Metraipolis › archive › dc_cf680151decc
LD-EnFF: Latent-Dynamics Ensemble Flow Filtering for Data Assimilation with Sparse Observations — arXiv:2610.04034
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.04034
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:30:22.290Z
- SHA-256 of the archived text
3dee640289a5b62d8d93d9d4246881fb36822f526cdc757ff03a2c2072e288c1- Stable URL of this page
https://metraipolis.com/documento/dc_cf680151decc
How to cite
LD-EnFF: Latent-Dynamics Ensemble Flow Filtering for Data Assimilation with Sparse Observations — arXiv:2610.04034 — arXiv, https://arxiv.org/abs/2610.04034 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cf680151decc (Metraipolis archive dc_cf680151decc, sha256 3dee640289a5b62d8d93d9d4246881fb36822f526cdc757ff03a2c2072e288c1)
BibTeX
@misc{dccf680151decc,
title = {LD-EnFF: Latent-Dynamics Ensemble Flow Filtering for Data Assimilation with Sparse Observations — arXiv:2610.04034},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.04034},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cf680151decc; sha256 3dee640289a5b62d8d93d9d4246881fb36822f526cdc757ff03a2c2072e288c1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04034. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Data assimilation combines model forecasts with noisy, incomplete observations to estimate the evolving state of a dynamical system. Existing methods face two compounding challenges: high-dimensional nonlinear dynamics make repeated forward simulation computationally expensive, while sparse observations provide limited direct information about the full state. To address these challenges, we propose the Latent-Dynamics Ensemble Flow Filter (LD-EnFF), a sequential Bayesian filtering framework that performs both forecast propagation and filtering updates in a compact latent space. LD-EnFF combines a latent dynamics surrogate for ensemble propagation with a variational autoencoder (VAE)-based observation model that evaluates a state-dependent observation likelihood in latent space. At each assimilation step, an ensemble filtering update based on flow matching uses the forecast ensemble and this likelihood to generate posterior samples, jointly updating latent states and uncertain parameters. This design avoids repeated full-state simulation during forecasting and full-field reconstruction during likelihood evaluation. LD-EnFF substantially outperforms a broad range of data assimilation algorithms on benchmarks spanning Kolmogorov flow, tsunami propagation, and atmospheric modeling, all featuring complex dynamics and sparse, noisy observations. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.04034 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-06T05:27:05.648Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).