Diffusion Models Bridge Deep Learning and Physics in ENSO Forecasting
Abstract
Accurate long-range forecasting of the El \Nino-Southern Oscillation (ENSO) is vital for global climate prediction and disaster risk management. Yet, limited understanding of ENSO's physical mechanisms constrains both numerical and deep learning approaches, which often struggle to balance predictive accuracy with physical interpretability. Here, we introduce a data driven model for ENSO prediction based on conditional diffusion model. By constructing a probabilistic mapping from historical to future states using higher-order Markov chain, our model explicitly quantifies intrinsic uncertainty. The approach achieves extending lead times of state-of-the-art methods, resolving early development signals of the spring predictability barrier, and faithfully reproducing the spatiotemporal evolution of historical extreme events. The most striking implication is that our analysis reveals that the reverse diffusion process inherently encodes the classical recharge-discharge mechanism, with its operational dynamics exhibiting remarkable consistency with the governing principles of the van der Pol oscillator equation. These findings establish diffusion models as a new paradigm for ENSO forecasting, offering not only superior probabilistic skill but also a physically grounded theoretical framework that bridges data-driven prediction with deterministic dynamical systems, thereby advancing the study of complex geophysical processes.
Cite
@article{arxiv.2511.01214,
title = {Diffusion Models Bridge Deep Learning and Physics in ENSO Forecasting},
author = {Weifeng Xu and Xiang Zhu and Xiaoyong Li and Qiang Yao and Xiaoli Ren and Kefeng Deng and Song Wu and Chengcheng Shao and Xiaolong Xu and Juan Zhao and Chengwu Zhao and Jianping Cao and Jingnan Wang and Wuxin Wang and Qixiu Li and Xiaori Gao and Xinrong Wu and Huizan Wang and Xiaoqun Cao and Weiming Zhang and Junqiang Song and Kaijun Ren},
journal= {arXiv preprint arXiv:2511.01214},
year = {2025}
}