Learning Enhanced Ensemble Filters
This work introduces the measure neural mapping enhanced ensemble filter (MNMEF), a learning-based data-assimilation method derived from a mean-field formulation of the filtering problem. Measure neural mappings extend neural operators to maps acting on probability measures; their finite-ensemble implementation uses a permutation-invariant set transformer.
Feb 15, 2026
ACM 154: Inverse Problems and Data Assimilation
In winter 2026, I co-taught Caltech ACM 154, Inverse Problems and Data Assimilation, with Prof. Andrew Stuart.
Jan 5, 2026
Learning Enhanced Ensemble Filters Published in JCP
Our measure neural mapping enhanced ensemble filter has been published in the Journal of Computational Physics.
Dec 11, 2025
🎉 Caltech SURF 2026
I will be a mentor for the Caltech Summer Undergraduate Research Fellowships (SURF) program in 2026.
Nov 10, 2025
AGU25 Oral — Learning Enhanced Ensemble Filters
AGU25 oral talk — Tue, Dec 16, 2025, 09:42–09:52 CT (07:42–07:52 PT), Session NG21A.
Nov 2, 2025
Talk Announcement: 1W-MINDS Seminar — Learning Enhanced Ensemble Filters
I will give a 1W-MINDS seminar on Thursday, November 6, 2025 at 2:30 PM Eastern (11:30 AM Pacific).
Nov 1, 2025