GENERATIVE MODELING OF ATMOSPHERIC CONVECTION

Griffin Mooers, Jens Tuyls, Stephan Mandt, Michael Pritchard, Tom Beucler

Abstract: While cloud-resolving models can explicitly simulate the details of small-scale storm formation and morphology, these details are often ignored by climate models for lack of computational resources. Here, we explore the potential of generative modeling to cheaply recreate small-scale storms by designing and implement- ing a Variational Autoencoder (VAE) that performs structural replication, dimensionality reduction, and clus- tering of high-resolution vertical velocity fields. Trained on ∼ 6 · 106 samples spanning the globe, the VAE successfully reconstructs the spatial structure of con- vection, performs unsupervised clustering of convective organization regimes, and identifies anomalous storm activity, confirming the potential of generative modeling to power stochastic parameterizations of convection in climate models.