English

Training-Free Data Assimilation with GenCast

Machine Learning 2025-10-02 v2 Atmospheric and Oceanic Physics

Abstract

Data assimilation is widely used in many disciplines such as meteorology, oceanography, and robotics to estimate the state of a dynamical system from noisy observations. In this work, we propose a lightweight and general method to perform data assimilation using diffusion models pre-trained for emulating dynamical systems. Our method builds on particle filters, a class of data assimilation algorithms, and does not require any further training. As a guiding example throughout this work, we illustrate our methodology on GenCast, a diffusion-based model that generates global ensemble weather forecasts.

Keywords

Cite

@article{arxiv.2509.18811,
  title  = {Training-Free Data Assimilation with GenCast},
  author = {Thomas Savary and François Rozet and Gilles Louppe},
  journal= {arXiv preprint arXiv:2509.18811},
  year   = {2025}
}
R2 v1 2026-07-01T05:51:45.076Z