Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Can machine learning improve the model representation of turbulent kinetic energy dissipation rate in the boundary layer for complex terrain?

Journal Article · · Geoscientific Model Development (Online)
 [1];  [1];  [2]
  1. Univ. of Colorado, Boulder, CO (United States); National Renewable Energy Lab. (NREL), Golden, CO (United States)
  2. National Renewable Energy Lab. (NREL), Golden, CO (United States)
+ Show Author Affiliations
Current turbulence parameterizations in numerical weather prediction models at the mesoscale assume a local equilibrium between production and dissipation of turbulence. As this assumption does not hold at fine horizontal resolutions, improved ways to represent turbulent kinetic energy (TKE) dissipation rate (ϵ) are needed. Here, we use a 6-week data set of turbulence measurements from 184 sonic anemometers in complex terrain at the Perdigão field campaign to suggest improved representations of dissipation rate. First, we demonstrate that the widely used Mellor, Yamada, Nakanishi, and Niino (MYNN) parameterization of TKE dissipation rate leads to a large inaccuracy and bias in the representation of ϵ. Next, we assess the potential of machine-learning techniques to predict TKE dissipation rate from a set of atmospheric and terrain-related features. We train and test several machine-learning algorithms using the data at Perdigão, and we find that the models eliminate the bias MYNN currently shows in representing ϵ, while also reducing the average error by up to almost 40 %. Of all the variables included in the algorithms, TKE is the variable responsible for most of the variability of ϵ, and a strong positive correlation exists between the two. These results suggest further consideration of machine-learning techniques to enhance parameterizations of turbulence in numerical weather prediction models.
Research Organization:
National Renewable Energy Laboratory (NREL), Golden, CO (United States)
Sponsoring Organization:
National Science Foundation (NSF); USDOE Office of Energy Efficiency and Renewable Energy (EERE), Renewable Power Office. Wind Energy Technologies Office
Grant/Contract Number:
AC36-08GO28308
OSTI ID:
1660091
Report Number(s):
NREL/JA--5000-75496; MainId:7081; UUID:eff628c9-b40b-ea11-9c2a-ac162d87dfe5; MainAdminID:14075
Journal Information:
Geoscientific Model Development (Online), Journal Name: Geoscientific Model Development (Online) Journal Issue: 9 Vol. 13; ISSN 1991-9603
Publisher:
Copernicus Publications, EGUCopyright Statement
Country of Publication:
United States
Language:
English

References (45)

An Improved Mellor–Yamada Level-3 Model: Its Numerical Stability and Application to a Regional Prediction of Advection Fog journal March 2006
Dissipation of Turbulence in the Wake of a Wind Turbine journal November 2014
Research towards a wake-vortex advisory system for optimal aircraft spacing journal May 2005
The importance of atmospheric turbulence and stability in machine-learning models of wind farm power production journal September 2019
Evaluation of Cut-Off Frequency and Correction of Filter-Induced Phase Lag and Attenuation in Eddy Covariance Analysis of Turbulence Data journal August 2003
Measurements of Boundary Layer Profiles in an Urban Environment journal June 2006
Dealing with Authenticity in the Conservation and Restoration of wall Paintings and Architectural Surfaces journal December 2019
A Description of the Advanced Research WRF Version 2 text January 2005
Spatial and temporal variability of turbulence dissipation rate in complex terrain journal January 2019
Wind turbulence estimates in a valley by coherent Doppler lidar: Turbulence Estimates from Doppler Lidar journal August 2011
Introduction book January 2001
Sensitivity of Turbine-Height Wind Speeds to Parameters in Planetary Boundary-Layer and Surface-Layer Schemes in the Weather Research and Forecasting Model journal July 2016
Sensitivity of Turbine-Height Wind Speeds to Parameters in the Planetary Boundary-Layer Parametrization Used in the Weather Research and Forecasting Model: Extension to Wintertime Conditions journal November 2018
Review: the atmospheric boundary layer journal October 1994
Impact assessment of biomass burning on air quality in Southeast and East Asia during BASE-ASIA journal October 2013
Short-term photovoltaic power forecasting using Artificial Neural Networks and an Analog Ensemble journal August 2017
Turbulence: The Legacy of A. N. Kolmogorov book January 1996
The determination of the Kolmogoroff constants for velocity, temperature and humidity fluctuations from second- and third-order structure functions journal November 1971
Improvement Of The Mellor–Yamada Turbulence Closure Model Based On Large-Eddy Simulation Data journal June 2001
Sonic Anemometer Tilt Correction Algorithms journal April 2001
Evaluation of Cut-Off Frequency and Correction of Filter-Induced Phase Lag and Attenuation in Eddy Covariance Analysis of Turbulence Data journal August 2003
Could Machine Learning Break the Convection Parameterization Deadlock? journal June 2018
U.S. East Coast Lidar Measurements Show Offshore Wind Turbines Will Encounter Very Low Atmospheric Turbulence journal May 2019
The average dissipation rate of turbulent kinetic energy in the neutral and unstable atmospheric surface layer journal June 1997
On the universality of the Kolmogorov constant journal November 1995
Ridge Regression: Biased Estimation for Nonorthogonal Problems journal February 1970
Using machine learning to predict wind turbine power output journal April 2013
Diagnosing wind turbine faults using machine learning techniques applied to operational data conference June 2016
Predicting solar generation from weather forecasts using machine learning
  • Sharma, Navin; Sharma, Pranshu; Irwin, David
  • 2011 IEEE Second International Conference on Smart Grid Communications (SmartGridComm), 2011 IEEE International Conference on Smart Grid Communications (SmartGridComm) https://doi.org/10.1109/SmartGridComm.2011.6102379
conference October 2011
A Hierarchy of Turbulence Closure Models for Planetary Boundary Layers journal October 1974
Flux Measurements, Flux Estimation Techniques, and Fine-Scale Turbulence Measurements in the Unstable Surface Layer Over Land journal March 1977
Surface-Layer Fluxes, Profiles, and Turbulence Measurements over Uniform Terrain under Near-Neutral Conditions journal April 1996
Next-Generation Numerical Weather Prediction: Bridging Parameterization, Explicit Clouds, and Large Eddies journal January 2012
The Perdigão: Peering into Microscale Details of Mountain Winds journal May 2019
Measurements of Boundary Layer Profiles in an Urban Environment journal June 2006
WRF-Fire: Coupled Weather–Wildland Fire Modeling with the Weather Research and Forecasting Model journal January 2013
Turbulence Dissipation Rate in the Atmospheric Boundary Layer: Observations and WRF Mesoscale Modeling during the XPIA Field Campaign journal January 2018
Coherent Doppler lidar signal covariance including wind shear and wind turbulence journal January 1994
An Alternative Family of Transformations journal January 1980
Wind and EDR Measurements with Scanning Doppler LIDARs for Preparing Future Weather Dependent Separation Concepts (Invited) conference June 2015
Machine Learning for Wind Turbine Blades Maintenance Management journal December 2017
Three-dimensional structure of wind turbine wakes as measured by scanning lidar journal January 2017
Estimation of turbulence dissipation rate and its variability from sonic anemometer and wind Doppler lidar during the XPIA field campaign journal January 2018
Estimation of turbulence dissipation rate from Doppler wind lidars and in situ instrumentation for the Perdigão 2017 campaign journal January 2019
Calculating the turbulent fluxes in the atmospheric surface layer with neural networks journal January 2019

Cited By (2)

Assessing boundary condition and parametric uncertainty in numerical-weather-prediction-modeled, long-term offshore wind speed through machine learning and analog ensemble journal November 2021
Utilizing physics-based input features within a machine learning model to predict wind speed forecasting error journal January 2021

Similar Records

Related Subjects

58 GEOSCIENCES
TKE dissipation rate
boundary layer: complex terrain
machine learning
model representation
wind energy