Causal Climate Emulation with Bayesian Filtering
This addresses the need for faster climate predictions and causal analysis for climate scientists, though it appears incremental as it builds on existing emulation approaches.
The researchers tackled the problem of computationally expensive climate simulations by developing an interpretable climate model emulator based on causal representation learning with a Bayesian filter, demonstrating accurate climate dynamics on synthetic and real climate model data.
Traditional models of climate change use complex systems of coupled equations to simulate physical processes across the Earth system. These simulations are highly computationally expensive, limiting our predictions of climate change and analyses of its causes and effects. Machine learning has the potential to quickly emulate data from climate models, but current approaches are not able to incorporate physically-based causal relationships. Here, we develop an interpretable climate model emulator based on causal representation learning. We derive a novel approach including a Bayesian filter for stable long-term autoregressive emulation. We demonstrate that our emulator learns accurate climate dynamics, and we show the importance of each one of its components on a realistic synthetic dataset and data from two widely deployed climate models.