|国家预印本平台
首页|Generative Lagrangian data assimilation for ocean dynamics under extreme sparsity

Generative Lagrangian data assimilation for ocean dynamics under extreme sparsity

Generative Lagrangian data assimilation for ocean dynamics under extreme sparsity

来源:Arxiv_logoArxiv
英文摘要

Reconstructing ocean dynamics from observational data is fundamentally limited by the sparse, irregular, and Lagrangian nature of spatial sampling, particularly in subsurface and remote regions. This sparsity poses significant challenges for forecasting key phenomena such as eddy shedding and rogue waves. Traditional data assimilation methods and deep learning models often struggle to recover mesoscale turbulence under such constraints. We leverage a deep learning framework that combines neural operators with denoising diffusion probabilistic models (DDPMs) to reconstruct high-resolution ocean states from extremely sparse Lagrangian observations. By conditioning the generative model on neural operator outputs, the framework accurately captures small-scale, high-wavenumber dynamics even at $99\%$ sparsity (for synthetic data) and $99.9\%$ sparsity (for real satellite observations). We validate our method on benchmark systems, synthetic float observations, and real satellite data, demonstrating robust performance under severe spatial sampling limitations as compared to other deep learning baselines.

Niloofar Asefi、Leonard Lupin-Jimenez、Tianning Wu、Ruoying He、Ashesh Chattopadhyay

计算技术、计算机技术遥感技术

Niloofar Asefi,Leonard Lupin-Jimenez,Tianning Wu,Ruoying He,Ashesh Chattopadhyay.Generative Lagrangian data assimilation for ocean dynamics under extreme sparsity[EB/OL].(2025-07-09)[2025-07-20].https://arxiv.org/abs/2507.06479.点此复制

评论