Interpretable Cross-Sphere Multiscale Deep Learning Predicts ENSO Skilfully Beyond 2 Years

Email: zhaoyuxin@hrbeu.edu.cn ( Y.Z.); szhang@ouc.edu.cn ( S.Z.) Abstract: El Niñ o - 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 in terpretability 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 co nsistency 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 interpretab le insights into innovative neural ocean modelling . 2 Introduction The El Niño Southern Oscillation (ENSO) represents the main source of interannual variability in the global climate system, and the ability to predict large - scale climate variability and its impacts on global social and environmental systems is highly depe ndent on the quality of ENSO predictions ( 1 - 5) . With significant advances in ENSO observations and process understanding, considerable progress has been made in associated modelling and prediction in recent decades ( 6 - 10) .