Convolutional neural networks trained on internal variability predict forced response of TOA radiation by learning the pattern effect

Predicting forced, long-term radiative feedbacks from internal climate variability has been a decades-long quest in climate science. We train a convolutional neural network (CNN) to predict annual- and global-mean top of the atmosphere radiation anomalies from time-varying maps of near-surface temperature in climate models. Trained on internal variability alone, the nonlinear CNN can predict radiation under strong climate change, outperforms a regularized linear regression approach, and works within and across different climate models.  We show with explainable artificial intelligence methods that the CNN draws predictive skill from physically meaningful regions but at much smaller spatial scales than currently assumed.