El Niño-Southern Oscillation (ENSO) exerts global climate and societal impacts, but real-time prediction with lead times beyond one year remains challenging. Dynamical models suffer from large biases and uncertainties, while deep learning struggles with interpretability and multi-scale dynamics. Here, we introduce PTSTnet, an interpretable model that unifies dynamical processes and cross-scale spatiotemporal learning in an innovative neural-network framework with physics-encoding learning. PTSTnet produces interpretable predictions significantly outperforming state-of-the-art benchmarks with lead times beyond 24 months, providing physical insights into error propagation in ocean-atmosphere interactions. PTSTnet learns feature representations with physical consistency from sparse data to tackle inherent multi-scale and multi-physics challenges underlying ocean-atmosphere processes, thereby inherently enhancing long-term prediction skill. Our successful realizations mark substantial steps forward in interpretable insights into innovative neural ocean modelling.
View on arXiv@article{hao2025_2503.21211,
title={ Interpretable Cross-Sphere Multiscale Deep Learning Predicts ENSO Skilfully Beyond 2 Years },
author={ Rixu Hao and Yuxin Zhao and Shaoqing Zhang and Guihua Wang and Xiong Deng },
journal={arXiv preprint arXiv:2503.21211},
year={ 2025 }
}