[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117233-en":3,"doc-seo-117233-105":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},117233,2336464648322,"Aria","https://ap-avatar.wpscdn.com/avatar/2200025388227c56fec?_k=1778556882303663488",8,"Research & Report","Interpretation of geospatial data using explainable machine learning methods","This dissertation addresses the need for transparent and interpretable analysis of spatial data in scientific research and geographic information systems. It frames geoprocessing pipelines as a basis for repeatability and critical evaluation, while arguing that expert-driven approaches can be insufficient for complex nonlinear environmental problems. Motivated by the rapid growth of multisensor spatial datasets, the work develops regression and classification workflows using machine learning, then contrasts supervised and unsupervised learning. It further discusses the trade-off between predictive accuracy and model explainability by comparing black-box and white-box models.","Adam Mickiewicz University Doctoral School of Natural Sciences Faculty of Geographical and Geological Sciences  \nDISSERTATION  \nKrzysztof Dyba  \nInterpretation of geospatial data using explainable machine learning methods  \nSupervisor  \nProf. UAM dr hab. Jarosław Jasiewicz  \nAssistant Supervisor  \n[Prof. UAM dr hab. in](Prof. UAM dr hab. in)ż. Cezary Kaźmierowski  \nAcknowledgments  \nI thank my parents Mirosław and Irena for their support and motivation in carrying out my scientific work.  \nI thank my supervisors Professor Jarosław Jasiewicz and Professor Cezary Kaźmierowski for their time, inspiration for scientific research, assistance and critical comments.  \nI thank my colleagues Prof. Jan Piekarczyk, Prof. Sławomir Królewicz, Prof. Jakub Nowosad and Dr. Jakub Ceglarek for cooperation, discussions and kindness. In addition, I thank Dr. Jakub Ceglarek for proofreading, which significantly improved the dissertation.  \nTable of contents  \n1. Introduction ……………………………………………………………………………….. 1  \n1.1. Objective……………………………………………………………………………… 5  \n2. Materials and methods …………………………………………………………...……….. 7  \n3. Summary of articles ………………………………………………………...………..…… 10  \n3.1. Regression analysis ………………………………………….……….…………….…. 10  \n3.2. Supervised classification .………………………………………………….………..... 12  \n3.3. Unsupervised classification ……………………………………………………..….… 14  \n4. Discussion………………………………………………………………………………… 16  \n5. Conclusion ……………………………………………………………..………………..… 18  \n6. Bibliography ………………………………………………………………………………. 19  \n7. Attachments ……………………………………………………………………………….. 26  \n7.1. Academic achievements ..……………………………………………………………... 26  \n7.2. Copies of articles ……………...………………………………………………………. 29  \n1. Introduction  \nIn scientific research, the transparency of the data processing is crucial, both for the interpretation of the results and the comparability of the results achieved using different methods. Numerical methods used in geographic information systems are mainly based on geoprocessing algorithms. If the sequence of algorithms is well-documented – from the acquisition of the data to the obtaining of the result, the analytical process is transparent to the user; thus allowing for repetition, but also for critical analysis. This approach reflects the knowledge of the researcher, understanding of the input data and knowing the analytical procedures that lead to the result. However, models created solely on the basis of expert knowledge are usually characterized by a certain approximation of the modeled process, i.e. they are its simplification.  \nThe rapid development of geoinformatics technologies is closely linked to the tremendous growth of spatial data, which is a mutual process. Data growth requires new efficient and effective analytical techniques, which contributes to the increased demand for data and investment in new sensors. These data are acquired from various sensors, including multispectral imagery and geographical coordinates from satellites, point clouds from laser scanning, as well as field surveysand digitization of archival data (Chiang et al., 2014; Gotway & Young, 2002) . In the face of such large datasets, the expert-based methods used so far turn out to be insufficient, especially for complex and non-linear problems occurring in the natural sciences. For this reason, researchers are turning to the use of advanced machine learning methods to analyze spatial data (Bergen et al., 2019; Casali et al., 2022; Du et al., 2020; Karpatne et al., 2019; Lary et al., 2016; Nikparvar & Thill, 2021) .  \nMachine learning is a subfield of artificial intelligence that involves creating regression or classification models based on self-learning algorithms and training data. The main goal of machine learning is the development of models that effectively recognize patterns and relationships on new datasets, resulting in easier and more automated work. The machine learning process is intended to produce useful tools whose effectiveness has been verified ","cbCaiaJDXWCRuDXW","https://ap.wps.com/l/cbCaiaJDXWCRuDXW","pdf",39314498,1,84,"English","en",105,"# Introduction\n## Objective\n# Materials and methods\n# Summary of articles\n## Regression analysis\n## Supervised classification\n## Unsupervised classification\n# Discussion\n# Conclusion\n# Bibliography\n# Attachments\n## Academic achievements\n## Copies of articles","[{\"question\":\"Why is transparency in geographic data processing important?\",\"answer\":\"Transparency supports interpretation of results and comparability across different methods. Documenting algorithm sequences from data acquisition to outputs enables repetition and critical analysis.\"},{\"question\":\"What distinguishes supervised and unsupervised learning for spatial data?\",\"answer\":\"Supervised learning uses a priori reference variables for either classification or regression, while unsupervised learning relies only on independent features. Unsupervised results require post-hoc interpretation and labeling of clustering groups.\"},{\"question\":\"How does explainability relate to predictive accuracy in the dissertation?\",\"answer\":\"White-box models offer more understandable mechanisms but may require stronger feature engineering and can yield lower accuracy. Black-box models can achieve high prediction accuracy, but their rationale is not explicitly available, raising questions about drivers and effects.\"}]","Interpretation of geospatial data using explainable machine learning methods | PDF",1785674596,212,{"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},"interpretation-of-geospatial-data-using-explainable-machine-learning-methods","",{"@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/interpretation-of-geospatial-data-using-explainable-machine-learning-methods/117233/",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","2026-08-02",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 transparency in geographic data processing important?","Question",{"text":75,"@type":76},"Transparency supports interpretation of results and comparability across different methods. Documenting algorithm sequences from data acquisition to outputs enables repetition and critical analysis.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What distinguishes supervised and unsupervised learning for spatial data?",{"text":80,"@type":76},"Supervised learning uses a priori reference variables for either classification or regression, while unsupervised learning relies only on independent features. Unsupervised results require post-hoc interpretation and labeling of clustering groups.",{"name":82,"@type":73,"acceptedAnswer":83},"How does explainability relate to predictive accuracy in the dissertation?",{"text":84,"@type":76},"White-box models offer more understandable mechanisms but may require stronger feature engineering and can yield lower accuracy. Black-box models can achieve high prediction accuracy, but their rationale is not explicitly available, raising questions about drivers and effects.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":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"]