[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117498-en":3,"doc-seo-117498-105":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},117498,1099514067438,"River Wang","https://ap-avatar.wpscdn.com/avatar/100002539ee87300030?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780474512215547542",8,"Research & Report","Outlier Detection & Reconstruction of Lost Big Earth Data using Machine Learning - Doctor of Philosophy Thesis","This dissertation enhances outlier detection and data reconstruction for Earth Observation (EO) datasets, focusing on Land Surface Temperature (LST) values where undetected anomalies can distort temperature patterns and missing records reduce assessment reliability. The study targets challenges in collecting, processing, and analyzing LST data driven by high variability, noise, and large volumes of satellite imagery. A research framework limits the study area to Beijing-Tianjin-Hebei (BTH), processes image rasters in ArcGIS, and converts them into machine-learning-ready tabular data. New techniques improve temperature representation accuracy and statistical learning while reducing reconstruction errors and data gaps. Self-supervised learning with a TabNet regressor improves anomaly forecasting and rectification, demonstrating higher detection precision and stronger reconstruction usability. Results address model adaptability across varied datasets and support reliable environmental monitoring, with transferability to other image-based data exhibiting similar obscured regions.","Outlier Detection & Reconstruction of Lost Big Earth Data Using Machine Learning  \nby  \nMuhammad Yasir Adnan  \nA Thesis Submitted in Partial Fulfilment of the Requirements for the Degree  \nof Doctor of Philosophy  \nJuly 7, 2025  \nCollege of Science and Engineering University of Derby  \nOutlier Detection & Reconstruction of Lost Big Earth Data using Machine Learning  \nby  \nMuhammad Yasir Adnan  \nDirector of Studies: Stephan Reiff-Marganiec 1st Supervisor: Richard Self  \nSchool of Computing and Engineering  \nJuly 7, 2025  \nFaculty of Science and Engineering  \nUniversity of Derby  \nAcknowledgments  \nFirst and foremost, I wish to extend my deepest gratitude to my wife, whose unwavering support and understanding have been the bedrock of my perseverance throughout the journey of this PhD. Her constant encouragement, patience, and belief in my capabilities have been invaluable, providing me with the strength and motivation needed to pursue and fulfill my academic ambitions. Her role in this process has been immeasurable, and for that, I am eternally grateful.  \nI would also like to express my heartfelt thanks to my parents and my siblings, whose prayers and endless love have surrounded me with positivity, faith and occasional distractions have been a welcome relief and a source of joy throughout this demanding period.  \nTo my friends, who have become more like a family during this journey, especially in the context of living abroad away from my family, your camaraderie, support, and faith in my work have been a constant source of comfort and motivation. The distance from home has been challenging, but the moments we shared, the discussions we had, and the memories we created together have enriched this journey in ways words cannot fully capture, making a foreign land feel like home.  \nI am profoundly grateful to my supervisory team, Professor Stephan ReifMarganiec, Professor Yong Xue and Senior Lecturer Richard Self, for their guidance, patience, and invaluable insights throughout this research. The expertise and thoughtful advice have been crucial in shaping the direction and execution of this work. Prof. Stephan’s support has not only been academic but also motivational, pushing me to achieve excellence while navigating the challenges of research. His mentorship has been a significant pillar of my PhD journey.  \nThis dissertation is not just a reflection of my efforts but a testament to the love, support, and faith of all the incredible individuals mentioned above. Their contributions to my life and this work are deeply appreciated and will always be remembered with gratitude.  \nAbstract  \nThis dissertation thoroughly examines enhancing outlier detection and reconstruction techniques for Earth Observation (EO) datasets, specifically focusing on Land Surface Temperature (LST) values. Addressing both outlier detection and data reconstruction is crucial for EO and LST data analysis because undetected anomalies can distort temperature patterns, and incomplete data reduces the reliability of environmental assessments.  \nThis research focuses on addressing important difficulties related to the collecting, processing, and analysis of LST data, which is in high demand for environmental monitoring and decision-making. In particular, the high variability of EO data, presence of noise and missing values, and the large volumes of satellite imagery pose significant challenges requiring robust and scalable methods.  \nThis effort focuses on identifying and setting boundaries for the study area, particularly the Beijing-Tianjin-Hebei (BTH) region. A high-level research method is adopted, where image raster data are processed in ArcGIS and then transformed into tabular format suitable for machine learning, enabling systematic detection and correction of anomalies.  \nThis thesis presents new techniques for improving the accuracy of temperature intensity representations and enabling effective statistical learning by processing image raster data in Ar","cbCaicQZIFbvqenn","https://ap.wps.com/l/cbCaicQZIFbvqenn","pdf",5838899,1,140,"English","en",105,"# Abstract\n## Motivation and problem scope\n## Study area and data workflow\n## Proposed techniques for LST reconstruction\n## Self-supervised learning with TabNet\n## Evaluation outcomes and applicability","[{\"question\":\"What problem does the dissertation address in Earth Observation data?\",\"answer\":\"It addresses enhancing outlier detection and reconstructing lost or incomplete Land Surface Temperature (LST) data. Undetected anomalies can distort temperature patterns, and missing data weakens environmental assessment reliability.\"},{\"question\":\"How is the study area and data prepared for machine learning?\",\"answer\":\"The research focuses on the Beijing-Tianjin-Hebei (BTH) region. Image raster data are processed in ArcGIS and transformed into tabular format suitable for machine learning.\"},{\"question\":\"What machine learning approach is used to improve anomaly detection and reconstruction?\",\"answer\":\"The dissertation uses self-supervised learning, specifically the TabNet regressor. Experiments show increased anomaly detection precision and reduced data gaps after reconstruction and rectification.\"}]","Outlier Detection & Reconstruction of Lost Big Earth Data using Machine Learning - Doctor of Philosophy Thesis | PDF",1785676342,353,{"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},"outlier-detection-reconstruction-of-lost-big-earth-data-using-machine-learning-doctor-of-philosophy-thesis","",{"@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/outlier-detection-reconstruction-of-lost-big-earth-data-using-machine-learning-doctor-of-philosophy-thesis/117498/",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},"What problem does the dissertation address in Earth Observation data?","Question",{"text":75,"@type":76},"It addresses enhancing outlier detection and reconstructing lost or incomplete Land Surface Temperature (LST) data. Undetected anomalies can distort temperature patterns, and missing data weakens environmental assessment reliability.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is the study area and data prepared for machine learning?",{"text":80,"@type":76},"The research focuses on the Beijing-Tianjin-Hebei (BTH) region. Image raster data are processed in ArcGIS and transformed into tabular format suitable for machine learning.",{"name":82,"@type":73,"acceptedAnswer":83},"What machine learning approach is used to improve anomaly detection and reconstruction?",{"text":84,"@type":76},"The dissertation uses self-supervised learning, specifically the TabNet regressor. Experiments show increased anomaly detection precision and reduced data gaps after reconstruction and rectification.","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"]