[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117494-en":3,"doc-seo-117494-105":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},117494,1099514067415,"Rowan","https://ap-avatar.wpscdn.com/avatar/100002539d78ffe74a7?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779092875211072502",8,"Research & Report","Uncertainty Quantification for Scientific Machine Learning","This dissertation investigates uncertainty quantification (UQ) for scientific machine learning, with an emphasis on robust predictions in deep spatiotemporal forecasting. It develops and evaluates a unified view of uncertainty methods, contrasting frequentist and Bayesian UQ approaches and providing a practical recipe for implementation, experimentation, and visualization. The work also proposes uncertainty-aware multi-fidelity surrogate modeling using hierarchical neural processes, integrating multiple data fidelities while explicitly accounting for predictive uncertainty. ","UC San Diego  \nUC San Diego Electronic Theses and Dissertations  \nTitle  \nUncertainty Quantification for Scientific Machine Learning  \nPermalink  \n[https://escholarship.org/uc/item/5d86g8wg](https://escholarship.org/uc/item/5d86g8wg)  \nAuthor  \nWu, Dongxia  \nPublication Date  \n2025  \nPeer reviewed|Thesis/dissertation  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nUNIVERSITY OF CALIFORNIA SAN DIEGO  \nUncertainty Quantification for Scientific Machine Learning  \nA dissertation submitted in partial satisfaction of the requirements for the degree Doctor of Philosophy  \nin  \nComputer Science  \nby  \nDongxia Wu  \nCommittee in charge:  \nProfessor Rose Yu, Chair  \nProfessor Yi-An Ma, Co-Chair  \nProfessor Sanjoy Dasgupta  \nProfessor Julian McAuley  \nCopyright Dongxia Wu, 2025 All rights reserved.  \nThe Dissertation of Dongxia Wu is approved, and it is acceptable in quality and form for publication on microfilm and electronically.  \nUniversity of California San Diego  \n2025  \nDEDICATION  \nFirst and foremost, I would like to express my sincere gratitude to my advisors, Rose Yu and Yi-An Ma, for their unwavering support throughout my Ph.D. journey. Their patience, motivation, enthusiasm, and immense knowledge have been truly invaluable. Their guidance has been instrumental in both my research and the writing of this thesis. I will always remember the days and nights we spent together tackling challenging research problems. I am also grateful tomy thesis committee members, Julian McAuley and Sanjoy Dasgupta, whose constructive feedback and insightful suggestions were instrumental in helping me complete my dissertation.  \nBeyond my thesis committee, I would also like to thank my colleagues, Brooks Niu, Nikki Kuang, Ray Wang, Zihao Zhou, Bo Zhao, Sumanth Varambally, Jianke Yang, Salva R¨uhling Cachay, Sophia Sun, Aysin Tumay, Geelon So, and Peter Eckmann. During times when I felt uncertain about my research direction, conversations with them always brought valuable inspiration. Their support helped me discover my true interests and understand the right path for my research. This journey of self-discovery has been the most valuable part of my Ph.D., and Iam determined to continue pursuing what I love in the future.  \nI am very fortunate to have worked with many amazing collaborators: Alessandro Vespignani, Matteo Chinazzi, Duncan Watson-Parris, Germano Heinzelmann, Kai Kim, Liyao Gao, Michael K. Gilson, Xinyue Xiong, Utkrisht Rajkumar, Sara Javadzadeh, Mihir Bafna, Jingbo Shang, Vineet Bafna, Lingkai Kong, Yuanqi Du, Wenhao Mu, Kirill Neklyudov, Valentin De Bortoli, Haorui Wang, Aaron Ferber, Carla P Gomes, Chao Zhang, Tsuyoshi Id, Aurlie Lozano, Georgios Kollias, Jiˇ´rı Navrtil, and Naoki Abe.  \nFinally, I would like to express my deepest gratitude to my family for their unwavering support throughout my Ph.D. journey. To my parents and grandparents, thank you for your endless love, encouragement, and inspiration. Your belief in me has been my greatest source of strength. I am also incredibly fortunate to have met my soulmate, Yi Lu, during this journey. Yi, your love, understanding, and companionship have made this experience all the more meaningful. I truly feel blessed to have such an extraordinary family and partner by my side. This milestone is as much yours as it is mine.  \nTABLE OF CONTENTS  \nDissertation Approval Page .................................................... iii  \nDedication .................................................................. iv  \nTable of Contents ............................................................ v  \nList of Figures ............................................................... ix  \nList of Tables ................................................................ xiii  \nAcknowledgements ........................................................... xv  \nVita ........................................................................ xvii  \nAbs","cbCaiu7COz4W5gDh","https://ap.wps.com/l/cbCaiu7COz4W5gDh","pdf",23013645,1,187,"English","en",105,"# Chapter 1 Introduction\n# Chapter 2 Quantifying Uncertainty in Deep Spatiotemporal Forecasting\n## 2.1 Overview\n## 2.2 Deep Spatiotemporal Forecasting\n## 2.3 Uncertainty Quantification in Spatiotemporal Forecasts\n## 2.4 Experiments\n## 2.5 Conclusion\n# Chapter 3 Uncertainty-Aware Multi-Fidelity Surrogate Modeling via Hierarchical Neural Processes\n## 3.1 Overview\n## 3.2 Background\n## 3.3 Methodology","[{\"question\":\"What problem does the dissertation address?\",\"answer\":\"The dissertation studies how to quantify uncertainty in scientific machine learning, especially for deep spatiotemporal forecasting and surrogate modeling tasks.\"},{\"question\":\"How does it organize uncertainty quantification approaches?\",\"answer\":\"It presents a unified framework that compares frequentist UQ methods and Bayesian UQ methods, then summarizes a practical recipe for applying them.\"},{\"question\":\"What methodology is introduced for multi-fidelity modeling?\",\"answer\":\"It proposes uncertainty-aware multi-fidelity surrogate modeling using hierarchical neural processes to integrate different fidelity information while accounting for predictive uncertainty.\"}]","Uncertainty Quantification for Scientific Machine Learning | PDF",1785676287,471,{"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},"uncertainty-quantification-for-scientific-machine-learning","",{"@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/uncertainty-quantification-for-scientific-machine-learning/117494/",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?","Question",{"text":75,"@type":76},"The dissertation studies how to quantify uncertainty in scientific machine learning, especially for deep spatiotemporal forecasting and surrogate modeling tasks.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does it organize uncertainty quantification approaches?",{"text":80,"@type":76},"It presents a unified framework that compares frequentist UQ methods and Bayesian UQ methods, then summarizes a practical recipe for applying them.",{"name":82,"@type":73,"acceptedAnswer":83},"What methodology is introduced for multi-fidelity modeling?",{"text":84,"@type":76},"It proposes uncertainty-aware multi-fidelity surrogate modeling using hierarchical neural processes to integrate different fidelity information while accounting for predictive uncertainty.","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"]