LanTu: Dynamics-Enhanced Deep Learning for Eddy-Resolving Ocean Forecasting
This work addresses the problem of high computational costs and scientific challenges in eddy-resolving ocean forecasting for applications like fisheries and navigation, representing an incremental improvement by enhancing AI models with physical dynamics.
The authors tackled the challenge of mesoscale eddy forecasting in ocean dynamics by developing LanTu, a dynamics-enhanced deep learning system that incorporates cross-scale interactions and physical constraints, resulting in outperformance of existing numerical and AI-based forecasting systems in temperature, salinity, sea level anomaly, and current predictions with a lead time of over 10 days.
Mesoscale eddies dominate the spatiotemporal multiscale variability of the ocean, and their impact on the energy cascade of the global ocean cannot be ignored. Eddy-resolving ocean forecasting is providing more reliable protection for fisheries and navigational safety, but also presents significant scientific challenges and high computational costs for traditional numerical models. Artificial intelligence (AI)-based weather and ocean forecasting systems are becoming powerful tools that balance forecast performance with computational efficiency. However, the complex multiscale features in the ocean dynamical system make AI models still face many challenges in mesoscale eddy forecasting (especially regional modelling). Here, we develop LanTu, a regional eddy-resolving ocean forecasting system based on dynamics-enhanced deep learning. We incorporate cross-scale interactions into LanTu and construct multiscale physical constraint for optimising LanTu guided by knowledge of eddy dynamics in order to improve the forecasting skill of LanTu for mesoscale evolution. The results show that LanTu outperforms the existing advanced operational numerical ocean forecasting system (NOFS) and AI-based ocean forecasting system (AI-OFS) in temperature, salinity, sea level anomaly and current prediction, with a lead time of more than 10 days. Our study highlights that dynamics-enhanced deep learning (LanTu) can be a powerful paradigm for eddy-resolving ocean forecasting.