About

I am a Gordon and Betty Moore Foundation Postdoctoral Fellow in the Computational Climate and Ocean Group at UC Davis, working with Dr. Maike Sonnewald. My research focuses on developing interpretable and trustworthy machine learning methods to understand and emulate ocean systems across scales.

I received my Ph.D. in Mathematics from Washington University in St. Louis in 2025, advised by Dr. Ari Stern. My doctoral work studied structure-preserving numerical integration and the stability of machine learning models. This foundation now informs my work on explainable AI for complex systems.

My current research lies at the intersection of machine learning and ocean science. I am particularly interested in interpretable AI emulators that improve our understanding of nonlinear ocean processes, extreme events, and long-term climate behavior. I love collaborating with other people so pleas

Research Interests: Interpretable AI, ocean and climate dynamics, stability of neural networks, numerical analysis, hybrid physics–machine learning models.

I enjoy collaborating across disciplines and welcome opportunities to connect! I received my undergraduate degree from Grinnell College and am always happy to connect with current students or alumni.


📄 Download my CV
📧 sansuri@ucdavis.edu


Publications

S. Suri, K. Ringel, M. Sonnewald (2026), OceanCBM: A Concept Bottleneck Model for Mechanistic Interpretability in Ocean Physics, Accepted as a NeurIPS Spotlight Paper.

S. Suri and M. Sonnewald (2026), Trusting Machine Learning with Physics: A Fidelity Verification Framework for Neural Networks, In Press at Journal of Geophysical Research: Machine Learning and Computation.

S. Suri (2025), Functional Equivariance and Backward Error Analysis, Ph.D. Thesis.

A. Stern and S. Suri (2023), Functional Equivariance and Modified Vector Fields, Journal of Computational Dynamics, 11(4), 409–426.

D. Rim, S. Suri, S. Hong, K. Lee, R. J. LeVeque (2023), A Stability Analysis of Neural Networks and Its Application to Tsunami Early Warning, Journal of Geophysical Research: Machine Learning and Computation, 1(4).

M. Chamberland, S. Jing, S. Suri (2020), A Generalization of the One-Seventh Ellipse, Mathematics Magazine, 93(4), 271–275.

News

  • 2026 Our paper on OceanCBM, the first concept bottleneck model for ocean forecasting, has been accepted as a NeurIPS Spotlight paper
  • 2026 Our paper on fidelity verification of neural networks for complex systems has been accepted by JGR: Machine Learning and Computation
  • 2026: Poster presentation on Trusting Machine Learning with Physics at Institute for Pure and Applied Mathematics (IPAM) in UCLA
  • 2025: Participated in ICERM Hot Topics Workshop on Modeling and Learning with HPC
  • 2025: Started Postdoctoral position at UC Davis in Computational Climate and Ocean Group
  • 2025: Graduated with Ph.D. in Mathematics from Washington University in St. Louis
  • 2024: Delivered invited talks at SciCADE, Midwest Numerical Analysis Day and Missouri S&T Applied Mathematics Seminar
  • 2024: Featured in WashU Ampersand magazine for my research: Math for a Changing World