Hybrid physics-data-driven modeling for sea ice thermodynamics and transfer learning

TL;DR

This paper develops a hybrid physics-data-driven model for sea ice thermodynamics using neural networks, demonstrating improved forecast accuracy, transfer learning capabilities, and insights into key physical variables.

Contribution

It introduces a neural network-based hybrid approach for sea-ice modeling, evaluates transfer learning for model updates, and analyzes feature importance for physical understanding.

Findings

Hybrid models outperform climatological benchmarks in forecast accuracy.

Pretrained neural networks can be adapted to new configurations via transfer learning.

Atmospheric forcing inputs have minimal impact on neural network predictive skill.

Abstract

This study explores a physics-data driven hybrid approach for sea-ice column physics models, in which a machine learning (ML) component acts as a state-dependent parameterization of forecast errors. We examine how perturbations in snow thermodynamics and sea-ice radiative properties affect forecast errors, and train dedicated neural networks (NNs) for each model configuration. The performance of the hybrid models is evaluated for long lead-time forecasts and compared against a benchmark system based on climatological forecast-error estimates. The NN-based hybrids prove to be stable, robust to initial condition and atmospheric forcing errors, and consistently outperform their climatology-based counterpart. To derive guiding principles for efficiently handling possible physical model updates, we perform transfer learning experiments to test whether pretrained NNs optimized for one model configuration can be successfully adapted to another. Results indicate that direct evaluation of pretrained networks on the target task provides useful insights into their adaptability, recommending transfer learning whenever performance exceeds a trivial baseline. Finally, a feature-importance analysis shows that atmospheric forcing inputs have negligible influence on NN predictive skill, while ice-layer enthalpies play a key role in achieving satisfactory performance.