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

2025-10-20

AI Summary

To address the poor generalizability and physical inconsistency of purely data-driven models in Arctic sea ice velocity and concentration forecasting, this paper proposes a physics-informed neural network method. We innovatively embed sea ice dynamics and thermodynamics into a Hierarchical Information-sharing U-Net (HIS-Unet) architecture, enforcing physical consistency via a physics-constrained loss function and custom activation functions that implicitly encode domain knowledge. The method significantly improves prediction reliability in data-sparse regions and extreme regimes—including melt season, freeze-up onset, and rapidly moving ice zones—while outperforming purely data-driven baselines under low-data conditions. Specifically, sea ice concentration prediction accuracy improves by 12.7% in RMSE. Moreover, the approach mitigates model reliance on historical climate states and enhances adaptability to thin-ice dynamics under future warming scenarios.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Low Level & Physics-based Vision
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

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.

Problem

• Predicting Arctic sea ice velocity and concentration using machine learning
• Improving physical consistency in sea ice modeling with limited data
• Addressing limitations of data-driven models in changing Arctic conditions

Innovation

• Physics-informed neural network predicts sea ice velocity
• Integrates physical knowledge into machine learning model
• Uses physics loss and activation functions for accuracy