WRF–ML v1.0: a bridge between WRF v4.3 and machine learning parameterizations and its application to atmospheric radiative transfer
<p>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 machine learning (ML) parameterizations of subgr...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2023-01-01
|
| Series: | Geoscientific Model Development |
| Online Access: | https://gmd.copernicus.org/articles/16/199/2023/gmd-16-199-2023.pdf |
| _version_ | 1797959872874020864 |
|---|---|
| author | X. Zhong Z. Ma Y. Yao L. Xu Y. Wu Z. Wang |
| author_facet | X. Zhong Z. Ma Y. Yao L. Xu Y. Wu Z. Wang |
| author_sort | X. Zhong |
| collection | DOAJ |
| description | <p>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 machine learning (ML) parameterizations of subgrid physics have the potential to accelerate and even outperform conventional physics-based schemes. However, as the ML models are commonly implemented using the ML libraries written in Python, very few ML-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 ML-based parameterizations to be coupled with a widely used NWP model, i.e., the Weather Research and Forecasting (WRF) model. Similar to the WRF I/O methodologies, the coupler provides the options to run the ML model inference with exclusive processors or the same processors for WRF calculations. In addition, to demonstrate the effectiveness of the coupler, the ML-based radiation emulators are trained and coupled with the WRF model successfully.</p> |
| first_indexed | 2024-04-11T00:38:53Z |
| format | Article |
| id | doaj.art-228de59116e04625af33f7e9dd60e13b |
| institution | Directory Open Access Journal |
| issn | 1991-959X 1991-9603 |
| language | English |
| last_indexed | 2024-04-11T00:38:53Z |
| publishDate | 2023-01-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | Geoscientific Model Development |
| spelling | doaj.art-228de59116e04625af33f7e9dd60e13b2023-01-06T12:38:07ZengCopernicus PublicationsGeoscientific Model Development1991-959X1991-96032023-01-011619920910.5194/gmd-16-199-2023WRF–ML v1.0: a bridge between WRF v4.3 and machine learning parameterizations and its application to atmospheric radiative transferX. ZhongZ. MaY. YaoL. XuY. WuZ. Wang<p>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 machine learning (ML) parameterizations of subgrid physics have the potential to accelerate and even outperform conventional physics-based schemes. However, as the ML models are commonly implemented using the ML libraries written in Python, very few ML-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 ML-based parameterizations to be coupled with a widely used NWP model, i.e., the Weather Research and Forecasting (WRF) model. Similar to the WRF I/O methodologies, the coupler provides the options to run the ML model inference with exclusive processors or the same processors for WRF calculations. In addition, to demonstrate the effectiveness of the coupler, the ML-based radiation emulators are trained and coupled with the WRF model successfully.</p>https://gmd.copernicus.org/articles/16/199/2023/gmd-16-199-2023.pdf |
| spellingShingle | X. Zhong Z. Ma Y. Yao L. Xu Y. Wu Z. Wang WRF–ML v1.0: a bridge between WRF v4.3 and machine learning parameterizations and its application to atmospheric radiative transfer Geoscientific Model Development |
| title | WRF–ML v1.0: a bridge between WRF v4.3 and machine learning parameterizations and its application to atmospheric radiative transfer |
| title_full | WRF–ML v1.0: a bridge between WRF v4.3 and machine learning parameterizations and its application to atmospheric radiative transfer |
| title_fullStr | WRF–ML v1.0: a bridge between WRF v4.3 and machine learning parameterizations and its application to atmospheric radiative transfer |
| title_full_unstemmed | WRF–ML v1.0: a bridge between WRF v4.3 and machine learning parameterizations and its application to atmospheric radiative transfer |
| title_short | WRF–ML v1.0: a bridge between WRF v4.3 and machine learning parameterizations and its application to atmospheric radiative transfer |
| title_sort | wrf ml v1 0 a bridge between wrf v4 3 and machine learning parameterizations and its application to atmospheric radiative transfer |
| url | https://gmd.copernicus.org/articles/16/199/2023/gmd-16-199-2023.pdf |
| work_keys_str_mv | AT xzhong wrfmlv10abridgebetweenwrfv43andmachinelearningparameterizationsanditsapplicationtoatmosphericradiativetransfer AT zma wrfmlv10abridgebetweenwrfv43andmachinelearningparameterizationsanditsapplicationtoatmosphericradiativetransfer AT yyao wrfmlv10abridgebetweenwrfv43andmachinelearningparameterizationsanditsapplicationtoatmosphericradiativetransfer AT lxu wrfmlv10abridgebetweenwrfv43andmachinelearningparameterizationsanditsapplicationtoatmosphericradiativetransfer AT ywu wrfmlv10abridgebetweenwrfv43andmachinelearningparameterizationsanditsapplicationtoatmosphericradiativetransfer AT zwang wrfmlv10abridgebetweenwrfv43andmachinelearningparameterizationsanditsapplicationtoatmosphericradiativetransfer |