# Evaluating Skill and Stability of ArchesWeather and ArchesWeatherGen under Multi-Decadal Climate Simulations

arXiv: https://arxiv.org/abs/2605.29976 · HTML: https://mlsanity.com/paper/2605.29976/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 37 references that are in the map.
- First posted on arXiv 28 May 2026.

## Builds on (most cited first, 6 of 6)

- [Neural General Circulation Models for Weather and Climate](https://mlsanity.com/paper/2311.07222/) (2023)
- [WeatherBench 2: A benchmark for the next generation of data-driven global weather models](https://mlsanity.com/paper/2308.15560/) (2023)
- [Pangu-Weather: A 3D High-Resolution Model for Fast and Accurate Global Weather Forecast](https://mlsanity.com/paper/2211.02556/) (2022)
- [Skillful joint probabilistic weather forecasting from marginals](https://mlsanity.com/paper/2506.10772/) (2025)
- [ACE2: Accurately learning subseasonal to decadal atmospheric variability and forced responses](https://mlsanity.com/paper/2411.11268/) (2024)
- [LUCIE: A Lightweight Uncoupled ClImate Emulator with long-term stability and physical consistency for O(1000)-member ensembles](https://mlsanity.com/paper/2405.16297/) (2024)

## Built on by (most cited first, 1 of 1)

- [Rescene: band-limited stochastic forcing turns a frozen neural weather operator into a climate emulator](https://mlsanity.com/paper/2608.09971/) (2026)

## Abstract (arXiv)

We evaluate the climate simulation capabilities of ArchesWeather and ArchesWeatherGen, two machine learning models originally trained for weather forecasting and evaluated up to a 10-day lead time. ArchesWeather is a deterministic model, while ArchesWeatherGen is a probabilistic flow-matching model leveraging ArchesWeather's forecasts, enabling ensemble-based uncertainty quantification. In this work, we adapt these models to act as forced atmospheric models by using additional conditioning on the monthly mean sea surface temperature (SST) and sea ice cover (SIC) as boundary conditions. In particular, we follow the AI Model Intercomparison Project (AIMIP) Phase 1 protocol, which, analogous to the Atmospheric Model Intercomparison Project (AMIP), proposes a standardized experimental setup to evaluate the climate skill of ML-based forced atmospheric models. We present a comprehensive evaluation of both models under these conditions, including comparison against numerical climate models, ablation studies that examine key design choices in the extension, and an analysis of forced versus unforced configurations. Despite being originally developed for weather forecasting, we demonstrate that forced configurations of ArchesWeather and ArchesWeatherGen produce stable long-term climate simulations, have a stable annual cycle, and capture the drift of many climate variables. The models faithfully reproduce ERA5's climatology, large-scale circulations and interannual variability, and they capture the tails of the distributions.