How can AI improve weather and climate prediction?
AI methods are rapidly taking hold in almost any aspect of our lives. In some specialized application areas, computers are outperforming humans with respect to image or audio analysis, speech recognition, and controlled movements. Nevertheless, weather and climate prediction still uses humongous computer codes, which solve thousands of differential equations on the fastest supercomputers. Everywhere along the workflow of such prediction systems researchers are trying out how AI could transform or even revolutionize weather and climate forecasting. While there are some promising research pathways, several scientific and technical challenges have to be overcome before we might see a widespread adaptation of such methods in weather centres and research organisations. I will discuss recent achievements and ongoing activities and I may be tempted to speculate about fundamental, inherent limitations of AI concepts in this application area.
Uncertainties in estimating Earth’s future climate stem from both inaccuracies in our models and the vast array of possible choices that society will make in the intervening years. One of the most pressing uncertainties in climate modelling is that of the effect of anthropogenic aerosol, particularly through their interactions with clouds. Here I will introduce a general earth system emulation framework which leverages advances in machine learning and describe its application to the emulation of entire climate models for the reduction of this uncertainty. I will also demonstrate how such emulation can be used to better approximate the climate response to different anthropogenic forcing agents in order to aid in their detection and attribution, and in the exploration of different future emissions pathways.