The convergence of machine learning and data assimilation in Earth system science

Arcucci, R., Healy, S., Dance, S. ORCID: https://orcid.org/0000-0003-1690-3338, Lei, L., Bach, E. ORCID: https://orcid.org/0000-0002-9725-0203, Weaver, A. T., Miyoshi, T., Eugenia Dillon, M., Draper, C., Schneider, R., Lang, S., Dueben, P., Bormann, N., Lean, P., Geer, A., Bonavita, M., Jan van Leeuwen, P., Cheng, S., Bocquet, M., Zagar, N., Fraga de Campos Velho, H., Jose Ruiz, J., Bauer, P., Ahmed Boukabara, S., Carrassi, A. ORCID: https://orcid.org/0000-0003-0722-5600, Treadon, R., Collard, A., Kleist, D., Gholoubi, A., Wang, X., Samrat, N., Ralton, G., Moore, A. M., Lamer, K. and Caltabiano, N. (2026) The convergence of machine learning and data assimilation in Earth system science. npj Artificial Intelligence, 2. 48. ISSN 3005-1460 doi: 10.1038/s44387-026-00107-0

Abstract/Summary

Data assimilation (DA) combines observations with numerical models to estimate evolving Earth system states for forecasting and monitoring. Machine learning (ML) enables surrogate modeling, pattern recognition and Bayesian inference. These fields are converging: ML accelerates DA, while DA provides uncertainty quantification and physical constraints. Hybrid DA-ML systems are promising, yet challenges persist in generalization, consistency and reproducibility. These approaches are increasingly integrated, shaping next-generation prediction systems and observing networks.

Item Type	Article
URI	https://centaur.reading.ac.uk/id/eprint/129498
Identification Number/DOI	10.1038/s44387-026-00107-0
Refereed	Yes
Divisions	Science > School of Mathematical, Physical and Computational Sciences > National Centre for Earth Observation (NCEO) Interdisciplinary Research Centres (IDRCs) > Centre for the Mathematics of Planet Earth (CMPE) Science > School of Mathematical, Physical and Computational Sciences > Department of Mathematics and Statistics Science > School of Mathematical, Physical and Computational Sciences > Department of Meteorology
Publisher	Springer
Download/View statistics	View download statistics for this item