Search Menu
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information
Search Scholarly Publications

Title: Fast domain-aware neural network emulation of a planetary boundary layer parameterization in a numerical weather forecast model

Journal Article · · Geoscientific Model Development (Online)
; ; ORCiD logo

Abstract. Parameterizations for physical processes in weather and climate models are computationally expensive. We use model output from the Weather Research Forecast (WRF) climate model to train deep neural networks (DNNs) and evaluate whether trained DNNs can provide an accurate alternative to the physics-based parameterizations. Specifically, we develop an emulator using DNNs for a planetary boundary layer (PBL) parameterization in the WRF model. PBL parameterizations are used in atmospheric models to represent the diurnal variation in the formation and collapse of the atmospheric boundary layer – the lowest part of the atmosphere. The dynamics and turbulence, as well as velocity, temperature, and humidity profiles within the boundary layer are all critical for determining many of the physical processes in the atmosphere. PBL parameterizations are used to represent these processes that are usually unresolved in a typical climate model that operates at horizontal spatial scales in the tens of kilometers. We demonstrate that a domain-aware DNN, which takes account of underlying domain structure (e.g., nonlocal mixing), can successfully simulate the vertical profiles within the boundary layer of velocities, temperature, and water vapor over the entire diurnal cycle. Results also show that a single trained DNN from one location can produce predictions of wind speed, temperature, and water vapor profiles over nearby locations with similar terrain conditions with correlations higher than 0.9 when compared with the WRF simulations used as the training dataset.

Sponsoring Organization:
USDOE
Grant/Contract Number:
AC02-06CH11357
OSTI ID:
1570018
Journal Information:
Geoscientific Model Development (Online), Journal Name: Geoscientific Model Development (Online) Journal Issue: 10 Vol. 12; ISSN 1991-9603
Publisher:
Copernicus Publications, EGUCopyright Statement
Country of Publication:
Germany
Language:
English

References (22)

Downscaling with a nested regional climate model in near-surface fields over the contiguous United States: WRF dynamical downscaling journal July 2014
A Deep Learning Algorithm of Neural Network for the Parameterization of Typhoon-Ocean Feedback in Typhoon Forecast Models journal April 2018
Modeling 3-D spatio-temporal biogeochemical processes with a forest of 1-D statistical emulators: MODELING 3-D PROCESSES WITH A FOREST OF 1-D EMULATORS journal December 2012
An artificial neural network model to predict thunderstorms within 400 km 2 South Texas domains : Thunderstorm artificial neural network journal April 2015
Use of a neural-network-based long-wave radiative-transfer scheme in the ECMWF atmospheric model journal January 2000
Parameterizations: representing key processes in climate models without resolving them: Parameterizations journal May 2011
Approximation by superpositions of a sigmoidal function journal December 1989
Approximation capabilities of multilayer feedforward networks journal January 1991
Approximations of Functions by a Multilayer Perceptron: a New Approach journal August 1997
Complex hybrid models combining deterministic and machine learning components for numerical climate modeling and weather prediction journal March 2006
Future atmospheric methane concentrations in the context of the stabilization of greenhouse gas concentrations journal August 1999
Toward Data‐Driven Weather and Climate Forecasting: Approximating a Simple General Circulation Model With Deep Learning journal November 2018
Modelling climate change: the role of unresolved processes journal October 2005
Approximation capability to functions of several variables, nonlinear functionals, and operators by radial basis function neural networks journal July 1995
Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its application to dynamical systems journal July 1995
Using Ensemble of Neural Networks to Learn Stochastic Convection Parameterizations for Climate and Numerical Weather Prediction Models from Data Simulated by a Cloud Resolving Model journal January 2013
Neural Networks Technique for Filling Gaps in Satellite Measurements: Application to Ocean Color Observations journal January 2016
A Neural Network Approach for a Fast and Accurate Computation of a Longwave Radiative Budget journal November 1998
New Approach to Calculation of Atmospheric Model Physics: Accurate and Fast Neural Network Emulation of Longwave Radiation in a Climate Model journal May 2005
A New Vertical Diffusion Package with an Explicit Treatment of Entrainment Processes journal September 2006
A Review of Planetary Boundary Layer Parameterization Schemes and Their Sensitivity in Simulating Southeastern U.S. Cold Season Severe Weather Environments journal June 2015
Emulation of a complex global aerosol model to quantify sensitivity to uncertain parameters journal January 2011

Similar Records

Related Subjects