Crowdsourcing the Frontier: Advancing Hybrid Physics‐ML Climate Simulation via a $50,000 Kaggle Competition

Journal article

Plain Language Summary: Future climate models may use machine learning (ML) to replace small‐scale physical processes that are otherwise too costly to simulate directly over long timescales. Such “hybrid” physics–ML models could improve predictions by reducing uncertainties from current approximations. But making them run reliably in full climate simulations has been a major challenge. To speed progress, scientists created an open data set, benchmarking framework, and global competition to drive improvement for these ML components. This paper follows up on that competition by testing ideas from the winning teams within hybrid climate models. For the first time, we show that stable hybrid simulation is now reproducible across a range of diverse ML architectures. We find that different architectures share similar patterns of errors both before and after coupling, although their responses to added training inputs can differ. Finally, some competition‐inspired designs achieve state‐of‐the‐art scores on individual performance measures, but no single approach beats the previous benchmark (Hu et al., 2025, https://doi.org/10.1029/2024ms004618) on every metric.

Authors: Lin, J; Hu, Z; Beucler, T; Frields, K; Christensen, H

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Wiley
• Journal: Journal of Advances in Modeling Earth Systems
• Volume: 18
• Issue: 5
• Article number: e2025MS005643
• Publication date: 2026-05-13
• Acceptance date: 2026-04-13
• DOI: 10.1029/2025ms005643
• EISSN: 1942-2466
• ISSN: 1942-2466
• Language: English
• Keywords: MMF; machine learning; superparameterization; hybrid; kaggle; physics