# Robustness of AI-based weather forecasts in a changing climate

arXiv: https://arxiv.org/abs/2409.18529 · HTML: https://mlsanity.com/paper/2409.18529/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 41 references that are in the map.
- First posted on arXiv 27 Sep 2024.

## Builds on (most cited first, 9 of 9)

- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [Neural General Circulation Models for Weather and Climate](https://mlsanity.com/paper/2311.07222/) (2023)
- [Scaling transformer neural networks for skillful and reliable medium-range weather forecasting](https://mlsanity.com/paper/2312.03876/) (2023)
- [Sub-seasonal forecasting with a large ensemble of deep-learning weather prediction models](https://mlsanity.com/paper/2102.05107/) (2021)
- [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)
- [Climate-Invariant Machine Learning](https://mlsanity.com/paper/2112.08440/) (2021)
- [Dynamical Tests of a Deep-Learning Weather Prediction Model](https://mlsanity.com/paper/2309.10867/) (2023)
- [Coupled Ocean-Atmosphere Dynamics in a Machine Learning Earth System Model](https://mlsanity.com/paper/2406.08632/) (2024)
- [Leveraging data-driven weather models for improving numerical weather prediction skill through large-scale spectral nudging](https://mlsanity.com/paper/2407.06100/) (2024)

## Built on by (most cited first, 11 of 11)

- [Can AI weather models predict out-of-distribution gray swan tropical cyclones?](https://mlsanity.com/paper/2410.14932/) (2024)
- [FengWu-W2S: A deep learning model for seamless weather-to-subseasonal forecast of global atmosphere](https://mlsanity.com/paper/2411.10191/) (2024)
- [Generative assimilation and prediction for weather and climate](https://mlsanity.com/paper/2503.03038/) (2025)
- [WIND: Weather Inverse Diffusion for Zero-Shot Atmospheric Modeling](https://mlsanity.com/paper/2602.03924/) (2026)
- [Forecasting the Future with Yesterday's Climate: Temperature Bias in AI Weather and Climate Models](https://mlsanity.com/paper/2509.22359/) (2025)
- [The Equilibrium Response of Atmospheric Machine-Learning Models to Uniform Sea Surface Temperature Warming](https://mlsanity.com/paper/2510.02415/) (2025)
- [Forecasting Fails: Unveiling Evasion Attacks in Weather Prediction Models](https://mlsanity.com/paper/2512.08832/) (2025)
- [Prediction of steady states in a marine ecosystem model by a machine learning technique](https://mlsanity.com/paper/2506.10475/) (2025)
- [Robustness Test for AI Forecasting of Hurricane Florence Using FourCastNetv2 and Random Perturbations of the Initial Condition](https://mlsanity.com/paper/2512.05323/) (2025)
- [No Epoch Like the Present: Robust Climate Emulation Requires Out-of-Distribution Generalisation](https://mlsanity.com/paper/2605.22248/) (2026)
- [Artificial intelligence pathways from weather to climate](https://mlsanity.com/paper/2610.09770/) (2026)

## Abstract (arXiv)

Data-driven machine learning models for weather forecasting have made transformational progress in the last 1-2 years, with state-of-the-art ones now outperforming the best physics-based models for a wide range of skill scores. Given the strong links between weather and climate modelling, this raises the question whether machine learning models could also revolutionize climate science, for example by informing mitigation and adaptation to climate change or to generate larger ensembles for more robust uncertainty estimates. Here, we show that current state-of-the-art machine learning models trained for weather forecasting in present-day climate produce skillful forecasts across different climate states corresponding to pre-industrial, present-day, and future 2.9K warmer climates. This indicates that the dynamics shaping the weather on short timescales may not differ fundamentally in a changing climate. It also demonstrates out-of-distribution generalization capabilities of the machine learning models that are a critical prerequisite for climate applications. Nonetheless, two of the models show a global-mean cold bias in the forecasts for the future warmer climate state, i.e. they drift towards the colder present-day climate they have been trained for. A similar result is obtained for the pre-industrial case where two out of three models show a warming. We discuss possible remedies for these biases and analyze their spatial distribution, revealing complex warming and cooling patterns that are partly related to missing ocean-sea ice and land surface information in the training data. Despite these current limitations, our results suggest that data-driven machine learning models will provide powerful tools for climate science and transform established approaches by complementing conventional physics-based models.