Subseasonal Forecasts of Opportunity Identified by an Explainable Neural Network

Abstract

Midlatitude prediction on subseasonal timescales is difficult due to the chaotic nature of the atmosphere and often requires the identification of favorable atmospheric conditions that may lead to enhanced skill (“forecasts of opportunity”). Here, we demonstrate that an artificial neural network (ANN) can identify such opportunities for tropical-extratropical circulation teleconnections within the North Atlantic (40°N, 325°E) at a lead of 22 days using the network's confidence in a given prediction. Furthermore, layer-wise relevance propagation (LRP), an ANN explainability technique, pinpoints the relevant tropical features the ANN uses to make accurate predictions. We find that LRP identifies tropical hot spots that correspond to known favorable regions for midlatitude teleconnections and reveals a potential new pattern for prediction in the North Atlantic on subseasonal timescales.