Stochastic Parameterization of Column Physics using Generative Adversarial Networks
This work addresses the need for more efficient and accurate physics parameterizations in climate modeling, though it appears incremental as it builds on prior deterministic methods.
The paper tackled the problem of improving atmospheric column-physics parameterizations in climate models by using generative adversarial networks to learn stochastic distributions of diabatic sources from temperature and humidity profiles, resulting in a method that enhances deterministic approaches by addressing computational demands and human-designed limitations.
We demonstrate the use of a probabilistic machine learning technique to develop stochastic parameterizations of atmospheric column-physics. After suitable preprocessing of NASA's Modern-Era Retrospective analysis for Research and Applications, version 2 (MERRA2) data to minimize the effects of high-frequency, high-wavenumber component of MERRA2 estimate of vertical velocity, we use generative adversarial networks to learn the probability distribution of vertical profiles of diabatic sources conditioned on vertical profiles of temperature and humidity. This may be viewed as an improvement over previous similar but deterministic approaches that seek to alleviate both, shortcomings of human-designed physics parameterizations, and the computational demand of the "physics" step in climate models.