ResoNet: Robust and Explainable ENSO Forecasts with Hybrid Convolution and Transformer Networks
This work addresses skepticism about deep learning reliability and interpretability in climate science, specifically for ENSO forecasting, by providing a robust and explainable model that could encourage broader AI applications in climate prediction.
The authors tackled the problem of unreliable and uninterpretable deep learning predictions for El Niño-Southern Oscillation (ENSO) by proposing ResoNet, a hybrid CNN-Transformer model that robustly predicts ENSO up to 26 months ahead, outperforming existing methods in forecast horizon, and explains predictions using physically reasonable mechanisms like the Recharge Oscillator.
Recent studies have shown that deep learning (DL) models can skillfully predict the El Niño-Southern Oscillation (ENSO) forecasts over 1.5 years ahead. However, concerns regarding the reliability of predictions made by DL methods persist, including potential overfitting issues and lack of interpretability. Here, we propose ResoNet, a DL model that combines convolutional neural network (CNN) and Transformer architectures. This hybrid architecture design enables our model to adequately capture local SSTA as well as long-range inter-basin interactions across oceans. We show that ResoNet can robustly predict ESNO at lead times between 19 and 26 months, thus outperforming existing approaches in terms of the forecast horizon. According to an explainability method applied to ResoNet predictions of El Niño and La Niña events from 1- to 18-month lead, we find that it predicts the Niño3.4 index based on multiple physically reasonable mechanisms, such as the Recharge Oscillator concept, Seasonal Footprint Mechanism, and Indian Ocean capacitor effect. Moreover, we demonstrate that for the first time, the asymmetry between El Niño and La Niña development can be captured by ResoNet. Our results could help alleviate skepticism about applying DL models for ENSO prediction and encourage more attempts to discover and predict climate phenomena using AI methods.