Learning the Representations of Moist Convection with Convolutional Neural Networks

TL;DR

This paper introduces a convolutional neural network approach to better represent moist convection effects in climate models, potentially replacing traditional parameterization methods with more realistic predictions.

Contribution

The study presents a novel CNN-based method that incorporates physical gradients, improving the realism of moist convection representation in climate models.

Findings

CNN predictions are more realistic than other machine learning models.

The method shows potential to replace conventional cumulus parameterization.

Incorporating physical gradients enhances model accuracy.

Abstract

The representations of atmospheric moist convection in general circulation models have been one of the most challenging tasks due to its complexity in physical processes, and the interaction between processes under different time/spatial scales. This study proposes a new method to predict the effects of moist convection on the environment using convolutional neural networks. With the help of considering the gradient of physical fields between adjacent grids in the grey zone resolution, the effects of moist convection predicted by the convolutional neural networks are more realistic compared to the effects predicted by other machine learning models. The result also suggests that the method proposed in this study has the potential to replace the conventional cumulus parameterization in the general circulation models.