Viewing Forced Climate Patterns through an AI Lens

Forced climate patterns are detected by an artificial neural network (ANN) trained on climate model simulations of annual surface temperature and precipitation. By identifying spatial patterns that serve as indicators of change, the ANN is able to determine the year from which the simulations came, without first separating the forced climate change signal from the noise of both internal climate variability and model uncertainty. Thus, the ANN indicator patterns are complex, non-linear combinations of signal and noise. The indicator patterns of temperature are identified by the ANN as early as the 1960s in climate simulations, and two decades later for precipitation. Furthermore, the ANN is able to identify the year of observed temperature and precipitation maps, demonstrating that the indicator patterns are also present in the observations. This approach suggests that viewing climate patterns through an AI lens has the power to uncover new insights into climate variability and change.