Rescene: stable century-long climate emulation from a frozen weather model
Abstract
Machine-learning weather models now match or exceed operational numerical prediction in the medium range, but when they are run freely for years they drift, blow up or lose their variability, and dedicated climate emulators are expensive to train. Here we present Rescene, a 0.4 M-parameter wrapper that turns a frozen 1.5∘, 6-hourly, 69-variable weather model into a stochastic climate emulator. A deterministic slow clock anchors the frozen model to a calendar climatology, and a band-limited AR(1) perturbation, whose spectral envelope is fixed to the observed anomaly spectrum, restores the weather that anchoring removes. A 100-year, 8-member Rescene run shows no detectable drift (−0.004 ± 0.014 K per 100 years), and on the 2022 test year the 16-member ensemble is calibrated (spread/skill 0.89, 0.97 and 0.93 for Z500, T2m and MSLP) with an extratropical synoptic amplitude of 97% of ERA5 on the tuning year. The free run reproduces the geography of day-to-day variability (pattern correlation 0.83 for Z500) and 71% of the observed blocking frequency, where the deterministic wrapper alone has none. Interventions on the frozen operator show a scale-local, approximately linear response in which Z500 perturbations grow upscale 6--14 times more than downscale per 6 h. All constants are fitted on a training year against a rule declared beforehand, and we show that common evaluation shortcuts would have overstated variability and skill. Rescene makes an existing weather model usable for century-long ensembles at negligible training cost.
Related
- Skillful Seasonal Tropical Cyclone Prediction with AI Weather--Climate Models Forced by Dynamically Predicted SSTs
- EC-EarthFlow: Probabilistic emulation of daily transient global climate model simulations with flow matching
- Variable Masking for Climate Emulation in ACE
- Climate Sensitivity from 21st-Century Trends in Earth's Energy Imbalance
- Impact of climate change on the photovoltaic power potential in Sweden across 21st century
BibTeX
@misc{cheon2026rescene,
title = {{Rescene: stable century-long climate emulation from a frozen weather model}},
author = {Minjong Cheon},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2608.09971},
eprint = {2608.09971},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.09971},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - Rescene: stable century-long climate emulation from a frozen weather model
AU - Minjong Cheon
PY - 2026
DA - 2026/10/14
PB - arXiv
DO - 10.48550/arxiv.2608.09971
UR - https://arxiv.org/abs/2608.09971
AB - Machine-learning weather models now match or exceed operational numerical prediction in the medium range, but when they are run freely for years they drift, blow up or lose their variability, and dedicated climate emulators are expensive to train. Here we present Rescene, a 0.4 M-parameter wrapper that turns a frozen 1.5^∘, 6-hourly, 69-variable weather model into a stochastic climate emulator. A deterministic slow clock anchors the frozen model to a calendar climatology, and a band-limited AR(1) perturbation, whose spectral envelope is fixed to the observed anomaly spectrum, restores the weather that anchoring removes. A 100-year, 8-member Rescene run shows no detectable drift (−0.004 ± 0.014 K per 100 years), and on the 2022 test year the 16-member ensemble is calibrated (spread/skill 0.89, 0.97 and 0.93 for Z500, T2m and MSLP) with an extratropical synoptic amplitude of 97% of ERA5 on the tuning year. The free run reproduces the geography of day-to-day variability (pattern correlation 0.83 for Z500) and 71% of the observed blocking frequency, where the deterministic wrapper alone has none. Interventions on the frozen operator show a scale-local, approximately linear response in which Z500 perturbations grow upscale 6--14 times more than downscale per 6 h. All constants are fitted on a training year against a rule declared beforehand, and we show that common evaluation shortcuts would have overstated variability and skill. Rescene makes an existing weather model usable for century-long ensembles at negligible training cost.
ER -