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

2026-03-23

AI Summary

This study addresses the complex genesis mechanisms of the Madden–Julian Oscillation (MJO) in the tropical atmosphere, which have proven difficult to reconcile with high-dimensional observational data using traditional theoretical frameworks. To bridge this gap, the work introduces— for the first time in climate modeling—a conditional video diffusion model trained on atmospheric reanalysis data. By embedding low-dimensional climate indices, such as seasonal phase and ENSO state, as conditioning prompts, the model enables idealized generation and controllable simulation of the MJO’s multiscale structure. The synthesized MJO sequences faithfully reproduce key statistical features of observations, including convectively coupled wave structures, spectral power distributions, and spatial evolution patterns, thereby establishing a robust link between simplified theoretical constructs and high-dimensional empirical data.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Generation

Application Category

• Web Mining and Content Analysis: Web data generation and simulation
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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.

Problem

• Madden-Julian Oscillation
• generative deep learning
• low-dimensional conditioning
• tropical atmosphere
• physical drivers

Innovation

• video diffusion
• low-dimensional conditioning
• Madden-Julian Oscillation
• generative modeling
• climate prompting