2025/11/07 by Germain, Hugo, Balogh, Blanka, Geoffroy, Olivier +1
Computer Science · Earth and Planetary Sciences · Physics and Astronomy · #Artificial neural network #Atmospheric and Oceanic Physics (physics.ao-ph) #Convection #Deep convection #FOS: Physical sciences #Generalization #Meteorological Phenomena and Simulations #Model Reduction and Neural Networks #Neural Networks and Reservoir Computing #Parametrization (atmospheric modeling) #Scheme (mathematics) #Stability (learning theory) #Training (meteorology)
paper · open access · doi:10.48550/arxiv.2511.05074
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2025/11/07 · openalex created_date 2025/11/11 · openalex updated_date 2026/07/28
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.