AI RESEARCH

DAISI: Data Assimilation with Inverse Sampling using Stochastic Interpolants

arXiv CS.LG

ArXi:2512.00252v3 Announce Type: replace-cross Data assimilation (DA) is a cornerstone of scientific and engineering applications, combining model forecasts with sparse and noisy observations to estimate latent system states. Classical high-dimensional DA methods, such as the ensemble Kalman filter, rely on Gaussian approximations that are violated for complex dynamics or observation operators. To address this limitation, we