A Hybrid Deep-Learning Model for El Niño Southern Oscillation in the Low-Data Regime
This work addresses the challenge of accurate ENSO prediction in low-data regimes for climate science, though it is incremental as it builds on existing LIM and deep-learning approaches.
The paper tackled the problem of forecasting El Niño Southern Oscillation (ENSO) with limited observational data by developing a hybrid model combining Linear Inverse Models (LIMs) and deep learning, resulting in improved skill over both LIMs and full deep-learning models for datasets of about 100 years, especially for leads beyond 9 months in the western tropical Pacific.
While deep-learning models have demonstrated skillful El Niño Southern Oscillation (ENSO) forecasts up to one year in advance, they are predominantly trained on climate model simulations that provide thousands of years of training data at the expense of introducing climate model biases. Simpler Linear Inverse Models (LIMs) trained on the much shorter observational record also make skillful ENSO predictions but do not capture predictable nonlinear processes. This motivates a hybrid approach, combining the LIMs modest data needs with a deep-learning non-Markovian correction of the LIM. For O(100 yr) datasets, our resulting Hybrid model is more skillful than the LIM while also exceeding the skill of a full deep-learning model. Additionally, while the most predictable ENSO events are still identified in advance by the LIM, they are better predicted by the Hybrid model, especially in the western tropical Pacific for leads beyond about 9 months, by capturing the subsequent asymmetric (warm versus cold phases) evolution of ENSO.