{"id":{"repo_id":"colostate","oai_identifier":"oai:mountainscholar.org:10217/241028"},"canonical_url":"https://search.dev.ndltd.org/etd/colostate/oai:mountainscholar.org:10217/241028","repository":{"repo_id":"colostate","name":"Colorado State University","base_url":"https://api.mountainscholar.org/server/oai/request"},"display":{"title":"Scalable predictive modeling for spatiotemporally evolving phenomena","abstract":"Spatiotemporally evolving phenomena occur in epidemiology, atmospheric sciences, agriculture, and traffic management, among others. Models can be used to understand and inform decision-making in these settings. There has been a growth in both mechanistic and physics-informed methods to model phenomena. A challenge in such models is the need for extensive parametrization and calibration, which can be difficult for modeling phenomena at the continental scale. This has occurred alongside the availability of diverse data that can be leveraged by model-fitting algorithms. This dissertation focuses on leveraging deep learning methods to model spatiotemporally evolving phenomena by combining sparse but high-precision in situ measurement data with voluminous, low-precision satellite imagery. The research explores techniques to integrate scientific models and make use of diverse data sources, overcoming their disparities in precision, spatial coverage, and temporal resolution. We explore several methods to leverage scientific models and harness available data despite disparities in their precision, spatial scope, or temporal frequencies. We also regulate how the networks learn by designing custom multipart loss functions that combine traditional measures of accuracy alongside physics/domain-informed variability. As data volumes increase, there is a corresponding increase in the resource requirements – GPU, memory, disk, and network I/O – requirements for model training. To address scalability issues, we designed a framework that manages multi-dimensional data volumes, partitions data effectively, curtails modeling costs, and transfer learning schemes to improve the efficiency of model training workflows. By incorporating scientific knowledge into the learning process, this research addresses the challenges of limited data availability and the data-intensive nature of deep neural networks. The method generalize effectively, enabling the way for scalable and accurate models in data-scarce domains.","abstract_html":"Spatiotemporally evolving phenomena occur in epidemiology, atmospheric sciences, agriculture, and traffic management, among others. Models can be used to understand and inform decision-making in these settings. There has been a growth in both mechanistic and physics-informed methods to model phenomena. A challenge in such models is the need for extensive parametrization and calibration, which can be difficult for modeling phenomena at the continental scale. This has occurred alongside the availability of diverse data that can be leveraged by model-fitting algorithms. This dissertation focuses on leveraging deep learning methods to model spatiotemporally evolving phenomena by combining sparse but high-precision in situ measurement data with voluminous, low-precision satellite imagery. The research explores techniques to integrate scientific models and make use of diverse data sources, overcoming their disparities in precision, spatial coverage, and temporal resolution. We explore several methods to leverage scientific models and harness available data despite disparities in their precision, spatial scope, or temporal frequencies. We also regulate how the networks learn by designing custom multipart loss functions that combine traditional measures of accuracy alongside physics/domain-informed variability. As data volumes increase, there is a corresponding increase in the resource requirements – GPU, memory, disk, and network I/O – requirements for model training. To address scalability issues, we designed a framework that manages multi-dimensional data volumes, partitions data effectively, curtails modeling costs, and transfer learning schemes to improve the efficiency of model training workflows. By incorporating scientific knowledge into the learning process, this research addresses the challenges of limited data availability and the data-intensive nature of deep neural networks. The method generalize effectively, enabling the way for scalable and accurate models in data-scarce domains.","abstract_has_math":false,"creators":["Khandelwal, Paahuni, author","Pallickara, Sangmi Lee, advisor","Pallickara, Shrideep, committee member","Ghosh, Sudipto, committee member","Andales, Allan, committee member"],"institution":"Colorado State University. Libraries","degree_name":"Doctor of Philosophy (Ph.D.)","degree_level":"Doctoral","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025","date_published":"2025","updated_at":"2026-07-27T19:13:20Z","subjects":["distributed learning","high-resolution imaging","transfer learning","GeoAI","deep neural network","science-guided learning"],"languages":["eng","English"],"rights":["Copyright and other restrictions may apply. User is responsible for compliance with all applicable laws. For information about copyright law, please see https://libguides.colostate.edu/copyright."],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://doi.org/10.25675/3.02551"],"render_values":[{"text":"https://doi.org/10.25675/3.02551","href":"https://doi.org/10.25675/3.02551","code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/10217/241028","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Khandelwal, Paahuni, author","Pallickara, Sangmi Lee, advisor","Pallickara, Shrideep, committee member","Ghosh, Sudipto, committee member","Andales, Allan, committee member"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-06-02T15:21:09Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2027-05-28"]},{"key":"dc:date.issued","label":"Date","values":["2025"]},{"key":"dc:publisher","label":"Institution","values":["Colorado State University. Libraries"]},{"key":"dc:type","label":"Dc Type","values":["Text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Doctoral"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy (Ph.D.)"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Colorado State University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["distributed learning","high-resolution imaging","transfer learning","GeoAI","deep neural network","science-guided learning"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["English"]},{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright and other restrictions may apply. User is responsible for compliance with all applicable laws. For information about copyright law, please see https://libguides.colostate.edu/copyright."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["Khandelwal_colostate_0053A_18815.pdf"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10217/241028","https://doi.org/10.25675/3.02551"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Spatiotemporally evolving phenomena occur in epidemiology, atmospheric sciences, agriculture, and traffic management, among others. Models can be used to understand and inform decision-making in these settings. There has been a growth in both mechanistic and physics-informed methods to model phenomena. A challenge in such models is the need for extensive parametrization and calibration, which can be difficult for modeling phenomena at the continental scale. This has occurred alongside the availability of diverse data that can be leveraged by model-fitting algorithms. This dissertation focuses on leveraging deep learning methods to model spatiotemporally evolving phenomena by combining sparse but high-precision in situ measurement data with voluminous, low-precision satellite imagery. The research explores techniques to integrate scientific models and make use of diverse data sources, overcoming their disparities in precision, spatial coverage, and temporal resolution. We explore several methods to leverage scientific models and harness available data despite disparities in their precision, spatial scope, or temporal frequencies. We also regulate how the networks learn by designing custom multipart loss functions that combine traditional measures of accuracy alongside physics/domain-informed variability. As data volumes increase, there is a corresponding increase in the resource requirements – GPU, memory, disk, and network I/O – requirements for model training. To address scalability issues, we designed a framework that manages multi-dimensional data volumes, partitions data effectively, curtails modeling costs, and transfer learning schemes to improve the efficiency of model training workflows. By incorporating scientific knowledge into the learning process, this research addresses the challenges of limited data availability and the data-intensive nature of deep neural networks. The method generalize effectively, enabling the way for scalable and accurate models in data-scarce domains."]},{"key":"dc:format.medium","label":"Dc Format Medium","values":["born digital","doctoral dissertations"]},{"key":"dc:title","label":"Title","values":["Scalable predictive modeling for spatiotemporally evolving phenomena"]}]}],"canonical_facts":{"dc:creator":["Khandelwal, Paahuni, author","Pallickara, Sangmi Lee, advisor","Pallickara, Shrideep, committee member","Ghosh, Sudipto, committee member","Andales, Allan, committee member"],"dc:date.accessioned":["2025-06-02T15:21:09Z"],"dc:date.available":["2027-05-28"],"dc:date.issued":["2025"],"dc:description.abstract":["Spatiotemporally evolving phenomena occur in epidemiology, atmospheric sciences, agriculture, and traffic management, among others. Models can be used to understand and inform decision-making in these settings. There has been a growth in both mechanistic and physics-informed methods to model phenomena. A challenge in such models is the need for extensive parametrization and calibration, which can be difficult for modeling phenomena at the continental scale. This has occurred alongside the availability of diverse data that can be leveraged by model-fitting algorithms. This dissertation focuses on leveraging deep learning methods to model spatiotemporally evolving phenomena by combining sparse but high-precision in situ measurement data with voluminous, low-precision satellite imagery. The research explores techniques to integrate scientific models and make use of diverse data sources, overcoming their disparities in precision, spatial coverage, and temporal resolution. We explore several methods to leverage scientific models and harness available data despite disparities in their precision, spatial scope, or temporal frequencies. We also regulate how the networks learn by designing custom multipart loss functions that combine traditional measures of accuracy alongside physics/domain-informed variability. As data volumes increase, there is a corresponding increase in the resource requirements – GPU, memory, disk, and network I/O – requirements for model training. To address scalability issues, we designed a framework that manages multi-dimensional data volumes, partitions data effectively, curtails modeling costs, and transfer learning schemes to improve the efficiency of model training workflows. By incorporating scientific knowledge into the learning process, this research addresses the challenges of limited data availability and the data-intensive nature of deep neural networks. The method generalize effectively, enabling the way for scalable and accurate models in data-scarce domains."],"dc:format.medium":["born digital","doctoral dissertations"],"dc:identifier":["Khandelwal_colostate_0053A_18815.pdf"],"dc:identifier.uri":["https://hdl.handle.net/10217/241028","https://doi.org/10.25675/3.02551"],"dc:language":["English"],"dc:language.iso":["eng"],"dc:publisher":["Colorado State University. Libraries"],"dc:rights":["Copyright and other restrictions may apply. User is responsible for compliance with all applicable laws. For information about copyright law, please see https://libguides.colostate.edu/copyright."],"dc:subject":["distributed learning","high-resolution imaging","transfer learning","GeoAI","deep neural network","science-guided learning"],"dc:title":["Scalable predictive modeling for spatiotemporally evolving phenomena"],"dc:type":["Text"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Doctoral"],"thesis:degree_name":["Doctor of Philosophy (Ph.D.)"],"thesis:institution_name":["Colorado State University"]},"updated_at":"2026-07-27T19:13:20Z"}