Score-based Data Assimilation for a Two-Layer Quasi-Geostrophic Model
This work addresses data assimilation for geoscientists dealing with high-dimensional systems, but it appears incremental as it modifies an existing method for a specific model.
The paper tackled the challenge of high-dimensional data assimilation in geophysical systems by proposing modifications to a score-based method to reduce memory and time usage, demonstrating promising results on a two-layer quasi-geostrophic model.
Data assimilation addresses the problem of identifying plausible state trajectories of dynamical systems given noisy or incomplete observations. In geosciences, it presents challenges due to the high-dimensionality of geophysical dynamical systems, often exceeding millions of dimensions. This work assesses the scalability of score-based data assimilation (SDA), a novel data assimilation method, in the context of such systems. We propose modifications to the score network architecture aimed at significantly reducing memory consumption and execution time. We demonstrate promising results for a two-layer quasi-geostrophic model.