Research

Paper

AI LLM March 23, 2026

Climate Prompting: Generating the Madden-Julian Oscillation using Video Diffusion and Low-Dimensional Conditioning

Authors

Sulian Thual, Feiyang Cai, Jingjing Wang, Feng Luo

Abstract

Generative Deep Learning is a powerful tool for modeling of the Madden-Julian oscillation (MJO) in the tropics, yet its relationship to traditional theoretical frameworks remains poorly understood. Here we propose a video diffusion model, trained on atmospheric reanalysis, to synthetize long MJO sequences conditioned on key low-dimensional metrics. The generated MJOs capture key features including composites, power spectra and multiscale structures including convectively coupled waves, despite some bias. We then prompt the model to generate more tractable MJOs based on intentionally idealized low-dimensional conditionings, for example a perpetual MJO, an isolated modulation by seasons and/or the El Nino-Southern Oscillation, and so on. This enables deconstructing the underlying processes and identifying physical drivers. The present approach provides a practical framework for bridging the gap between low-dimensional MJO theory and high-resolution atmospheric complexity and will help tropical atmosphere prediction.

Metadata

arXiv ID: 2603.21856
Provider: ARXIV
Primary Category: cs.CV
Published: 2026-03-23
Fetched: 2026-03-24 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.21856v1</id>\n    <title>Climate Prompting: Generating the Madden-Julian Oscillation using Video Diffusion and Low-Dimensional Conditioning</title>\n    <updated>2026-03-23T11:47:17Z</updated>\n    <link href='https://arxiv.org/abs/2603.21856v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.21856v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Generative Deep Learning is a powerful tool for modeling of the Madden-Julian oscillation (MJO) in the tropics, yet its relationship to traditional theoretical frameworks remains poorly understood. Here we propose a video diffusion model, trained on atmospheric reanalysis, to synthetize long MJO sequences conditioned on key low-dimensional metrics. The generated MJOs capture key features including composites, power spectra and multiscale structures including convectively coupled waves, despite some bias. We then prompt the model to generate more tractable MJOs based on intentionally idealized low-dimensional conditionings, for example a perpetual MJO, an isolated modulation by seasons and/or the El Nino-Southern Oscillation, and so on. This enables deconstructing the underlying processes and identifying physical drivers. The present approach provides a practical framework for bridging the gap between low-dimensional MJO theory and high-resolution atmospheric complexity and will help tropical atmosphere prediction.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <published>2026-03-23T11:47:17Z</published>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>Sulian Thual</name>\n    </author>\n    <author>\n      <name>Feiyang Cai</name>\n    </author>\n    <author>\n      <name>Jingjing Wang</name>\n    </author>\n    <author>\n      <name>Feng Luo</name>\n    </author>\n  </entry>"
}