Physically Interpretable Emulation of a Moist Convecting Atmosphere with a Recurrent Neural Network

TL;DR

This paper presents a recurrent neural network model that emulates a moist convecting atmosphere, combining linear and nonlinear components for physical interpretability, stability, and realistic long-term behavior in climate simulations.

Contribution

It introduces a physically interpretable RNN architecture that accurately emulates convective atmospheric processes and demonstrates stability and generalizability in long-term climate simulations.

Findings

Model exhibits stable, realistic long-term emulation of atmospheric convection.

Linear responses to perturbations are physically interpretable.

Model performs well with prescribed and coupled forcings.

Abstract

Data-driven convective parameterization aims to accurately represent convective adjustments to large-scale forcings in a computationally economic manner. While previous studies have demonstrated success using various model architectures, challenges persist in developing physically interpretable models and assessing generalizability and confidence level. In this study, we develop a recurrent neural network to predict time series of temperature, moisture, and precipitation of a cumulus ensemble in response to large-scale forcings. The recurrent cell combines a linear component, pre-identified as a time-invariant state-space model within the linear limit of the problem, and a multilayer neural network for the nonlinear component. Trained on ensembles of limited-domain cloud-resolving model simulation data, the model exhibits stable and realistic performance in long-term emulations, both with prescribed large-scale forcings and when coupled with two-dimensional gravity waves. We further calculate linear responses to perturbations for the coupled emulation, revealing physically interpretable, state-dependent properties of the convectively coupled gravity wave system.