Prediction of Sea Ice Velocity and Concentration in the Arctic Ocean using Physics-informed Neural Network

TL;DR

This paper introduces a physics-informed neural network model that integrates physical laws into machine learning to improve the prediction of sea ice velocity and concentration in the Arctic, especially under changing conditions.

Contribution

The study develops a novel PINN model based on HIS-Unet architecture that enhances sea ice predictions by incorporating physical knowledge, outperforming traditional data-driven models.

Findings

PINN model outperforms fully data-driven models in SIV and SIC predictions.

Significant improvement in SIC predictions during melting and freezing seasons.

Model performs well with limited training data.

Abstract

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.