Improving Tropical Cyclone Forecasting With Video Diffusion Models

TL;DR

This paper introduces a novel video diffusion model approach for tropical cyclone forecasting that captures long-term dynamics and improves forecast horizon and accuracy over previous methods.

Contribution

The paper presents a new application of video diffusion models with a two-stage training strategy for better long-term cyclone forecasting.

Findings

Outperforms previous methods with 19.3% lower MAE

Extends forecast horizon from 36 to 50 hours

Produces more temporally coherent forecasts

Abstract

Tropical cyclone (TC) forecasting is crucial for disaster preparedness and mitigation. While recent deep learning approaches have shown promise, existing methods often treat TC evolution as a series of independent frame-to-frame predictions, limiting their ability to capture long-term dynamics. We present a novel application of video diffusion models for TC forecasting that explicitly models temporal dependencies through additional temporal layers. Our approach enables the model to generate multiple frames simultaneously, better capturing cyclone evolution patterns. We introduce a two-stage training strategy that significantly improves individual-frame quality and performance in low-data regimes. Experimental results show our method outperforms the previous approach of Nath et al. by 19.3% in MAE, 16.2% in PSNR, and 36.1% in SSIM. Most notably, we extend the reliable forecasting horizon from 36 to 50 hours. Through comprehensive evaluation using both traditional metrics and Fr\'echet Video Distance (FVD), we demonstrate that our approach produces more temporally coherent forecasts while maintaining competitive single-frame quality. Code accessible at https://github.com/Ren-creater/forecast-video-diffmodels.