Intelligent Reconstruction of Radar Composite Reflectivity Based on Satellite Observations and Deep Learning
Weather radar is a useful tool for monitoring and forecasting severe weather but has limited coverage due to beam blockage from mountainous terrain or other factors. To overcome this issue, an intelligent technology called “Echo Reconstruction UNet (ER-UNet)” is proposed in this study. It reconstruc...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/16/2/275 |
| _version_ | 1797342631611596800 |
|---|---|
| author | Jianyu Zhao Jinkai Tan Sheng Chen Qiqiao Huang Liang Gao Yanping Li Chunxia Wei |
| author_facet | Jianyu Zhao Jinkai Tan Sheng Chen Qiqiao Huang Liang Gao Yanping Li Chunxia Wei |
| author_sort | Jianyu Zhao |
| collection | DOAJ |
| description | Weather radar is a useful tool for monitoring and forecasting severe weather but has limited coverage due to beam blockage from mountainous terrain or other factors. To overcome this issue, an intelligent technology called “Echo Reconstruction UNet (ER-UNet)” is proposed in this study. It reconstructs radar composite reflectivity (CREF) using observations from Fengyun-4A geostationary satellites with broad coverage. In general, ER-UNet outperforms UNet in terms of root mean square error (RMSE), mean absolute error (MAE), structural similarity index (SSIM), probability of detection (POD), false alarm rate (FAR), critical success index (CSI), and Heidke skill score (HSS). Additionally, ER-UNet provides the better reconstruction of CREF compared to the UNet model in terms of the intensity, location, and details of radar echoes (particularly, strong echoes). ER-UNet can effectively reconstruct strong echoes and provide crucial decision-making information for early warning of severe weather. |
| first_indexed | 2024-03-08T10:36:03Z |
| format | Article |
| id | doaj.art-0dc5704c003c4953a3ce66870f277c94 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-08T10:36:03Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-0dc5704c003c4953a3ce66870f277c942024-01-26T18:17:27ZengMDPI AGRemote Sensing2072-42922024-01-0116227510.3390/rs16020275Intelligent Reconstruction of Radar Composite Reflectivity Based on Satellite Observations and Deep LearningJianyu Zhao0Jinkai Tan1Sheng Chen2Qiqiao Huang3Liang Gao4Yanping Li5Chunxia Wei6Key Laboratory of Remote Sensing of Gansu Province, Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou 730000, ChinaSouthern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Zhuhai 519000, ChinaKey Laboratory of Remote Sensing of Gansu Province, Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou 730000, ChinaKey Laboratory of Remote Sensing of Gansu Province, Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou 730000, ChinaState Key Laboratory of Internet of Things for Smart City, and Department of Ocean Science and Technology, University of Macau, Macau 999078, ChinaGuangxi Meteorological Information Center, Nanning 530022, ChinaGuangxi Institute of Meteorological Sciences, Nanning 530022, ChinaWeather radar is a useful tool for monitoring and forecasting severe weather but has limited coverage due to beam blockage from mountainous terrain or other factors. To overcome this issue, an intelligent technology called “Echo Reconstruction UNet (ER-UNet)” is proposed in this study. It reconstructs radar composite reflectivity (CREF) using observations from Fengyun-4A geostationary satellites with broad coverage. In general, ER-UNet outperforms UNet in terms of root mean square error (RMSE), mean absolute error (MAE), structural similarity index (SSIM), probability of detection (POD), false alarm rate (FAR), critical success index (CSI), and Heidke skill score (HSS). Additionally, ER-UNet provides the better reconstruction of CREF compared to the UNet model in terms of the intensity, location, and details of radar echoes (particularly, strong echoes). ER-UNet can effectively reconstruct strong echoes and provide crucial decision-making information for early warning of severe weather.https://www.mdpi.com/2072-4292/16/2/275severe weatherdeep learningcomposite reflectivitygeostationary satellites |
| spellingShingle | Jianyu Zhao Jinkai Tan Sheng Chen Qiqiao Huang Liang Gao Yanping Li Chunxia Wei Intelligent Reconstruction of Radar Composite Reflectivity Based on Satellite Observations and Deep Learning Remote Sensing severe weather deep learning composite reflectivity geostationary satellites |
| title | Intelligent Reconstruction of Radar Composite Reflectivity Based on Satellite Observations and Deep Learning |
| title_full | Intelligent Reconstruction of Radar Composite Reflectivity Based on Satellite Observations and Deep Learning |
| title_fullStr | Intelligent Reconstruction of Radar Composite Reflectivity Based on Satellite Observations and Deep Learning |
| title_full_unstemmed | Intelligent Reconstruction of Radar Composite Reflectivity Based on Satellite Observations and Deep Learning |
| title_short | Intelligent Reconstruction of Radar Composite Reflectivity Based on Satellite Observations and Deep Learning |
| title_sort | intelligent reconstruction of radar composite reflectivity based on satellite observations and deep learning |
| topic | severe weather deep learning composite reflectivity geostationary satellites |
| url | https://www.mdpi.com/2072-4292/16/2/275 |
| work_keys_str_mv | AT jianyuzhao intelligentreconstructionofradarcompositereflectivitybasedonsatelliteobservationsanddeeplearning AT jinkaitan intelligentreconstructionofradarcompositereflectivitybasedonsatelliteobservationsanddeeplearning AT shengchen intelligentreconstructionofradarcompositereflectivitybasedonsatelliteobservationsanddeeplearning AT qiqiaohuang intelligentreconstructionofradarcompositereflectivitybasedonsatelliteobservationsanddeeplearning AT lianggao intelligentreconstructionofradarcompositereflectivitybasedonsatelliteobservationsanddeeplearning AT yanpingli intelligentreconstructionofradarcompositereflectivitybasedonsatelliteobservationsanddeeplearning AT chunxiawei intelligentreconstructionofradarcompositereflectivitybasedonsatelliteobservationsanddeeplearning |