetic and real datasets demonstrate that DAV quantifies dissimilarity accurately across the full range, and that CV method performance varies with dissimilarity, with random CV best at low dissimilarity, geospatial CV methods improving as it increases, and all methods failing at very high dissimilarity.","GIScience & Remote Sensing  \nISSN: 1548-1603 (Print) 1943-7226 (Online) Journal [homepage: ](homepage: www.tandfonline.com/journals/tgrs20)[www.tandfonline.com/journals/tgrs20](homepage: www.tandfonline.com/journals/tgrs20)  \nOn the use of adversarial validation for quantifying dissimilarity in geospatial machine learning prediction  \nYanwen Wang, Mahdi Khodadadzadeh & Raúl Zurita-Milla  \nTo cite this article: Yanwen Wang, Mahdi Khodadadzadeh & Raúl Zurita-Milla (2025) On the use of adversarial validation for quantifying dissimilarity in geospatial machine learning prediction, GIScience & Remote Sensing, 62: 1, 2460513, DOI: 10.1080/15481603.2025.2460513 To link to this article: [https://doi.org/10.1080/15481603.2025.2460513](https://doi.org/10.1080/15481603.2025.2460513)  \n© 2025 The Author(s) . Published by Informa UK Limited, trading as Taylor & Francis Group.  \n\n|  View supplementary material  |  |\n| --- | --- |\n|  Published online: 04 Feb 2025. |  |\n|  Submit your article to this journal  |  |\n|  | Article views: 736 |\n|  | View related articles  |\n|  View Crossmark data |  |\n\nFull Terms & Conditions of access and use can be found at [https://www.tandfonline.com/action/journalInformation?journalCode=tgrs20](https://www.tandfonline.com/action/journalInformation?journalCode=tgrs20)  \nGISCIENCE & REMOTE SENSING  \n2025, VOL. 62, NO. 1, 2460513 [https://doi.org/10.1080/15481603.2025.2460513](https://doi.org/10.1080/15481603.2025.2460513)  \nOn the use of adversarial validation for quantifying dissimilarity in geospatial machine learning prediction  \nYanwen Wang , Mahdi Khodadadzadeh  and Raúl Zurita-Milla   \nFaculty of Geo-Information Science and Earth Observation (ITC), University of Twente, Enschede, The Netherlands  \nABSTRACT  \nRecent geospatial machine learning studies have shown that the results of model evaluation viacross-validation (CV) are strongly affected by the dissimilarity between the sample data and the prediction locations. In this paper, we propose a method to quantify such a dissimilarity in the interval 0 to 100% and from the perspective of the data feature space. The proposed method is based on adversarial validation, which is an approach that can check whether sample data and prediction locations can be separated with a binary classifier. The proposed method is called dissimilarity quantification by adversarial validation (DAV). To study the effectiveness and generality of DAV, we tested it on a series of experiments based on both synthetic and real datasets and with gradually increasing dissimilarities. Results show that DAV effectively quantified dissimilarity across the entire range of values. Next to this, we studied how dissimilarity affects CV methods’evaluations by comparing the results of random CV method (RDM-CV) and of two geospatial CV methods, namely, block and spatial+ CV (BLK-CV and SP-CV) . Our results showed the evaluations follow similar patterns in all datasets and predictions: when dissimilarity is low (usually lower than 30%), RDM-CV provides the most accurate evaluation results. As dissimilarity increases, geospatial CV methods, especially SP-CV, become more and more accurate and even outperform RDM-CV. When dissimilarity is high (􀀕90%), no CV method provides accurate evaluations. These results show the importance of considering feature space dissimilarity when working with geospatial machine learning predictions and can help researchers and practitioners to select more suitable CV methods for evaluating their predictions.  \nARTICLE HISTORY  \nReceived 19 April 2024 Accepted 24 January 2025  \nKEYWORDS  \nMachine learning; geospatial regression; model evaluation; cross-validation; feature space  \n1. Introduction  \nMachine learning (ML) is widely used in geospatial prediction to estimate unknown values at specific prediction locations (Aguilar et al. 2018; Hengl et al. 2018; Usman et al. 2023) . These predictions are often done to create spatially continuous products, for example, mineral (","cbCaifTLWiUV47qI","https://ap.wps.com/l/cbCaifTLWiUV47qI","pdf",12708260,1,20,"English","en",105,"# Introduction\n## Geospatial machine learning evaluation and cross-validation\n## Adversarial validation and proposed dissimilarity quantification method","[{\"question\":\"What problem does the paper address in geospatial machine learning evaluation?\",\"answer\":\"It addresses how dissimilarity between sample data and prediction locations affects the reliability of cross-validation evaluation results.\"},{\"question\":\"How does the proposed DAV method quantify dissimilarity?\",\"answer\":\"DAV uses adversarial validation by training a binary classifier to check whether sample data and prediction locations can be separated in feature space, then maps this to a 0–100% dissimilarity measure.\"},{\"question\":\"How do different cross-validation methods perform as dissimilarity changes?\",\"answer\":\"When dissimilarity is low (typically below 30%), random CV is most accurate; as dissimilarity increases, geospatial CV methods—especially spatial+ CV (SP-CV)—become more accurate; at very high dissimilarity (over 90%), no CV method yields accurate evaluations.\"}]","On the use of adversarial validation for quantifying dissimilarity in geospatial machine learning prediction | PDF",1785905274,50,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"on-the-use-of-adversarial-validation-for-quantifying-dissimilarity-in-geospatial-machine-learning-prediction-126478","",{"@graph":36,"@context":86},[37,54,69],{"@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/on-the-use-of-adversarial-validation-for-quantifying-dissimilarity-in-geospatial-machine-learning-prediction-126478/126478/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":11},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does the paper address in geospatial machine learning evaluation?","Question",{"text":76,"@type":77},"It addresses how dissimilarity between sample data and prediction locations affects the reliability of cross-validation evaluation results.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the proposed DAV method quantify dissimilarity?",{"text":81,"@type":77},"DAV uses adversarial validation by training a binary classifier to check whether sample data and prediction locations can be separated in feature space, then maps this to a 0–100% dissimilarity measure.",{"name":83,"@type":74,"acceptedAnswer":84},"How do different cross-validation methods perform as dissimilarity changes?",{"text":85,"@type":77},"When dissimilarity is low (typically below 30%), random CV is most accurate; as dissimilarity increases, geospatial CV methods—especially spatial+ CV (SP-CV)—become more accurate; at very high dissimilarity (over 90%), no CV method yields accurate evaluations.","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":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,115,120,123,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":29,"slug":114},6,"Technology","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":21,"slug":126},9,"Religion & Spirituality","religion-spirituality",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":21,"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":107,"slug":137},19,"General","general"]