I will present our work on learning nonlinear, non-Gaussian filtering distributions in a three-part minisymposium on structure-preserving data assimilation and learning.
Jul 14, 2026
I wrote a detailed GitHub repository of textbook-ready demo notebooks for Machine Learning for Inverse Problems and Data Assimilation.
Jul 8, 2026

Our new PSEF framework learns calibrated ensemble filters from simulated trajectories without requiring the true filtering distribution as a training target.
Jun 25, 2026

The proper scoring ensemble filter (PSEF) learns an ensemble analysis operator that targets the complete Bayesian filtering distribution rather than only its conditional mean. The operator takes a forecast ensemble and a new observation as input and returns an analysis ensemble. A permutation-invariant transformer ensures that the result respects the exchangeability of ensemble members and can be evaluated at different ensemble sizes.
Jun 25, 2026

The ensemble flow filter (EnFF) is a training-free data-assimilation framework that uses flow matching to transform a forecast ensemble into samples from the filtering distribution. Its Monte Carlo flow-field estimator and localized observation guidance avoid model training while retaining the flexibility of generative flow design.
Jun 15, 2026

Our ensemble flow filter brings training-free flow matching to efficient, scalable data assimilation.
Jun 15, 2026
I will speak at ILAS 2026 on Tuesday, May 19, 2026, 2:50 PM Eastern, in McBryde Hall 113 at Virginia Tech.
May 19, 2026
Hojjat Kaveh, Nicholas Nelsen, and I are organizing a minisymposium on measure transport at the 2026 SIAM Conference on Mathematics of Data Science.
May 18, 2026
I will give a SIAM student chapter talk on Wednesday, March 11, 2026, 12:00-1:00 PM Pacific at ANB 213, Caltech.
Mar 4, 2026
I will give a JHU AMS postdoc seminar on Wednesday, March 11, 2026, 12:30-1:30 PM Eastern (9:30-10:30 AM Pacific).
Mar 4, 2026