[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118817-en":3,"doc-seo-118817-105":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":20,"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},118817,962075006959,"Anda","https://ap-avatar.wpscdn.com/avatar/e0002397efbe92a78e?_k=1776741047341049297",8,"Research & Report","Integration of Spatial Data Context into Machine Learning Models - Dissertation","The oil and gas industry has accumulated extensive spatial data from seismic surveys, well logs, and production records, creating strong potential for analytics and machine learning to support physics-based models. Unconventional resources add high measurement uncertainty and incomplete understanding of production mechanisms, motivating data-driven reservoir modeling and decision support. Existing ML tools often overlook key spatial context, leading to unrealistic results and costly risk. This dissertation proposes interpretable, spatially aware workflows that integrate multivariate, multiscale information, domain knowledge, and physics constraints, using geostatistics and graph neural networks to improve prediction accuracy and decision confidence.","Copyright by  \nWendi Liu  \n2022  \nThe Dissertation Committee for Wendi Liu Certifies that this is the approved version of the following Dissertation:  \nIntegration of Spatial Data Context into Machine Learning Models  \nCommittee:  \nMichael J. Pyrcz, Supervisor  \nLarry W. Lake  \nJohn T. Foster  \nMaša Prodanović  \nShane J. Prochnow  \nIntegration of Spatial Data Context into Machine Learning Models  \nby  \nWendi Liu  \nDissertation  \nPresented to the Faculty of the Graduate School of The University of Texas at Austin  \nin Partial Fulfillment  \nof the Requirements  \nfor the Degree of  \nDoctor of Philosophy  \nThe University of Texas at Austin December 2022  \nDedication  \nTo my parents, for their unconditional love, encouragement, and support.  \nAcknowledgements  \nFirst of all, I would like to sincerely express my gratitude to my supervisor, Dr. Michael Pyrcz. None of this work would be possible without the guidance, encouragement, and support from Dr. Pyrcz. His enthusiasm towards education and research always motivates me whenever I encounter difficulties in my Ph.D. journey. I sincerely appreciate the trust, patience, and freedom he provides for me to fully explore my research interest and being always reachable when I need guidance. It is my great honor to work with such an inspiring, patient, and warmhearted advisor in my years of Ph.D. I would also like to extend my gratitude towards my committee members: Dr. Larry Lake, Dr. John Foster, Dr. Maša Prodanović and Dr. Shane Prochnow. I am grateful for them taking their time to provide constructive feedback and helpful discussions.  \nIn addition, I sincerely appreciate the support and friendship from my friends and colleagues throughout my graduate school years, including but not limited to Wan Wei, Zhongmin Tao, Youguang Chen, Yujing Du, Xiao Tian, Amber, Chelsea, Julia, Ricardo, Sheila, Hector, Honggeun, Julian, Mide, Lei Liu, Yuchen Xiao, Mahmood, Wen Pan, Jose, Elnara, Eduardo, Misael, Blazej and many others I did not cite explicitly.  \nMy special thanks go to my parents, Baofeng Liu and Ping Sun, for them always being there for me through ups and downs and always having faith in me that I can achieve anything I set up my mind to. Without their love and support, I would never be the same person I am today. I would also like to thank my boyfriend, Sofiane Achour, for his constant love and encouragement. Pursuing a Ph.D. is never an easy path, but we are so lucky to have each other’s back when there are struggles and challenges and we have so much fun together throughout the graduate school years. I also appreciate the companionship of our “pandemic puppy” Ponyo. She is the cutest crazy little thing in the  \nworld to me. She fully revealed the “dog person” side of me and my graduate school life would be much less fun and joyful without her.  \nLast but not least, I would like to thank the support and help I received from the staff members of the PGE department, especially Jin Lee, John Cassibry, Amy Stewart and Glen Baum. Thanks to their effort, our department is such a lovable and enjoyable place for us to work and study here.  \nAbstract  \nIntegration of Spatial Data Context into Machine Learning Models  \nWendi Liu, Ph. D.  \nThe University of Texas at Austin, 2022  \nSupervisor: Michael J. Pyrcz  \nThe oil and gas industry, over its long history, has accumulated a large volume of spatial data from various resources like seismic surveys, well logs and production information, which provide a huge potential for data analytics and machine learning application to assist physics-based models. The ongoing digitalization transformation in the oil and gas industry also emphasizes this opportunity. In addition, the nature of unconventional resources poses the challenges of high uncertainty among the data measurements and less well-understood production mechanisms. The challenges bring data-driven solutions like machine learning to our attention to support reservoir modeling and decision-makin","cbCaiaXhDjMgo9yy","https://ap.wps.com/l/cbCaiaXhDjMgo9yy","pdf",8940437,1,181,"English","en",105,"# List of Tables\n# Dedication\n# Acknowledgements\n# Abstract\n# Table of Contents","[{\"question\":\"Why is spatial data context important for machine learning in subsurface applications?\",\"answer\":\"Because subsurface data contain spatial continuity, heterogeneity, sampling bias, and data sparsity that can be ignored by direct ML usage, producing unrealistic results and higher-cost risk.\"},{\"question\":\"What main problem does the dissertation address?\",\"answer\":\"The gap between widely used data-driven workflows and the complex spatial context within subsurface data, especially when black-box models are hard for domain experts to interrogate.\"},{\"question\":\"What techniques and design principles does the dissertation use to improve model reliability?\",\"answer\":\"It develops interpretable, data-driven workflows that incorporate domain expertise and physics constraints, integrating geostatistics and graph neural networks across preprocessing, feature engineering, anomaly segmentation, and production forecasting.\"}]","Integration of Spatial Data Context into Machine Learning Models - Dissertation | PDF",1785720428,456,{"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},"integration-of-spatial-data-context-into-machine-learning-models-dissertation","",{"@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/integration-of-spatial-data-context-into-machine-learning-models-dissertation/118817/",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","2026-08-04","2026-08-03",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why is spatial data context important for machine learning in subsurface applications?","Question",{"text":76,"@type":77},"Because subsurface data contain spatial continuity, heterogeneity, sampling bias, and data sparsity that can be ignored by direct ML usage, producing unrealistic results and higher-cost risk.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What main problem does the dissertation address?",{"text":81,"@type":77},"The gap between widely used data-driven workflows and the complex spatial context within subsurface data, especially when black-box models are hard for domain experts to interrogate.",{"name":83,"@type":74,"acceptedAnswer":84},"What techniques and design principles does the dissertation use to improve model reliability?",{"text":85,"@type":77},"It develops interpretable, data-driven workflows that incorporate domain expertise and physics constraints, integrating geostatistics and graph neural networks across preprocessing, feature engineering, anomaly segmentation, and production forecasting.","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},[94,98,102,106,111,116,121,124,129,132,136],{"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":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]