Hybrid precipitation downscaling over coastal watersheds in Japan using WRF and CNN
Study region: Kuma River Watershed in Japan. Study focus: High-quality precipitation information is desirable in hydrological modeling and water resources management. This study aimed to generate long-term fine-resolution precipitation datasets over the study region. A hybrid downscaling framework t...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-10-01
|
| Series: | Journal of Hydrology: Regional Studies |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2214581821001506 |
| _version_ | 1819014165365260288 |
|---|---|
| author | Tongbi Tu Kei Ishida Ali Ercan Masato Kiyama Motoki Amagasaki Tongtiegang Zhao |
| author_facet | Tongbi Tu Kei Ishida Ali Ercan Masato Kiyama Motoki Amagasaki Tongtiegang Zhao |
| author_sort | Tongbi Tu |
| collection | DOAJ |
| description | Study region: Kuma River Watershed in Japan. Study focus: High-quality precipitation information is desirable in hydrological modeling and water resources management. This study aimed to generate long-term fine-resolution precipitation datasets over the study region. A hybrid downscaling framework that integrates a dynamical approach by the Weather Research and Forecasting (WRF) model and a deep learning approach by the Convolutional Neural Network (CNN) model was proposed to derive precipitation information at fine resolutions from ERA-Interim datasets. The proposed hybrid downscaling framework was then applied to a coastal watershed in Japan. The merit of the hybrid downscaling approach in generating precipitation datasets at a 6-km resolution from 80-km ERA-Interim datasets, and 54-km and 18-km WRF simulated gridded datasets was explored as an alternative to pure dynamical downscaling approach by WRF. New hydrological insights for the region: The Nash-Sutcliffe efficiency coefficients of daily basin-averaged precipitation at 6-km resolution obtained by CNN from ERA-Interim, 54-km and 18-km WRF simulated datasets were 0.79, 0.93, and 0.98, respectively for training period; 0.71, 0.85, and 0.96, respectively for validation, when compared to 6-km WRF simulated gridded precipitation. The results demonstrated that CNN can reproduce 6-km WRF simulated precipitation and fine-resolution WRF modeling is needed to further enhance the downscaling performance, especially to capture spatial heterogeneity and extreme events. The hybrid downscaling framework of precipitation is promising to preserve the physics of atmospheric dynamics in precipitation modeling and reduce the computational cost considerably compared to pure dynamical downscaling. |
| first_indexed | 2024-12-21T02:11:30Z |
| format | Article |
| id | doaj.art-f99907b3370f4b1493bcfa09cbfece14 |
| institution | Directory Open Access Journal |
| issn | 2214-5818 |
| language | English |
| last_indexed | 2024-12-21T02:11:30Z |
| publishDate | 2021-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Hydrology: Regional Studies |
| spelling | doaj.art-f99907b3370f4b1493bcfa09cbfece142022-12-21T19:19:22ZengElsevierJournal of Hydrology: Regional Studies2214-58182021-10-0137100921Hybrid precipitation downscaling over coastal watersheds in Japan using WRF and CNNTongbi Tu0Kei Ishida1Ali Ercan2Masato Kiyama3Motoki Amagasaki4Tongtiegang Zhao5Center of Water Resources and Environment, Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai), School of Civil Engineering, Sun Yat-Sen University, Guangzhou, 510275, China; Henan Institute of Sun Yat-sen University, Sun Yat-Sen University, Guangzhou, 510275, ChinaCenter for Water Cycle, Marine Environment, and Disaster Management, International Research Organization for Advanced Science and Technology, Kumamoto University, 2-39-1 Kurokami, Kumamoto, 860-8555, JapanDepartment of Civil and Environmental Engineering, University of California, Davis, One Shields Avenue, Davis, CA, 95616, USAFaculty of Advanced Science and Technology, Kumamoto University, 2-39-1 Kurokami, Kumamoto, 860-8555, JapanFaculty of Advanced Science and Technology, Kumamoto University, 2-39-1 Kurokami, Kumamoto, 860-8555, JapanCenter of Water Resources and Environment, Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai), School of Civil Engineering, Sun Yat-Sen University, Guangzhou, 510275, China; Henan Institute of Sun Yat-sen University, Sun Yat-Sen University, Guangzhou, 510275, China; Corresponding author.Study region: Kuma River Watershed in Japan. Study focus: High-quality precipitation information is desirable in hydrological modeling and water resources management. This study aimed to generate long-term fine-resolution precipitation datasets over the study region. A hybrid downscaling framework that integrates a dynamical approach by the Weather Research and Forecasting (WRF) model and a deep learning approach by the Convolutional Neural Network (CNN) model was proposed to derive precipitation information at fine resolutions from ERA-Interim datasets. The proposed hybrid downscaling framework was then applied to a coastal watershed in Japan. The merit of the hybrid downscaling approach in generating precipitation datasets at a 6-km resolution from 80-km ERA-Interim datasets, and 54-km and 18-km WRF simulated gridded datasets was explored as an alternative to pure dynamical downscaling approach by WRF. New hydrological insights for the region: The Nash-Sutcliffe efficiency coefficients of daily basin-averaged precipitation at 6-km resolution obtained by CNN from ERA-Interim, 54-km and 18-km WRF simulated datasets were 0.79, 0.93, and 0.98, respectively for training period; 0.71, 0.85, and 0.96, respectively for validation, when compared to 6-km WRF simulated gridded precipitation. The results demonstrated that CNN can reproduce 6-km WRF simulated precipitation and fine-resolution WRF modeling is needed to further enhance the downscaling performance, especially to capture spatial heterogeneity and extreme events. The hybrid downscaling framework of precipitation is promising to preserve the physics of atmospheric dynamics in precipitation modeling and reduce the computational cost considerably compared to pure dynamical downscaling.http://www.sciencedirect.com/science/article/pii/S2214581821001506WRFConvolutional neural networkPrecipitationDownscalingDeep learning |
| spellingShingle | Tongbi Tu Kei Ishida Ali Ercan Masato Kiyama Motoki Amagasaki Tongtiegang Zhao Hybrid precipitation downscaling over coastal watersheds in Japan using WRF and CNN Journal of Hydrology: Regional Studies WRF Convolutional neural network Precipitation Downscaling Deep learning |
| title | Hybrid precipitation downscaling over coastal watersheds in Japan using WRF and CNN |
| title_full | Hybrid precipitation downscaling over coastal watersheds in Japan using WRF and CNN |
| title_fullStr | Hybrid precipitation downscaling over coastal watersheds in Japan using WRF and CNN |
| title_full_unstemmed | Hybrid precipitation downscaling over coastal watersheds in Japan using WRF and CNN |
| title_short | Hybrid precipitation downscaling over coastal watersheds in Japan using WRF and CNN |
| title_sort | hybrid precipitation downscaling over coastal watersheds in japan using wrf and cnn |
| topic | WRF Convolutional neural network Precipitation Downscaling Deep learning |
| url | http://www.sciencedirect.com/science/article/pii/S2214581821001506 |
| work_keys_str_mv | AT tongbitu hybridprecipitationdownscalingovercoastalwatershedsinjapanusingwrfandcnn AT keiishida hybridprecipitationdownscalingovercoastalwatershedsinjapanusingwrfandcnn AT aliercan hybridprecipitationdownscalingovercoastalwatershedsinjapanusingwrfandcnn AT masatokiyama hybridprecipitationdownscalingovercoastalwatershedsinjapanusingwrfandcnn AT motokiamagasaki hybridprecipitationdownscalingovercoastalwatershedsinjapanusingwrfandcnn AT tongtiegangzhao hybridprecipitationdownscalingovercoastalwatershedsinjapanusingwrfandcnn |