{"id":{"repo_id":"vt","oai_identifier":"oai:vtechworks.lib.vt.edu:10919/117966"},"canonical_url":"https://search.dev.ndltd.org/etd/vt/oai:vtechworks.lib.vt.edu:10919/117966","repository":{"repo_id":"vt","name":"Virginia Tech","base_url":"https://vtechworks.lib.vt.edu/oai/request"},"display":{"title":"Physics-informed Machine Learning with Uncertainty Quantification","abstract":"Physics Informed Machine Learning (PIML) has emerged as the forefront of research in scientific machine learning with the key motivation of systematically coupling machine learning (ML) methods with prior domain knowledge often available in the form of physics supervision. Uncertainty quantification (UQ) is an important goal in many scientific use-cases, where the obtaining reliable ML model predictions and accessing the potential risks associated with them is crucial. In this thesis, we propose novel methodologies in three key areas for improving uncertainty quantification for PIML. First, we propose to explicitly infuse the physics prior in the form of monotonicity constraints through architectural modifications in neural networks for quantifying uncertainty. Second, we demonstrate a more general framework for quantifying uncertainty with PIML that is compatible with generic forms of physics supervision such as PDEs and closed form equations. Lastly, we study the limitations of physics-based loss in the context of Physics-informed Neural Networks (PINNs), and develop an efficient sampling strategy to mitigate the failure modes.","abstract_html":"Physics Informed Machine Learning (PIML) has emerged as the forefront of research in scientific machine learning with the key motivation of systematically coupling machine learning (ML) methods with prior domain knowledge often available in the form of physics supervision. Uncertainty quantification (UQ) is an important goal in many scientific use-cases, where the obtaining reliable ML model predictions and accessing the potential risks associated with them is crucial. In this thesis, we propose novel methodologies in three key areas for improving uncertainty quantification for PIML. First, we propose to explicitly infuse the physics prior in the form of monotonicity constraints through architectural modifications in neural networks for quantifying uncertainty. Second, we demonstrate a more general framework for quantifying uncertainty with PIML that is compatible with generic forms of physics supervision such as PDEs and closed form equations. Lastly, we study the limitations of physics-based loss in the context of Physics-informed Neural Networks (PINNs), and develop an efficient sampling strategy to mitigate the failure modes.","abstract_has_math":false,"creators":["Daw, Arka"],"institution":"Virginia Tech","degree_name":"Doctor of Philosophy","degree_level":"doctoral","degree_discipline":"Computer Science and Applications","degree_department":"Computer Science and Applications","school":null,"contributors":[],"advisors":[],"committee_chairs":["Karpatne, Anuj"],"committee_members":["Reddy, Chandan K.","Ramakrishnan, Narendran","Perdikaris, Paris","Lourentzou, Ismini"],"year":2024,"date_issued":"2024-02-12","date_published":"2024-02-12","updated_at":"2026-07-24T05:56:22Z","subjects":["Deep Learning","Physics-informed Machine Learning","Uncertainty Quantification","Physics-informed Neural Networks."],"languages":["en"],"rights":["In Copyright"],"rights_urls":["http://rightsstatements.org/vocab/InC/1.0/"],"identifier_entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:39285"],"render_values":[{"text":"vt_gsexam:39285","href":null,"code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/10919/117966","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.committeechair","label":"Committee Chair","values":["Karpatne, Anuj"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Reddy, Chandan K.","Ramakrishnan, Narendran","Perdikaris, Paris","Lourentzou, Ismini"]},{"key":"dc:contributor.department","label":"Department","values":["Computer Science and Applications"]},{"key":"dc:creator","label":"Author","values":["Daw, Arka"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2024-02-13T09:00:20Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2024-02-13T09:00:20Z"]},{"key":"dc:date.issued","label":"Date","values":["2024-02-12"]},{"key":"dc:publisher","label":"Institution","values":["Virginia Tech"]},{"key":"dc:type","label":"Dc Type","values":["Dissertation"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science and Applications"]},{"key":"thesis:degree_level","label":"Degree Level","values":["doctoral"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Virginia Polytechnic Institute and State University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Deep Learning","Physics-informed Machine Learning","Uncertainty Quantification","Physics-informed Neural Networks."]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["In Copyright"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/vocab/InC/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:39285"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10919/117966"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Physics Informed Machine Learning (PIML) has emerged as the forefront of research in scientific machine learning with the key motivation of systematically coupling machine learning (ML) methods with prior domain knowledge often available in the form of physics supervision. Uncertainty quantification (UQ) is an important goal in many scientific use-cases, where the obtaining reliable ML model predictions and accessing the potential risks associated with them is crucial. In this thesis, we propose novel methodologies in three key areas for improving uncertainty quantification for PIML. First, we propose to explicitly infuse the physics prior in the form of monotonicity constraints through architectural modifications in neural networks for quantifying uncertainty. Second, we demonstrate a more general framework for quantifying uncertainty with PIML that is compatible with generic forms of physics supervision such as PDEs and closed form equations. Lastly, we study the limitations of physics-based loss in the context of Physics-informed Neural Networks (PINNs), and develop an efficient sampling strategy to mitigate the failure modes."]},{"key":"dc:description.abstractgeneral","label":"General Abstract","values":["Owing to the success of deep learning in computer vision and natural language processing there is a growing interest of using deep learning in scientific applications. In scientific applications, knowledge is available in the form of closed form equations, partial differential equations, etc. along with labeled data. My work focuses on developing deep learning methods that integrate these forms of supervision. Especially, my work focuses on building methods that can quantify uncertainty in deep learning models, which is an important goal for high-stakes applications."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Doctor of Philosophy"]},{"key":"dc:format.medium","label":"Dc Format Medium","values":["ETD"]},{"key":"dc:title","label":"Title","values":["Physics-informed Machine Learning with Uncertainty Quantification"]}]}],"canonical_facts":{"dc:contributor.committeechair":["Karpatne, Anuj"],"dc:contributor.committeemember":["Reddy, Chandan K.","Ramakrishnan, Narendran","Perdikaris, Paris","Lourentzou, Ismini"],"dc:contributor.department":["Computer Science and Applications"],"dc:creator":["Daw, Arka"],"dc:date.accessioned":["2024-02-13T09:00:20Z"],"dc:date.available":["2024-02-13T09:00:20Z"],"dc:date.issued":["2024-02-12"],"dc:description.abstract":["Physics Informed Machine Learning (PIML) has emerged as the forefront of research in scientific machine learning with the key motivation of systematically coupling machine learning (ML) methods with prior domain knowledge often available in the form of physics supervision. Uncertainty quantification (UQ) is an important goal in many scientific use-cases, where the obtaining reliable ML model predictions and accessing the potential risks associated with them is crucial. In this thesis, we propose novel methodologies in three key areas for improving uncertainty quantification for PIML. First, we propose to explicitly infuse the physics prior in the form of monotonicity constraints through architectural modifications in neural networks for quantifying uncertainty. Second, we demonstrate a more general framework for quantifying uncertainty with PIML that is compatible with generic forms of physics supervision such as PDEs and closed form equations. Lastly, we study the limitations of physics-based loss in the context of Physics-informed Neural Networks (PINNs), and develop an efficient sampling strategy to mitigate the failure modes."],"dc:description.abstractgeneral":["Owing to the success of deep learning in computer vision and natural language processing there is a growing interest of using deep learning in scientific applications. In scientific applications, knowledge is available in the form of closed form equations, partial differential equations, etc. along with labeled data. My work focuses on developing deep learning methods that integrate these forms of supervision. Especially, my work focuses on building methods that can quantify uncertainty in deep learning models, which is an important goal for high-stakes applications."],"dc:description.degree":["Doctor of Philosophy"],"dc:format.medium":["ETD"],"dc:identifier.other":["vt_gsexam:39285"],"dc:identifier.uri":["https://hdl.handle.net/10919/117966"],"dc:language.iso":["en"],"dc:publisher":["Virginia Tech"],"dc:rights":["In Copyright"],"dc:rights.uri":["http://rightsstatements.org/vocab/InC/1.0/"],"dc:subject":["Deep Learning","Physics-informed Machine Learning","Uncertainty Quantification","Physics-informed Neural Networks."],"dc:title":["Physics-informed Machine Learning with Uncertainty Quantification"],"dc:type":["Dissertation"],"thesis:degree_discipline":["Computer Science and Applications"],"thesis:degree_level":["doctoral"],"thesis:degree_name":["Doctor of Philosophy"],"thesis:institution_name":["Virginia Polytechnic Institute and State University"]},"updated_at":"2026-07-24T05:56:22Z"}