23 Sep 2022
23 Sep 2022
Status: this preprint is open for discussion.

WRF-DL v1.0: A Bridge between WRF v4.3 and Deep Learning Parameterizations and its Application to Atmospheric Radiative Transfer

Xiaohui Zhong, Zhijian Ma, Yichen Yao, Lifei Xu, Yuan Wu, and Zhibin Wang Xiaohui Zhong et al.
  • Damo Academy, Alibaba Group, Hangzhou 311121, China

Abstract. In numerical weather prediction (NWP) models, physical parameterization schemes are the most computationally expensive components, despite being greatly simplified. In the past few years, an increasing number of studies have demonstrated that deep learning (DL) parameterizations of subgrid physics have the potential to accelerate and even outperform conventional physic-based schemes. However, as the DL models are commonly implemented using the DL libraries written in Python, very few DL-based parameterizations have been successfully integrated with NWP models due to the difficulty of embedding Python functions into Fortran-based NWP models. To address this issue, we developed a coupler to allow the DL-based parameterizations to be coupled with a widely used NWP model, i.e., the Weather and Research Forecasting (WRF) model. Similar to the WRF I/O methodologies, the coupler provides the options to run the DL model inference with exclusive processors or the same processors for WRF calculations. In addition, to demonstrate the effectiveness of the coupler, the DL-based radiation emulators are trained and coupled with the WRF model successfully.

Xiaohui Zhong et al.

Status: open (until 18 Nov 2022)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Xiaohui Zhong et al.

Model code and software

A Bridge between WRF and Deep Learning Parameterization and Application on Deep Learning Parameterization of Atmospheric Radiative Transfer Zhong, Xiaohui and Ma, Zhijian and Yao, Yichen and Xue, Lifei and Wu, Yuan and Wang, Zhibin

Xiaohui Zhong et al.


Total article views: 123 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
94 25 4 123 2 2
  • HTML: 94
  • PDF: 25
  • XML: 4
  • Total: 123
  • BibTeX: 2
  • EndNote: 2
Views and downloads (calculated since 23 Sep 2022)
Cumulative views and downloads (calculated since 23 Sep 2022)

Viewed (geographical distribution)

Total article views: 123 (including HTML, PDF, and XML) Thereof 123 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 28 Sep 2022
Short summary
More and more researchers use deep learning models to replace physics-based parameterizations to accelerate weather simulations. However, embedding the DL models within the weather models is difficult as they are implemented in different languages. This work proposes a coupling framework to allow DL-based parameterization to be coupled with the Weather Research and Forecasting (WRF) model. We also demonstrate using the coupler to couple the DL-based radiation schemes with the WRF model.