Climate Change Data Portal
DOI | 10.1029/2019MS001711 |
Spatially Extended Tests of a Neural Network Parametrization Trained by Coarse-Graining | |
Brenowitz N.D.; Bretherton C.S. | |
发表日期 | 2019 |
ISSN | 19422466 |
起始页码 | 2728 |
结束页码 | 2744 |
卷号 | 11期号:8 |
英文摘要 | General circulation models (GCMs) typically have a grid size of 25–200 km. Parametrizations are used to represent diabatic processes such as radiative transfer and cloud microphysics and account for subgrid-scale motions and variability. Unlike traditional approaches, neural networks (NNs) can readily exploit recent observational data sets and global cloud-system resolving model (CRM) simulations to learn subgrid variability. This article describes an NN parametrization trained by coarse-graining a near-global CRM simulation with a 4-km horizontal grid spacing. The NN predicts the residual heating and moistening averaged over (160 km)2 grid boxes as a function of the coarse-resolution fields within the same atmospheric column. This NN is coupled to the dynamical core of a GCM with the same 160-km resolution. A recent study described how to train such an NN to be stable when coupled to specified time-evolving advective forcings in a single-column model, but feedbacks between NN and GCM components cause spatially extended simulations to crash within a few days. Analyzing the linearized response of such an NN reveals that it learns to exploit a strong synchrony between precipitation and the atmospheric state above 10 km. Removing these variables from the NN's inputs stabilizes the coupled simulations, which predict the future state more accurately than a coarse-resolution simulation without any parametrizations of subgrid-scale variability, although the mean state slowly drifts. ©2019. The Authors. |
英文关键词 | global cloud-system resolving model; machine learning; parameterization |
语种 | 英语 |
scopus关键词 | Earth sciences; Learning systems; Parameterization; Atmospheric columns; General circulation model; Global clouds; Horizontal grid spacing; Neural networks (NNS); Sub-grid variability; Subgrid scale variabilities; Traditional approaches; Turbulent flow; advection; artificial neural network; cloud microphysics; diabatic process; general circulation model; machine learning; parameterization; radiative transfer; simulation; spatial analysis |
来源期刊 | Journal of Advances in Modeling Earth Systems |
文献类型 | 期刊论文 |
条目标识符 | http://gcip.llas.ac.cn/handle/2XKMVOVA/156874 |
作者单位 | Department of Atmospheric Sciences, University of Washington, Seattle, WA, United States |
推荐引用方式 GB/T 7714 | Brenowitz N.D.,Bretherton C.S.. Spatially Extended Tests of a Neural Network Parametrization Trained by Coarse-Graining[J],2019,11(8). |
APA | Brenowitz N.D.,&Bretherton C.S..(2019).Spatially Extended Tests of a Neural Network Parametrization Trained by Coarse-Graining.Journal of Advances in Modeling Earth Systems,11(8). |
MLA | Brenowitz N.D.,et al."Spatially Extended Tests of a Neural Network Parametrization Trained by Coarse-Graining".Journal of Advances in Modeling Earth Systems 11.8(2019). |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。