Predicting global patterns of long-term climate change from short-term simulations using machine learning

To estimate the response of the climate to a change in emissions, we typically run long simulations with a global climate model, which tend to be very computationally demanding. This paper explores the use of use of machine learning to learn the long-term patterns of climate change, given short-term simulations from a climate model. These methods could help accelerate climate change projections. You can access the paper here