Can Machine Learning Improve the Model Representation of TKE Dissipation Rate in the Boundary Layer for Complex Terrain?

Nicola Bodini, Julie K. Lundquist, Mike Optis

Research output: Contribution to journalArticlepeer-review

15 Scopus Citations

Abstract

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 Perdigõ 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 machinelearning 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 Perdigõ, 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.

Original languageAmerican English
Pages (from-to)4271-4285
Number of pages15
JournalGeoscientific Model Development
Volume13
Issue number9
DOIs
StatePublished - 2020

Bibliographical note

Publisher Copyright:
© 2020 Author(s).

NREL Publication Number

  • NREL/JA-5000-75496

Keywords

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

Fingerprint

Dive into the research topics of 'Can Machine Learning Improve the Model Representation of TKE Dissipation Rate in the Boundary Layer for Complex Terrain?'. Together they form a unique fingerprint.

Cite this