Physics-Informed Machine Learning On Polar Ice: A Survey

TL;DR

This survey reviews physics-informed machine learning methods applied to polar ice modeling, highlighting their advantages, challenges, and future research directions in understanding ice behavior and sea-level rise.

Contribution

It provides a comprehensive taxonomy of PIML algorithms, analyzes their benefits over traditional models, and discusses future opportunities in polar ice research.

Findings

PIML improves accuracy and efficiency in ice modeling.

It combines physical models with data-driven approaches effectively.

Challenges include data scarcity and method integration.

Abstract

The mass loss of the polar ice sheets contributes considerably to ongoing sea-level rise and changing ocean circulation, leading to coastal flooding and risking the homes and livelihoods of tens of millions of people globally. To address the complex problem of ice behavior, physical models and data-driven models have been proposed in the literature. Although traditional physical models can guarantee physically meaningful results, they have limitations in producing high-resolution results. On the other hand, data-driven approaches require large amounts of high-quality and labeled data, which is rarely available in the polar regions. Hence, as a promising framework that leverages the advantages of physical models and data-driven methods, physics-informed machine learning (PIML) has been widely studied in recent years. In this paper, we review the existing algorithms of PIML, provide our own taxonomy based on the methods of combining physics and data-driven approaches, and analyze the advantages of PIML in the aspects of accuracy and efficiency. Further, our survey discusses some current challenges and highlights future opportunities, including PIML on sea ice studies, PIML with different combination methods and backbone networks, and neural operator methods.