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

Bodini, Nicola; Lundquist, Julie K.; Optis, Mike

doi:https://doi.org/10.5194/gmd-13-4271-2020

Articles | Volume 13, issue 9

https://doi.org/10.5194/gmd-13-4271-2020

© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/gmd-13-4271-2020

© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 13, issue 9

Development and technical paper

|

16 Sep 2020

Development and technical paper |

| 16 Sep 2020

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

Nicola Bodini, Julie K. Lundquist, and Mike Optis

Supplement

https://doi.org/10.5194/gmd-13-4271-2020-supplement

Data sets

High-resolution data from sonic anemometers on the meteorological towers at Perdigão UCAR/NCAR, EOL https://doi.org/10.26023/8X1N-TCT4-P50X

Model code and software

Machine learning code for TKE dissipation rates Nicola Bodini https://doi.org/10.5281/zenodo.3754710

Short summary

While turbulence dissipation rate (ε) is an essential parameter for the prediction of wind speed, its current representation in weather prediction models is inaccurate, especially in complex terrain. In this study, we leverage the potential of machine-learning techniques to provide a more accurate representation of turbulence dissipation rate. Our results show a 30 % reduction in the average error compared to the current model representation of ε and a total elimination of its average bias.