ORCID ID
0000-0001-7838-6116
Date of Award
12-2025
Degree Type
Dissertation
Degree Name
Ph.D.
Degree Program
Engineering and Applied Science - Computer Science
Department
Computer Science
Major Professor
Mahdi Abdelguerfi
Second Advisor
Md Meftahul Ferdaus
Third Advisor
Christopher Summa
Fourth Advisor
Vincent Xiaochuan Yu
Fifth Advisor
Elias Ioup
Sixth Advisor
Julian Simeonov
Abstract
This dissertation investigates surrogate modeling for fixed-location environmental forecasting using novel data-combination techniques. The work surveys the landscape of observational measurements and numerically generated data, identifying similar research and gaps in current methodologies. The ratio-coupled training framework is introduced to combine two data sources per predicted feature through a tunable parameter that weights training signal strength. An optimization scheme is developed to simultaneously tune surrogate weights and the coupled signal ratio, allowing relative influence between signals to act as an explicit regularizer. Three case studies demonstrate the methodology and approach in a variety of contexts. The first study is based on the Cahn-Hilliard equations. This introductory example shows the technique can be used for non-linear equation estimation. The second study uses buoy observation data and two model sources to couple three features at once. Low data quantity and use of an additive architecture yield results unique from the other case studies. Finally, a weather station dataset of nearby observation platforms is used with many coupled features. Baselines were improved upon with careful model tuning and use of a multi-year dataset at training time. In all examples, Gaussian noise is found to be a strong regularizer. When used within the optimization scheme, many examples improved over the direct numerical coupling. Comprehensive comparisons of search methods indicate that optimized and Bayesian hyperparameter selection techniques can deliver competitive accuracy while keeping the hyperparameter tuning time low. Localized surrogates can generate forecast inferences significantly faster than global numerical analyses once a performant model is trained. The results provide guidance on model selection, hyperparameter selection, and search strategy, depending on the underlying dataset and prediction domain. The dissertation concludes with an overview of best methods found as well as suggestions for continued improvements in the near- and long-term.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Recommended Citation
Schmidt, Austin B., "Coupled Machine Learning Models: Combining Observations and Numerical Analysis in a Physics-Regularized Approach" (2025). University of New Orleans Theses and Dissertations. 3311.
https://scholarworks.uno.edu/td/3311
Included in
Applied Statistics Commons, Climate Commons, Data Science Commons, Environmental Monitoring Commons, Fluid Dynamics Commons, Multivariate Analysis Commons, Non-linear Dynamics Commons, Numerical Analysis and Computation Commons, Oceanography Commons, Software Engineering Commons, Statistical Models Commons, Theory and Algorithms Commons
Rights
The University of New Orleans and its agents retain the non-exclusive license to archive and make accessible this dissertation or thesis in whole or in part in all forms of media, now or hereafter known. The author retains all other ownership rights to the copyright of the thesis or dissertation.