Explore the ideology of deep learning in ENSO forecasts
- 1State Key Laboratory of Physical Oceanography, Ocean University of China
- 2Frontier Science Center for Deep Ocean Multispheres and Earth System, Ocean University of China
Abstract
The El Niño–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.
Related
- Learning joint probabilistic weather forecasts from station observations alone
- Improving flood forecasts: the combined impact of data assimilation and machine learning post-processing
- Anatomy of the Indian summer monsoon and ENSO relationship in a state-of-the-art CGCM: role of the tropical Atlantic Ocean
- The relation of ENSO with global surface temperature
- Recent strengthening of eastern Pacific ENSO in the last millennium paleorecord
BibTeX
@article{gan2026explore,
title = {{Explore the ideology of deep learning in ENSO forecasts}},
author = {Yanhai Gan and Yipeng Chen and Ning Li and Xingguo Liu and Junyu Dong and Xianyao Chen},
journal = {Geoscience Letters},
year = {2026},
month = oct,
doi = {10.1186/s40562-026-00504-y},
url = {https://doi.org/10.1186/s40562-026-00504-y},
note = {CC BY},
}
RIS
TY - JOUR
TI - Explore the ideology of deep learning in ENSO forecasts
AU - Yanhai Gan
AU - Yipeng Chen
AU - Ning Li
AU - Xingguo Liu
AU - Junyu Dong
AU - Xianyao Chen
PY - 2026
DA - 2026/10/25
JO - Geoscience Letters
DO - 10.1186/s40562-026-00504-y
UR - https://doi.org/10.1186/s40562-026-00504-y
AB - The El Niño–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.
SN - 2196-4092
ER -