FlowDAS uses stochastic interpolants to learn step-by-step transition dynamics and conditions each step on observations, beating diffusion, neural operator, and model-driven data assimilation baselines on Lorenz-63, Navier-Stokes, and SEVIR weather tasks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SP 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FlowDAS: A Stochastic Interpolant-based Framework for Data Assimilation
FlowDAS uses stochastic interpolants to learn step-by-step transition dynamics and conditions each step on observations, beating diffusion, neural operator, and model-driven data assimilation baselines on Lorenz-63, Navier-Stokes, and SEVIR weather tasks.