[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118201-en":3,"doc-seo-118201-105":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},118201,8796095461610,"Oliver","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Machine Learning Approaches for Building Inventory Characterisation","Accurate building inventories underpin sustainable urban governance and support Sustainable Development Goal 11 on sustainable cities and communities. Manual acquisition of building information in complex, densely built areas is impractical and often fails to deliver the thematic and spatial detail required for real-world applications. Leveraging advances in remote sensing and open-access satellite and drone imagery, this study investigates machine learning and deep learning methods for multi-class urban building characterisation.","Machine Learning Approaches for Building Inventory Characterisation  \nA thesis submitted in partial fulfilment of the requirements for the Degree of Master of Science in Geospatial Technologies  \nby  \nSunil Tamang  \nSupervised by:  \nDr. Bakhtiar Feizizadeh  \nInstitute of Geoinformatics  \nUniversity of Münster  \nMünster, Germany  \nCo-supervised by:  \nDr. Marco Painho  \nNOVA Information Management School Universidade Nova de Lisboa Lisboa, Portugal  \nDr. Christian Geiss  \nGerman Remote Sensing Data Center German Aerospace Center (DLR) Oberpfaffenhofen, Germany  \n20 February 2024  \nDeclaration  \nI hereby confirm that the thesis titled \"Machine Learning Approaches for Building Inventory Characterisation\" is entirely my original work, completed with the guidance of my supervisors. All sources used, including books, journals, handouts, unpublished manuscripts, and various internet resources, have been accurately cited. This thesis has not been approved for any degree and is not currently being submitted for any other academic qualification.  \nSunil Tamang Münster, Germany 20 February 2024  \nCopyright Statement  \nYou are permitted to access and review this thesis under the following usage guidelines:  \n• You may utilise the thesis copy solely for research or personal study purposes.  \n• Acknowledge the author's right to be recognised as the author of the thesis and provide appropriate acknowledgment when necessary.  \n• Seek permission from the author before publishing any material derived from the thesis.  \nAcknowledgements  \nI want to express my sincere appreciation to my supervisors: Dr. Bhaktiar Fezizadeh from Institute of Geoinformatics (IFGI), University of Münster; Prof. Dr. Marco Painho from NOVA University of Lison; and Prof. Dr. Christian Geiss from German Aerospace Center (DLR) for guiding and supporting me throughout my thesis research. Special thanks to Anne Schauss from Heidelberg Institute for Geoinformation Technology (HeiGIT) for connecting me to Dr. Geiss, who proposed thesis topic and provided the data. I am equally thankful to Dr. Maciej Adamiak from HeiGIT for continued technical consultation and encouragement.  \nAcknowledgements are also due to Prof. Joaquin Huerta from University Jaume (UJI), and Dr. Chrisopher Brox at IFGI, and Prof. Dr. Marco Painho for their outstanding coordination of Erasmus Mundus joint master`s degree program. My heartfelt thanks to Erasmus Mundus program for providing a fully funded scholarship, which played important role in enriching my academic and personal experience.  \nI extend my gratitude to all professors from UJI and IFGI involved in the joint master program. A special note of gratitude goes to Prof. Sven Casteleyn for his unparalleled support and inspiration in learning programming skills. I am also thankful to Gloria from UJI for consistent assistance in navigating unexpected bureaucratic processes.  \nThank you to all friends from Castellon cohort and Lisbon cohort for many beautiful experiencesand mutual support that propelled us forward together. Lastly, my deepest thanks to my family for their unwavering belief in my pursuits and encouragement to continue learning and exploring new avenues.  \nAbstract  \nAccurate building inventories and relevant information are essential for sustainable urban governance, thereby contributing to achieve the Sustainable Development Goal 11, which focuses on sustainable cities and communities. Acquiring building information manually in complex-built environment with densely populated buildings is impractical and may not guarantee the high thematic and spatial detail necessary for real world applications.  \nRecent advancements in remote sensing technology, coupled with the availability of highresolution satellite and drone-based imagery through open access channels and as machine learning (ML) and deep learning (DL) continue to advance, showcasing their capability to recognise complex patterns, new opportunities for interpreting various surface","cbCaio1zrVxousuf","https://ap.wps.com/l/cbCaio1zrVxousuf","pdf",3065726,1,50,"English","en",105,"# Abstract\n# Declaration\n# Copyright Statement\n# Acknowledgements\n# Keywords","[{\"question\":\"Why are accurate building inventories important for urban governance?\",\"answer\":\"They provide the information needed for sustainable urban management and contribute to Sustainable Development Goal 11 focused on sustainable cities and communities.\"},{\"question\":\"What models are implemented for building characterisation in the study?\",\"answer\":\"Random Forest (RF) is used as the machine learning model, and a dense neural network (DNN) is used as the deep learning model.\"},{\"question\":\"How does the DNN performance compare with RF?\",\"answer\":\"Overall accuracy is higher for RF, while DNN achieves better classification for four classes and shows higher recall for those same four categories.\"}]","Machine Learning Approaches for Building Inventory Characterisation | PDF",1785682142,126,{"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},"machine-learning-approaches-for-building-inventory-characterisation","",{"@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/machine-learning-approaches-for-building-inventory-characterisation/118201/",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 are accurate building inventories important for urban governance?","Question",{"text":75,"@type":76},"They provide the information needed for sustainable urban management and contribute to Sustainable Development Goal 11 focused on sustainable cities and communities.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What models are implemented for building characterisation in the study?",{"text":80,"@type":76},"Random Forest (RF) is used as the machine learning model, and a dense neural network (DNN) is used as the deep learning model.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the DNN performance compare with RF?",{"text":84,"@type":76},"Overall accuracy is higher for RF, while DNN achieves better classification for four classes and shows higher recall for those same four categories.","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},[93,97,101,105,110,114,119,122,127,130,134],{"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":21,"slug":113},6,"Technology","technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"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"]