Training-Free Data Assimilation with GenCast
This work addresses data assimilation in fields like meteorology and robotics, offering a general approach without additional training, though it appears incremental as it builds on existing particle filters and diffusion models.
The authors tackled the problem of data assimilation for dynamical systems by proposing a lightweight, training-free method using pre-trained diffusion models, demonstrating it on GenCast for weather forecasting.
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.