Physics-Informed Neural Networks as Differentiable Surrogates for 4D-Variational Data Assimilation
Poster, Accelerating Research in the Age of AI (Google–UH), Honolulu, HI
Poster presentation; received the Pacific Islands Impact Award.
Talks and presentations
Physics-Informed Neural Networks as Differentiable Surrogates for 4D-Variational Data Assimilation
Poster, Machine Learning and Dynamical Systems (MLDS 5) & Differential Equations for Data Science (DEDS 2026), Kyoto, Japan
Poster presentation on differentiable neural surrogates for 4D-Var data assimilation.
Leveraging Physics-Informed Neural Networks for 4D-Variational Data Assimilation
Talk, CBIOMES Annual Meeting 2025, Simons Foundation, New York, NY
Presented research on physics-informed neural networks for 4D-Var data assimilation in marine ecosystem modeling.
Building a Physics-Informed Neural Network for NPZ Modeling
Workshop, CBIOMES Workshop on Photosynthesis and Primary Production, Simons Foundation, New York, NY
Workshop presentation on developing physics-informed neural networks for NPZ ecosystem dynamics.
Discovering Governing Equations from Data using Sparse Regression
Talk, Joint Statistical Meetings (JSM) & Symposium on Data Science & Statistics (SDSS), Virtual
Presented work on sparse regression methods for discovering ordinary differential equations from time-series data at the American Statistical Association conferences.
Discovering Governing Equations from Data using Sparse Regression
Talk, SIAM Conference on Optimization (OP21) & Conference on Dynamical Systems (DS21), Virtual
Presented work on sparse regression methods for system identification at the Society for Industrial and Applied Mathematics conferences.