# Dynamical Tests of a Deep-Learning Weather Prediction Model

arXiv: https://arxiv.org/abs/2309.10867 · HTML: https://mlsanity.com/paper/2309.10867/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 36 references that are in the map.
- First posted on arXiv 19 Sep 2023.

## Builds on (most cited first, 2 of 2)

- [GraphCast: Learning skillful medium-range global weather forecasting](https://mlsanity.com/paper/2212.12794/) (2022)
- [FourCastNet: Accelerating Global High-Resolution Weather Forecasting using Adaptive Fourier Neural Operators](https://mlsanity.com/paper/2208.05419/) (2022)

## Built on by (most cited first, 24 of 24)

- [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)
- [Foundation Models for the Electric Power Grid](https://mlsanity.com/paper/2407.09434/) (2024)
- [Generative Data Assimilation of Sparse Weather Station Observations at Kilometer Scales](https://mlsanity.com/paper/2406.16947/) (2024)
- [Can AI weather models predict out-of-distribution gray swan tropical cyclones?](https://mlsanity.com/paper/2410.14932/) (2024)
- [Coupled Ocean-Atmosphere Dynamics in a Machine Learning Earth System Model](https://mlsanity.com/paper/2406.08632/) (2024)
- [Huge Ensembles Part II: Properties of a Huge Ensemble of Hindcasts Generated with Spherical Fourier Neural Operators](https://mlsanity.com/paper/2408.01581/) (2024)
- [Robustness of AI-based weather forecasts in a changing climate](https://mlsanity.com/paper/2409.18529/) (2024)
- [Generative assimilation and prediction for weather and climate](https://mlsanity.com/paper/2503.03038/) (2025)
- [MAUSAM: An Observations-focused assessment of Global AI Weather Prediction Models During the South Asian Monsoon](https://mlsanity.com/paper/2509.01879/) (2025)
- [Learning to forecast diagnostic parameters using pre-trained weather embedding](https://mlsanity.com/paper/2312.00290/) (2023)
- [LUCIE-3D: A three-dimensional climate emulator for forced responses](https://mlsanity.com/paper/2509.02061/) (2025)
- [Assessing the Geographic Generalization and Physical Consistency of Generative Models for Climate Downscaling](https://mlsanity.com/paper/2510.13722/) (2025)
- [A Score Filter Enhanced Data Assimilation Framework for Data-Driven Dynamical Systems](https://mlsanity.com/paper/2603.14863/) (2026)
- [Extreme Weather Bench: A framework and benchmark for evaluation of high-impact weather](https://mlsanity.com/paper/2605.01126/) (2026)
- [Lightning-Fast Convective Outlooks: Predicting Severe Convective Environments with Global AI-based Weather Models](https://mlsanity.com/paper/2406.09474/) (2024)
- [Benchmarking atmospheric circulation variability in an AI emulator, ACE2, and a hybrid model, NeuralGCM](https://mlsanity.com/paper/2510.04466/) (2025)
- [Harnessing AI data-driven global weather models for climate attribution: An analysis of the 2017 Oroville Dam extreme atmospheric river](https://mlsanity.com/paper/2409.11605/) (2024)
- [Accelerating Quasi-Static Time Series Simulations with Foundation Models](https://mlsanity.com/paper/2411.08652/) (2024)
- [Hierarchical Testing of a Hybrid Machine Learning-Physics Global Atmosphere Model](https://mlsanity.com/paper/2602.11313/) (2026)
- [Phys-Diff: A Physics-Inspired Latent Diffusion Model for Tropical Cyclone Forecasting](https://mlsanity.com/paper/2603.00521/) (2026)
- [Missing the Butterfly and Predicting the Past: Features or Bugs of Accurate AI Weather Models?](https://mlsanity.com/paper/2608.25835/) (2026)
- [Evaluating Dynamical Fidelity through Predictive Structure in Physical Representations](https://mlsanity.com/paper/2609.34627/) (2026)
- [AI Emulation of Stochastic Sudden Stratospheric Warming with Interpretable Latent Structure](https://mlsanity.com/paper/2610.02069/) (2026)
- [Strategic Governance of AI Models in Earth Science](https://mlsanity.com/paper/2610.10560/) (2026)

## Abstract (arXiv)

Global deep-learning weather prediction models have recently been shown to produce forecasts that rival those from physics-based models run at operational centers. It is unclear whether these models have encoded atmospheric dynamics, or simply pattern matching that produces the smallest forecast error. Answering this question is crucial to establishing the utility of these models as tools for basic science. Here we subject one such model, Pangu-weather, to a set of four classical dynamical experiments that do not resemble the model training data. Localized perturbations to the model output and the initial conditions are added to steady time-averaged conditions, to assess the propagation speed and structural evolution of signals away from the local source. Perturbing the model physics by adding a steady tropical heat source results in a classical Matsuno--Gill response near the heating, and planetary waves that radiate into the extratropics. A localized disturbance on the winter-averaged North Pacific jet stream produces realistic extratropical cyclones and fronts, including the spontaneous emergence of polar lows. Perturbing the 500hPa height field alone yields adjustment from a state of rest to one of wind--pressure balance over ~6 hours. Localized subtropical low pressure systems produce Atlantic hurricanes, provided the initial amplitude exceeds about 5 hPa, and setting the initial humidity to zero eliminates hurricane development. We conclude that the model encodes realistic physics in all experiments, and suggest it can be used as a tool for rapidly testing ideas before using expensive physics-based models.