Prediction of Sea Ice Velocity and Concentration in the Arctic Ocean using Physics-informed Neural Network
This work addresses the need for more generalizable and physically consistent sea ice predictions for climate research and Arctic monitoring, representing an incremental improvement over fully data-driven methods.
The study tackled the problem of predicting sea ice velocity and concentration in the Arctic Ocean by developing a physics-informed neural network (PINN) that integrates physical knowledge into machine learning models, resulting in improved daily predictions, especially with small training samples and in challenging conditions like melting seasons and fast-moving ice regions.
As an increasing amount of remote sensing data becomes available in the Arctic Ocean, data-driven machine learning (ML) techniques are becoming widely used to predict sea ice velocity (SIV) and sea ice concentration (SIC). However, fully data-driven ML models have limitations in generalizability and physical consistency due to their excessive reliance on the quantity and quality of training data. In particular, as Arctic sea ice entered a new phase with thinner ice and accelerated melting, there is a possibility that an ML model trained with historical sea ice data cannot fully represent the dynamically changing sea ice conditions in the future. In this study, we develop physics-informed neural network (PINN) strategies to integrate physical knowledge of sea ice into the ML model. Based on the Hierarchical Information-sharing U-net (HIS-Unet) architecture, we incorporate the physics loss function and the activation function to produce physically plausible SIV and SIC outputs. Our PINN model outperforms the fully data-driven model in the daily predictions of SIV and SIC, even when trained with a small number of samples. The PINN approach particularly improves SIC predictions in melting and early freezing seasons and near fast-moving ice regions.