A Physical-Informed Neural Network for Improving Air-Sea Turbulent Heat Flux Parameterization

The parameterizations of air-sea turbulent heat flux are one of the major bottlenecks in atmosphere-ocean coupled model development, which play a crucial role in sea surface temperature (SST) prediction. Recently, neural networks start to be applied for the development of parameterizations of interface turbulent heat flux. However, these new parameterizations are primairily developed for specific regions and have not been tested in real atmosphere-ocean coupled models. In this study, we propose a new air-sea heat flux parameterization using a physical-informed neural network (PINN) based on multiple observational data sets worldwide. Evaluated with an independent observation data set, it is shown that the PINN can significantly reduce the RMSE of latent heat flux by at least about 48.6% compared to three traditional bulk formulas. Moreover, the PINN can be flexibly updated with new observational data by transfer learning. To test the performance of the new parameterization in realistic application, we implement the PINN into a global ocean-atmosphere coupled model and make seasonal forecasts for the first time. The PINN markedly reduce the errors of equatorial SST forecast, indicating a good performance of the PINN-based air-sea turbulent heat flux scheme. Noticeably, due to limited observational data, the NN-based parameterizations tend to underestimate heat flux at high wind speeds compared with bulk formula-based parameterizations. With more data available at extreme conditions, the PINN can be improved via transfer learning and need to be futher evaluated. This study suggests that PINN-based air-sea heat flux parameterization is promising to improve SST simulation. The air-sea turbulent heat flux plays a crucial role in advancing marine science and is the key to improving the accuracy of the sea surface temperature (SST) prediction. The traditional parameterizations for air-sea turbulent heat flux have large deviations in some circumstances and are hard to update since they are developed based on unique observation datasets. The emergence of artificial intelligence offers a fresh avenue to address this issue. In this study, we develop air-sea heat flux parameterization based on a PINN and multiple observational data sets, which measured air-sea heat fluxes directly. Our novel parameterization outperforms three bulk formula-based parameterizations in offline tests and solves the problem of unphysical result of neural networks. The new parameterization also shows great potential in improving the accuracy of SST prediction in multiple online tests. We propose a new air-sea turbulent heat flux parameterization based on physical-informed neural network (PINN) which is trained on data in situ The new scheme can accurately calculate the air-sea turbulent heat flux and perform well in a global seasonal forecast The PINN can be flexibly updated with new observational data by transfer learning