Explaining the high skill of reservoir computing methods in El Niño prediction

Accurate prediction of the extreme phases of the El Niño–Southern Oscillation (ENSO) is important to mitigate the socioeconomic impacts of this phenomenon. It has long been thought that prediction skill was limited to a 6-month lead time. However, machine learning methods have shown to have skill at lead times of up to 21 months. In this paper, we aim to explain for one class of such methods, i.e. reservoir computers (RCs), the origin of this high skill. Using a conditional nonlinear optimal perturbation (CNOP) approach, we compare the initial error propagation in a deterministic Zebiak–Cane (ZC) ENSO model and that in an RC trained on synthetic observations derived from a stochastic ZC model. Optimal initial perturbations at long lead times in the RC involve both sea surface temperature and thermocline anomalies, which leads to decreased error propagation compared to the ZC model, where mainly thermocline anomalies dominate the optimal initial perturbations. This reduced error propagation allows the RC to provide a higher skill at long lead times than the deterministic ZC model.