FloeNet: A mass-conserving global sea ice emulator that generalizes across climates

2026-03-12

AI Summary

Traditional sea ice models are computationally expensive and struggle to efficiently simulate sea ice evolution across multiple climate scenarios. This work proposes FloeNet—the first globally applicable, mass-conserving machine learning emulator for sea ice—trained on 6-hourly budget data from the SIS2 model and integrating both thermodynamic and dynamic processes. By enforcing strict mass conservation, FloeNet ensures physical consistency while achieving strong generalization across diverse climate conditions. The model outputs key coupled variables, including sea ice volume, skin temperature, and salt fluxes. Evaluated against observational benchmarks, FloeNet demonstrates high skill in reproducing sea ice volume anomalies, with correlation coefficients exceeding 0.76 in the Arctic and 0.96 in the Antarctic. It significantly outperforms non-conservative emulators in capturing mean states, long-term trends, and interannual variability.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Search and Optimization: Learning to Search
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

We introduce FloeNet, a machine-learning emulator trained on the Geophysical Fluid Dynamics Laboratory global sea ice model, SIS2. FloeNet is a mass-conserving model, emulating 6-hour mass and area budget tendencies related to sea ice and snow-on-sea-ice growth, melt, and advection. We train FloeNet using simulated data from a reanalysis-forced ice-ocean simulation and test its ability to generalize to pre-industrial control and 1% CO2 climates. FloeNet outperforms a non-conservative model at reproducing sea ice and snow-on-sea-ice mean state, trends, and inter-annual variability, with volume anomaly correlations above 0.96 in the Antarctic and 0.76 in the Arctic, across all forcings. FloeNet also produces the correct thermodynamic vs dynamic response to forcing, enabling physical interpretability of emulator output. Finally, we show that FloeNet outputs high-fidelity coupling-related variables, including ice-surface skin temperature, ice-to-ocean salt flux, and melting energy fluxes. We hypothesize that FloeNet will improve polar climate processes within existing atmosphere and ocean emulators.

Problem

• sea ice emulator
• mass conservation
• climate generalization
• thermodynamic-dynamic response
• polar climate processes

Innovation

• mass-conserving
• sea ice emulator
• machine learning
• climate generalization
• thermodynamic-dynamic response