Climate Prompting: Generating the Madden-Julian Oscillation using Video Diffusion and Low-Dimensional Conditioning
This work addresses the gap between low-dimensional MJO theory and high-resolution atmospheric complexity for tropical atmosphere prediction, representing an incremental advance by applying a known method to a specific domain.
The authors tackled the problem of modeling the Madden-Julian Oscillation (MJO) by proposing a video diffusion model trained on atmospheric reanalysis to generate long MJO sequences conditioned on low-dimensional metrics, capturing key features like composites and power spectra despite some bias, and enabling deconstruction of physical drivers through idealized prompts.
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.