Physically consistent global atmospheric data assimilation with machine learning in latent space
Science Advances · 02.01.2026 · 12 (1)
DOI: 10.1126/sciadv.aea4248 ↗Kurz gefasst
Fachartikel in der Zeitschrift Science Advances, erschienen am 02.01.2026. Verfasst von Hang Fan und 8 weiteren Autor:innen. Beteiligte Einrichtung: Shanghai Artificial Intelligence Laboratory, Shanghai, China. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 69 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: National Science Foundation, H2020 European Research Council.
Abstract (Originalsprache)
Data assimilation (DA) integrates observations with model forecasts to produce optimized atmospheric states, whose physical consistency is critical for stable weather forecasting and reliable climate research. Traditional Bayesian DA methods enforce these nonlinear, flow-dependent physical constraints through empirical and tunable covariance structures, but with limited accuracy and robustness. Here, we introduce latent DA (LDA), a framework that performs Bayesian DA in a latent space learned from multivariate global atmospheric data via an autoencoder. We demonstrate that the autoencoder can largely capture nonlinear physical relationships, enabling LDA to produce balanced analyses without explicitly modeling physical constraints. Assimilation in latent space also improves both analysis quality and forecast skill compared to traditional model-space DA, under both idealized and real observational settings. Furthermore, LDA exhibits strong robustness across latent dimensions and remains effective even when the autoencoder is trained on inaccurate but physically realistic forecasts, highlighting its flexibility for real-world applications.
Autor:innen und Institutionen
- Shanghai Artificial Intelligence Laboratory, Shanghai, China.
- Department of Earth and Environmental Engineering, Columbia University, New York, NY, USA.
- Learning the Earth with Artificial intelligence and Physics (LEAP) Center, Columbia University, New York, NY, USA.
- Nanjing University of Information Science and Technology, Nanjing, China.
- The Chinese University of Hong Kong, Hong Kong, China.
ORCID-Profile: Hang Fan, Lei Bai, Ben Fei, Yubao Liu, Yongquan Qu, Fenghua Ling, Pierre Gentine
Förderung
- National Science Foundation
- H2020 European Research Council
Zitieren
APA
Fan, H., Bai, L., Fei, B., Xiao, Y., Chen, K., Liu, Y., Qu, Y., Ling, F., & Gentine, P. (2026). Physically consistent global atmospheric data assimilation with machine learning in latent space. Science Advances, 12(1). https://doi.org/10.1126/sciadv.aea4248
Vancouver
Fan H, Bai L, Fei B, Xiao Y, Chen K, Liu Y, et al. Physically consistent global atmospheric data assimilation with machine learning in latent space. Science Advances. 2026;12(1). doi:10.1126/sciadv.aea4248
BibTeX
@article{Fan2026,
author = {Fan, Hang and Bai, Lei and Fei, Ben and Xiao, Yi and Chen, Kun and Liu, Yubao and Qu, Yongquan and Ling, Fenghua and Gentine, Pierre},
title = {Physically consistent global atmospheric data assimilation with machine learning in latent space},
journal = {Science Advances},
year = {2026},
volume = {12},
number = {1},
doi = {10.1126/sciadv.aea4248}
}
EUVIMED