Articles | Volume 12, issue 10
Geosci. Model Dev., 12, 4261–4274, 2019
https://doi.org/10.5194/gmd-12-4261-2019
Geosci. Model Dev., 12, 4261–4274, 2019
https://doi.org/10.5194/gmd-12-4261-2019

Development and technical paper 10 Oct 2019

Development and technical paper | 10 Oct 2019

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

Jiali Wang et al.

Viewed

Total article views: 2,490 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
1,673 790 27 2,490 51 43
  • HTML: 1,673
  • PDF: 790
  • XML: 27
  • Total: 2,490
  • BibTeX: 51
  • EndNote: 43
Views and downloads (calculated since 29 Apr 2019)
Cumulative views and downloads (calculated since 29 Apr 2019)

Viewed (geographical distribution)

Total article views: 2,029 (including HTML, PDF, and XML) Thereof 2,017 with geography defined and 12 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Latest update: 21 Oct 2021
Download
Short summary
Parameterizations are frequently used in models representing physical phenomena and are often the computationally expensive portions of the code. Using model output from simulations performed using a weather model, we train deep neural networks to provide an accurate alternative to a physics-based parameterization. We demonstrate that a domain-aware deep neural network can successfully simulate the entire diurnal cycle of the boundary layer physics and the results are transferable.