📝 SummarXiv

Abstract

Machine learning (ML) has achieved remarkable success in climate and marine science. Given that greenhouse warming fundamentally reshapes ocean conditions such as stratification, circulation patterns and eddy activity, evaluating the climate adaptability of the ML model is crucial. While physical constraints have been shown to enhance the performance of ML models, kinetic energy (KE) cascade has not been used as a constraint despite its importance in regulating multi-scale ocean motions. Here we develop two sea surface height (SSH) prediction models (with and without KE cascade constraint) and quantify their climate adaptability at the Kuroshio Extension. Our results demonstrate that both models exhibit only slight performance degradation under greenhouse warming conditions. Incorporating the KE cascade as a physical constraint significantly improve the model performance, reducing eddy kinetic energy errors by 14.7% in the present climate and 15.9% under greenhouse warming. This work presents the first application of the kinetic energy (KE) cascade as a physical constraint for ML based ocean state prediction and demonstrates its robust adaptability across climates, offering guidance for the further development of global ML models for both present and future conditions.