paper2026Data assimilationReview, survey or tutorialBureau of Meteorology (Australia)Colorado State University (incl. CIRA)ECMWFMax Planck Institute for MeteorologyNASANOAA (incl. GFDL, PSL, GSL, NCEP/EMC)University of Oklahoma (AI2ES)University of ReadingJournal2026-04-23051Apr 2026Rossella Arcucci, S. Healy, S. Dance et al.npj Artificial IntelligenceBureau of Meteorology (Australia), Colorado State University (incl. CIRA), ECMWF, Max Planck Institute for Meteorology, NASA, NOAA (incl. GFDL, PSL, GSL, NCEP/EMC), University of Oklahoma (AI2ES), University of ReadingReview arguing machine learning and data assimilation are converging, with ML accelerating DA and DA supplying uncertainty quantification and physical constraints.
The convergence of machine learning and data assimilation in Earth system science
Rossella Arcucci, S. Healy, S. Dance, L. Lei, Eviatar Bach, Anthony T. Weaver, T. Miyoshi, M. E. Dillon, C. Draper, Rochelle Schneider, S. Lang, P. Dueben et al.
npj Artificial Intelligence ·
· Bureau of Meteorology (Australia), Colorado State University (incl. CIRA), ECMWF, Max Planck Institute for Meteorology, NASA, NOAA (incl. GFDL, PSL, GSL, NCEP/EMC), University of Oklahoma (AI2ES), University of Reading
In one sentence. Review arguing machine learning and data assimilation are converging, with ML accelerating DA and DA supplying uncertainty quantification and physical constraints.
Abstract
Abstract 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.
