Improvement of a neural network convection scheme by including triggering and evaluation in present and future climates

TL;DR

This paper enhances a neural network-based deep convection scheme in a climate model by incorporating a triggering mechanism and evaluating its performance across present and future warmer climates.

Contribution

It introduces a new NN parameterization with a triggering mechanism and demonstrates its improved performance and generalization in different climate scenarios.

Findings

The new NN outperforms previous schemes in present climate.

Using relative humidity improves NN performance in warmer climates.

Training NN on warmer climate data yields consistent results across climates.

Abstract

In this study, we improve a neural network (NN) parameterization of deep convection in the global atmosphere model ARP-GEM. To take into account the sporadic nature of convection, we develop a NN parameterization that includes a triggering mechanism that can detect whether deep convection is active or not within a grid-cell. This new data-driven parameterization outperforms the existing NN parameterization in present climate when replacing the original deep convection scheme of ARP-GEM. Online simulations with the NN parameterization run without stability issues. Then, this NN parameterization is evaluated online in a warmer climate. We confirm that using relative humidity instead of the specific total humidity as input for the NN (trained with present data) improves the performance and generalization in warmer climate. Finally, we perform the training of the NN parameterization with data from a warmer climate and this configuration get similar results when used in simulations in present or warmer climates.