Kevin Egan

Kevin Egan

Postdoctoral Research Scientist at UH Mānoa

Publications

You can also find my articles on my Google Scholar profile.

Journal Articles

Physics-Informed Neural Networks as Differentiable Surrogates for 4D-Variational Data Assimilation

Accepted for publication in Journal of Advances in Modeling Earth Systems (JAMES), 2026

Developed a differentiable physics-informed neural surrogate for 4D-Variational Data Assimilation, using automatic differentiation to replace separately developed tangent-linear and adjoint models while maintaining comparable state-estimation accuracy.

Recommended citation: Egan, K. & Powell, B. (2026). "Physics-Informed Neural Networks as Differentiable Surrogates for 4D-Variational Data Assimilation." Journal of Advances in Modeling Earth Systems. Accepted for publication.
Download Paper

Automatically discovering ordinary differential equations from data with sparse regression

Published in Communications Physics, 2024

Developed ARGOS methodology combining denoising techniques, sparse regression, and bootstrap confidence intervals to automatically discover dynamical systems from noisy data.

Recommended citation: Egan, K., Li, W. & Carvalho, R. (2024). "Automatically discovering ordinary differential equations from data with sparse regression." Communications Physics. 7, 20.
Download Paper

Automatic Extraction of Ordinary Differential Equations from Data: Sparse Regression Tools for System Identification

Published in Durham University, 2023

PhD thesis developing three automated strategies for discovering ordinary differential equation models from data.

Recommended citation: Egan, K. (2023). "Automatic Extraction of Ordinary Differential Equations from Data: Sparse Regression Tools for System Identification." PhD thesis, Durham University.
Download Paper