Title: Spatially Extended Tests of a Neural Network Parametrization Trained by Coarse‐Graining

Abstract

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 16-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 accuratelymore » than a coarse-resolution simulation without any parametrizations of subgrid-scale variability, although the mean state slowly drifts.« less

Authors:

Brenowitz, Noah D.  ^[1];

• Search DOE PAGES for author "Brenowitz, Noah D."
• Search DOE PAGES for ORCID "0000-0001-8615-4921"
• Search orcid.org for ORCID "0000-0001-8615-4921"

Bretherton, Christopher S.  ^[1]

• Search DOE PAGES for author "Bretherton, Christopher S."
• Search DOE PAGES for ORCID "0000-0002-6712-8856"
• Search orcid.org for ORCID "0000-0002-6712-8856"

---

+ Show Author Affiliations

1. Department of Atmospheric SciencesUniversity of Washington Seattle WA USA

Publication Date:

2019-08-22

Research Org.:

Univ. of Washington, Seattle, WA (United States)

Sponsoring Org.:

Univ. of Washington, Seattle, WA (United States); USDOE Office of Science (SC)

OSTI Identifier:

1567951

Alternate Identifier(s):

OSTI ID: 1567953; OSTI ID: 1611814

Grant/Contract Number:  

SC0012451; SC0016433

Resource Type:

Published Article

Journal Name:

Journal of Advances in Modeling Earth Systems

Additional Journal Information:

Journal Name: Journal of Advances in Modeling Earth Systems Journal Volume: 11 Journal Issue: 8; Journal ID: ISSN 1942-2466

Publisher:

American Geophysical Union (AGU)

Country of Publication:

United States

Language:

English

Subject:

54 ENVIRONMENTAL SCIENCES; Meteorology & Atmospheric Sciences