Explore the Ideology of Deep Learning in ENSO Forecasts

TL;DR

This paper introduces an interpretability framework for deep learning models in ENSO forecasting, revealing key oceanic influences and analyzing the Spring Predictability Barrier to improve long-term predictions.

Contribution

It presents a mathematically grounded interpretability method that enhances model capacity and aligns deep learning insights with physical climate understanding.

Findings

ENSO predictability mainly from tropical Pacific

Contributions from Indian and Atlantic Oceans confirmed

Spring Predictability Barrier persists despite increased sensitivity

Abstract

The El Ni{~n}o-Southern Oscillation (ENSO) exerts profound influence on global climate variability, yet its prediction remains a grand challenge. Recent advances in deep learning have significantly improved forecasting skill, but the opacity of these models hampers scientific trust and operational deployment. Here, we introduce a mathematically grounded interpretability framework based on bounded variation function. By rescuing the "dead" neurons from the saturation zone of the activation function, we enhance the model's expressive capacity. Our analysis reveals that ENSO predictability emerges dominantly from the tropical Pacific, with contributions from the Indian and Atlantic Oceans, consistent with physical understanding. Controlled experiments affirm the robustness of our method and its alignment with established predictors. Notably, we probe the persistent Spring Predictability Barrier (SPB), finding that despite expanded sensitivity during spring, predictive performance declines-likely due to suboptimal variable selection. These results suggest that incorporating additional ocean-atmosphere variables may help transcend SPB limitations and advance long-range ENSO prediction.