ArchesClimate: Probabilistic Decadal Ensemble Generation With Flow Matching
This work addresses the computational expense of climate modeling for researchers and policymakers, though it is incremental as it builds on existing flow matching methods.
The authors tackled the high computational cost of generating climate projection ensembles by developing ArchesClimate, a deep learning-based emulator trained on decadal hindcasts, which generates stable and physically consistent simulations for up to 10 years and is interchangeable with the IPSL model for several key climate variables.
Climate projections have uncertainties related to components of the climate system and their interactions. A typical approach to quantifying these uncertainties is to use climate models to create ensembles of repeated simulations under different initial conditions. Due to the complexity of these simulations, generating such ensembles of projections is computationally expensive. In this work, we present ArchesClimate, a deep learning-based climate model emulator that aims to reduce this cost. ArchesClimate is trained on decadal hindcasts of the IPSL-CM6A-LR climate model at a spatial resolution of approximately 2.5x1.25 degrees. We train a flow matching model following ArchesWeatherGen, which we adapt to predict near-term climate. Once trained, the model generates states at a one-month lead time and can be used to auto-regressively emulate climate model simulations of any length. We show that for up to 10 years, these generations are stable and physically consistent. We also show that for several important climate variables, ArchesClimate generates simulations that are interchangeable with the IPSL model. This work suggests that climate model emulators could significantly reduce the cost of climate model simulations.