Reconstruction of the Radar Reflectivity of Convective Storms Based on Deep Learning and Himawari-8 Observations
Radar reflectivity (RR) greater than 35 dBZ usually indicates the presence of severe convective weather, which affects a variety of human activities, including aviation. However, RR data are scarce, especially in regions with poor radar coverage or substantial terrain obstructions. Fortunately, the...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/16/3330 |
| _version_ | 1797522127752003584 |
|---|---|
| author | Mingshan Duan Jiangjiang Xia Zhongwei Yan Lei Han Lejian Zhang Hanmeng Xia Shuang Yu |
| author_facet | Mingshan Duan Jiangjiang Xia Zhongwei Yan Lei Han Lejian Zhang Hanmeng Xia Shuang Yu |
| author_sort | Mingshan Duan |
| collection | DOAJ |
| description | Radar reflectivity (RR) greater than 35 dBZ usually indicates the presence of severe convective weather, which affects a variety of human activities, including aviation. However, RR data are scarce, especially in regions with poor radar coverage or substantial terrain obstructions. Fortunately, the radiance data of space-based satellites with universal coverage can be converted into a proxy field of RR. In this study, a convolutional neural network-based data-driven model is developed to convert the radiance data (infrared bands 07, 09, 13, 16, and 16–13) of Himawari-8 into the radar combined reflectivity factor (CREF). A weighted loss function is designed to solve the data imbalance problem due to the sparse convective pixels in the sample. The developed model demonstrates an overall reconstruction capability and performs well in terms of classification scores with 35 dBZ as the threshold. A five-channel input is more efficient in reconstructing the CREF than the commonly used one-channel input. In a case study of a convective event over North China in the summer using the test dataset, U-Net reproduces the location, shape and strength of the convective storm well. The present RR reconstruction technology based on deep learning and Himawari-8 radiance data is shown to be an efficient tool for producing high-resolution RR products, which are especially needed for regions without or with poor radar coverage. |
| first_indexed | 2024-03-10T08:25:03Z |
| format | Article |
| id | doaj.art-10af28ef2a074963b43e8cf31aaaa9b4 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T08:25:03Z |
| publishDate | 2021-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-10af28ef2a074963b43e8cf31aaaa9b42023-11-22T09:35:53ZengMDPI AGRemote Sensing2072-42922021-08-011316333010.3390/rs13163330Reconstruction of the Radar Reflectivity of Convective Storms Based on Deep Learning and Himawari-8 ObservationsMingshan Duan0Jiangjiang Xia1Zhongwei Yan2Lei Han3Lejian Zhang4Hanmeng Xia5Shuang Yu6College of Oceanic and Atmospheric Sciences, Ocean University of China, Qingdao 266100, ChinaInstitute of Atmospheric Physics, Chinese Academy of Sciences, Beijing 100029, ChinaInstitute of Atmospheric Physics, Chinese Academy of Sciences, Beijing 100029, ChinaCollege of Information Science and Engineering, Ocean University of China, Qingdao 266100, ChinaMeteorological Observation Center, China Meteorological Administration, Beijing 100081, ChinaState Key Laboratory of Earth Surface Processes and Resource Ecology, College of Global Change and Earth System Science, Beijing Normal University, Beijing 100875, ChinaInstitut Pierre-Simon Laplace, 4 Place Jussieu, 75005 Paris, FranceRadar reflectivity (RR) greater than 35 dBZ usually indicates the presence of severe convective weather, which affects a variety of human activities, including aviation. However, RR data are scarce, especially in regions with poor radar coverage or substantial terrain obstructions. Fortunately, the radiance data of space-based satellites with universal coverage can be converted into a proxy field of RR. In this study, a convolutional neural network-based data-driven model is developed to convert the radiance data (infrared bands 07, 09, 13, 16, and 16–13) of Himawari-8 into the radar combined reflectivity factor (CREF). A weighted loss function is designed to solve the data imbalance problem due to the sparse convective pixels in the sample. The developed model demonstrates an overall reconstruction capability and performs well in terms of classification scores with 35 dBZ as the threshold. A five-channel input is more efficient in reconstructing the CREF than the commonly used one-channel input. In a case study of a convective event over North China in the summer using the test dataset, U-Net reproduces the location, shape and strength of the convective storm well. The present RR reconstruction technology based on deep learning and Himawari-8 radiance data is shown to be an efficient tool for producing high-resolution RR products, which are especially needed for regions without or with poor radar coverage.https://www.mdpi.com/2072-4292/13/16/3330aviationdeep learningconvective stormsweather radar reflectivityHimawari-8 |
| spellingShingle | Mingshan Duan Jiangjiang Xia Zhongwei Yan Lei Han Lejian Zhang Hanmeng Xia Shuang Yu Reconstruction of the Radar Reflectivity of Convective Storms Based on Deep Learning and Himawari-8 Observations Remote Sensing aviation deep learning convective storms weather radar reflectivity Himawari-8 |
| title | Reconstruction of the Radar Reflectivity of Convective Storms Based on Deep Learning and Himawari-8 Observations |
| title_full | Reconstruction of the Radar Reflectivity of Convective Storms Based on Deep Learning and Himawari-8 Observations |
| title_fullStr | Reconstruction of the Radar Reflectivity of Convective Storms Based on Deep Learning and Himawari-8 Observations |
| title_full_unstemmed | Reconstruction of the Radar Reflectivity of Convective Storms Based on Deep Learning and Himawari-8 Observations |
| title_short | Reconstruction of the Radar Reflectivity of Convective Storms Based on Deep Learning and Himawari-8 Observations |
| title_sort | reconstruction of the radar reflectivity of convective storms based on deep learning and himawari 8 observations |
| topic | aviation deep learning convective storms weather radar reflectivity Himawari-8 |
| url | https://www.mdpi.com/2072-4292/13/16/3330 |
| work_keys_str_mv | AT mingshanduan reconstructionoftheradarreflectivityofconvectivestormsbasedondeeplearningandhimawari8observations AT jiangjiangxia reconstructionoftheradarreflectivityofconvectivestormsbasedondeeplearningandhimawari8observations AT zhongweiyan reconstructionoftheradarreflectivityofconvectivestormsbasedondeeplearningandhimawari8observations AT leihan reconstructionoftheradarreflectivityofconvectivestormsbasedondeeplearningandhimawari8observations AT lejianzhang reconstructionoftheradarreflectivityofconvectivestormsbasedondeeplearningandhimawari8observations AT hanmengxia reconstructionoftheradarreflectivityofconvectivestormsbasedondeeplearningandhimawari8observations AT shuangyu reconstructionoftheradarreflectivityofconvectivestormsbasedondeeplearningandhimawari8observations |