# Atmospheric Predictability Beyond 30 Days with Machine Learning

arXiv: https://arxiv.org/abs/2504.20238 · HTML: https://mlsanity.com/paper/2504.20238/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 62 references that are in the map.
- First posted on arXiv 28 Apr 2025.

## Builds on (most cited first, 10 of 10)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [WeatherBench 2: A benchmark for the next generation of data-driven global weather models](https://mlsanity.com/paper/2308.15560/) (2023)
- [Exploring the Space of Adversarial Images](https://mlsanity.com/paper/1510.05328/) (2015)
- [Advancing Parsimonious Deep Learning Weather Prediction using the HEALPix Mesh](https://mlsanity.com/paper/2311.06253/) (2023)
- [A Practical Probabilistic Benchmark for AI Weather Models](https://mlsanity.com/paper/2401.15305/) (2024)
- [Do AI models produce better weather forecasts than physics-based models? A quantitative evaluation case study of Storm Ciar'an](https://mlsanity.com/paper/2312.02658/) (2023)
- [Adversarial Perturbations Are Not So Weird: Entanglement of Robust and Non-Robust Features in Neural Network Classifiers](https://mlsanity.com/paper/2102.05110/) (2021)

## Built on by (most cited first, 5 of 5)

- [The Recipe Matters More Than the Kitchen:Mathematical Foundations of the AI Weather Prediction Pipeline](https://mlsanity.com/paper/2604.01215/) (2026)
- [Weather Emulators at the Frontier of Heat Extremes Predictability](https://mlsanity.com/paper/2607.28220/) (2026)
- [Learning to Forecast Crop Growth from Earth Observation Data](https://mlsanity.com/paper/2608.14281/) (2026)
- [Missing the Butterfly and Predicting the Past: Features or Bugs of Accurate AI Weather Models?](https://mlsanity.com/paper/2608.25835/) (2026)
- [Artificial intelligence pathways from weather to climate](https://mlsanity.com/paper/2610.09770/) (2026)

## Abstract (arXiv)

Atmospheric predictability research has long held that rapid error growth at small spatial scales imposes an intrinsic limit of roughly two weeks on deterministic weather forecast skill. We challenge this limit using GraphCast, a machine-learning weather model, by optimizing initial conditions for twice-daily forecasts spanning 2020. This approach yields an average error reduction of 86% at ten days relative to control forecasts from reanalysis initial conditions, with skill lasting beyond 30 days. Mean optimal initial-condition perturbations reveal large-scale, spatially coherent corrections primarily reflecting an intensification of the Hadley circulation. Forecasts using GraphCast-optimal initial conditions in the Pangu-Weather model achieve a 21% error reduction, peaking at four days, indicating that analysis corrections reflect adjustments that target both model and analysis error. These results demonstrate the existence of initial conditions producing skillful deterministic forecasts far beyond two weeks. Whether such initial conditions can be identified in real-time for improving operational weather forecasts remains a topic of future research.