Year: 2020
Type: conference-paper
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 implementing a Variational Autoencoder (VAE) that performs structural replication, dimensionality reduction, and clustering of high-resolution vertical velocity fields. Trained on ∼ 6 · 106 samples spanning the globe, the VAE successfully reconstructs the spatial structure of convection, 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.
Authors: Griffin Mooers, Jens Tuyls, Stephan Mandt, Mike Pritchard, Tom G Beucler
Institution: University of California, Irvine
Language: English
Subfield: Atmospheric Science
Field: Earth and Planetary Sciences
Domain: Physical Sciences
SDG: Climate action
Open Access status: gold
Awards: G1440168966, Collaborative Research: HDR Elements: Software for a new machine learning based parameterization of moist convection for improved climate and weather prediction using deep learning, Collaborative Research: HDR Elements: Software for a new machine learning based parameterization of moist convection for improved climate and weather prediction using deep learning, NRT-DESE: Team Science for Integrative Graduate Training in Data Science and Physical Science, Collaborative Research: Role of Cloud Albedo and Land-Atmosphere Interactions on Continental Tropical Climates
OpenAlex ID: W3040489657