The convergence of machine learning and data assimilation in Earth system science
Rossella Arcucci·Nico Caltabiano·Sarah Dance·Lili Lei·Eviatar Bach·Anthony Weaver·Takemasa Miyoshi·María Eugenia Dillon·Clara Draper·Rochelle Schneider·Simon Lang·Peter Dueben·Niels Bormann·Peter Lean·Alan Geer·Massimo Bonavita·Peter Jan van Leeuwen·Sibo Cheng·Marc Bocquet·Nedjeljka Žagar·Haroldo Fraga de Campos Velho·Juan José Ruiz·Peter Bauer·Sid‐Ahmed Boukabara·Alberto Carrassi·Russ Treadon·Andrew Collard·Daryl Kleist·Azadeh Gholoubi·Xuguang Wang·Nahidul Samrat·Gemma Ralton·Andrew M. Moore·Katia Lamer·Sean Healy
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 increa