Assessing the Potential of Deep Learning for Emulating Cloud Superparameterization in Climate Models With Real‐Geography Boundary Conditions

Details

Ressource 1Request a copy Under indefinite embargo.
UNIL restricted access
State: Public
Version: author
License: CC BY-NC 4.0
Serval ID
serval:BIB_A7F04116FCF5
Type
Article: article from journal or magazin.
Collection
Publications
Title
Assessing the Potential of Deep Learning for Emulating Cloud Superparameterization in Climate Models With Real‐Geography Boundary Conditions
Journal
Journal of Advances in Modeling Earth Systems
Author(s)
Mooers Griffin, Pritchard Michael, Beucler Tom, Ott Jordan, Yacalis Galen, Baldi Pierre, Gentine Pierre
ISSN
1942-2466
1942-2466
Publication state
Published
Issued date
05/2021
Peer-reviewed
Oui
Volume
13
Number
5
Language
english
Abstract
We explore the potential of feed-forward deep neural networks (DNNs) for emulating cloud superparameterization in realistic geography, using offline fits to data from the superparameterized community atmospheric model. To identify the network architecture of greatest skill, we formally optimize hyperparameters using ∼250 trials. Our DNN explains over 70% of the temporal variance at the 15-min sampling scale throughout the mid-to-upper troposphere. Autocorrelation timescale analysis compared against DNN skill suggests the less good fit in the tropical, marine boundary layer is driven by neural network difficulty emulating fast, stochastic signals in convection. However, spectral analysis in the temporal domain indicates skillful emulation of signals on diurnal to synoptic scales. A closer look at the diurnal cycle reveals correct emulation of land-sea contrasts and vertical structure in the heating and moistening fields, but some distortion of precipitation. Sensitivity tests targeting precipitation skill reveal complementary effects of adding positive constraints versus hyperparameter tuning, motivating the use of both in the future. A first attempt to force an offline land model with DNN emulated atmospheric fields produces reassuring results further supporting neural network emulation viability in real-geography settings. Overall, the fit skill is competitive with recent attempts by sophisticated Residual and Convolutional Neural Network architectures trained on added information, including memory of past states. Our results confirm the parameterizability of superparameterized convection with continents through machine learning and we highlight the advantages of casting this problem locally in space and time for accurate emulation and hopefully quick implementation of hybrid climate models.
Keywords
climate modeling, cloud superparameterization, convection parameterizations, machine learning
Web of science
Open Access
Yes
Create date
21/02/2023 14:36
Last modification date
25/10/2023 11:13
Usage data