FloeNet: A mass-conserving global sea ice emulator that generalizes across climates
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912964343234560 |
|---|---|
| author | Gregory, William Bushuk, Mitchell Duncan, James Wu, Elynn Subel, Adam Clark, Spencer K. Hurlin, Bill Watt-Meyer, Oliver Adcroft, Alistair Bretherton, Chris Zanna, Laure |
| author_facet | Gregory, William Bushuk, Mitchell Duncan, James Wu, Elynn Subel, Adam Clark, Spencer K. Hurlin, Bill Watt-Meyer, Oliver Adcroft, Alistair Bretherton, Chris Zanna, Laure |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_12449 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FloeNet: A mass-conserving global sea ice emulator that generalizes across climates Gregory, William Bushuk, Mitchell Duncan, James Wu, Elynn Subel, Adam Clark, Spencer K. Hurlin, Bill Watt-Meyer, Oliver Adcroft, Alistair Bretherton, Chris Zanna, Laure Atmospheric and Oceanic Physics Machine Learning 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. |
| title | FloeNet: A mass-conserving global sea ice emulator that generalizes across climates |
| topic | Atmospheric and Oceanic Physics Machine Learning |
| url | https://arxiv.org/abs/2603.12449 |