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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: De Cillis, Giovanni, Carrassi, Alberto, Brajard, Julien, Bertino, Laurent, Broccoli, Matteo, Iovino, Dorotea, Finn, Tobias Sebastian, Bocquet, Marc
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914461754851328
author De Cillis, Giovanni
Carrassi, Alberto
Brajard, Julien
Bertino, Laurent
Broccoli, Matteo
Iovino, Dorotea
Finn, Tobias Sebastian
Bocquet, Marc
author_facet De Cillis, Giovanni
Carrassi, Alberto
Brajard, Julien
Bertino, Laurent
Broccoli, Matteo
Iovino, Dorotea
Finn, Tobias Sebastian
Bocquet, Marc
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_23190
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Hybrid physics-data-driven modeling for sea ice thermodynamics and transfer learning
De Cillis, Giovanni
Carrassi, Alberto
Brajard, Julien
Bertino, Laurent
Broccoli, Matteo
Iovino, Dorotea
Finn, Tobias Sebastian
Bocquet, Marc
Atmospheric and Oceanic Physics
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.
title Hybrid physics-data-driven modeling for sea ice thermodynamics and transfer learning
topic Atmospheric and Oceanic Physics
url https://arxiv.org/abs/2601.23190