DSRSS-Net: Improved-Resolution Snow Cover Mapping from FY-4A Satellite Images Using the Dual-Branch Super-Resolution Semantic Segmentation Network
The Qinghai–Tibet Plateau is one of the regions with the highest snow accumulation in China. Although the Fengyun-4A (FY4A) satellite is capable of monitoring snow-covered areas in real time and on a wide scale at high temporal resolution, its spatial resolution is low. In this study, the Qinghai–Ti...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/18/4431 |
| _version_ | 1827723855239577600 |
|---|---|
| author | Xi Kan Zhengsong Lu Yonghong Zhang Linglong Zhu Kenny Thiam Choy Lim Kam Sian Jiangeng Wang Xu Liu Zhou Zhou Haixiao Cao |
| author_facet | Xi Kan Zhengsong Lu Yonghong Zhang Linglong Zhu Kenny Thiam Choy Lim Kam Sian Jiangeng Wang Xu Liu Zhou Zhou Haixiao Cao |
| author_sort | Xi Kan |
| collection | DOAJ |
| description | The Qinghai–Tibet Plateau is one of the regions with the highest snow accumulation in China. Although the Fengyun-4A (FY4A) satellite is capable of monitoring snow-covered areas in real time and on a wide scale at high temporal resolution, its spatial resolution is low. In this study, the Qinghai–Tibet Plateau, which has a harsh climate with few meteorological stations, was selected as the study area. We propose a deep learning model called the Dual-Branch Super-Resolution Semantic Segmentation Network (DSRSS-Net), in which one branch focuses with super resolution to obtain high-resolution snow distributions and the other branch carries out semantic segmentation to achieve accurate snow recognition. An edge enhancement module and coordinated attention mechanism were introduced into the network to improve the classification performance and edge segmentation effect for cloud versus snow. Multi-task loss is also used for optimization, including feature affinity loss and edge loss, to obtain fine structural information and improve edge segmentation. The 1 km resolution image obtained by coupling bands 1, 2, and 3; the 2 km resolution image obtained by coupling bands 4, 5, and 6; and the 500 m resolution image for a single channel, band 2, were inputted into the model for training. The accuracy of this model was verified using ground-based meteorological station data. Snow classification accuracy, false detection rate, and total classification accuracy were compared with the MOD10A1 snow product. The results show that, compared with MOD10A1, the snow classification accuracy and the average total accuracy of DSRSS-Net improved by 4.45% and 5.1%, respectively. The proposed method effectively reduces the misidentification of clouds and snow, has higher classification accuracy, and effectively improves the spatial resolution of FY-4A satellite snow cover products. |
| first_indexed | 2024-03-10T22:06:38Z |
| format | Article |
| id | doaj.art-add913d76728453dad39743b9fc09e06 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T22:06:38Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-add913d76728453dad39743b9fc09e062023-11-19T12:47:36ZengMDPI AGRemote Sensing2072-42922023-09-011518443110.3390/rs15184431DSRSS-Net: Improved-Resolution Snow Cover Mapping from FY-4A Satellite Images Using the Dual-Branch Super-Resolution Semantic Segmentation NetworkXi Kan0Zhengsong Lu1Yonghong Zhang2Linglong Zhu3Kenny Thiam Choy Lim Kam Sian4Jiangeng Wang5Xu Liu6Zhou Zhou7Haixiao Cao8School of the Internet of Thing Engineering, Wuxi University, Wuxi 214105, ChinaSchool of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaSchool of the Internet of Thing Engineering, Wuxi University, Wuxi 214105, ChinaSchool of the Internet of Thing Engineering, Wuxi University, Wuxi 214105, ChinaSchool of Atmospheric Science and Remote Sensing, Wuxi University, Wuxi 214105, ChinaCollaborative Innovation Centre on Forecast and Evaluation of Meteorological Disasters, Key Laboratory for Aerosol-Cloud-Precipitation of China Meteorological Administration, School of Atmospheric Physics, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaSchool of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaSchool of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaSchool of the Internet of Thing Engineering, Wuxi University, Wuxi 214105, ChinaThe Qinghai–Tibet Plateau is one of the regions with the highest snow accumulation in China. Although the Fengyun-4A (FY4A) satellite is capable of monitoring snow-covered areas in real time and on a wide scale at high temporal resolution, its spatial resolution is low. In this study, the Qinghai–Tibet Plateau, which has a harsh climate with few meteorological stations, was selected as the study area. We propose a deep learning model called the Dual-Branch Super-Resolution Semantic Segmentation Network (DSRSS-Net), in which one branch focuses with super resolution to obtain high-resolution snow distributions and the other branch carries out semantic segmentation to achieve accurate snow recognition. An edge enhancement module and coordinated attention mechanism were introduced into the network to improve the classification performance and edge segmentation effect for cloud versus snow. Multi-task loss is also used for optimization, including feature affinity loss and edge loss, to obtain fine structural information and improve edge segmentation. The 1 km resolution image obtained by coupling bands 1, 2, and 3; the 2 km resolution image obtained by coupling bands 4, 5, and 6; and the 500 m resolution image for a single channel, band 2, were inputted into the model for training. The accuracy of this model was verified using ground-based meteorological station data. Snow classification accuracy, false detection rate, and total classification accuracy were compared with the MOD10A1 snow product. The results show that, compared with MOD10A1, the snow classification accuracy and the average total accuracy of DSRSS-Net improved by 4.45% and 5.1%, respectively. The proposed method effectively reduces the misidentification of clouds and snow, has higher classification accuracy, and effectively improves the spatial resolution of FY-4A satellite snow cover products.https://www.mdpi.com/2072-4292/15/18/4431super-resolutioncloud and snow identificationFY-4A |
| spellingShingle | Xi Kan Zhengsong Lu Yonghong Zhang Linglong Zhu Kenny Thiam Choy Lim Kam Sian Jiangeng Wang Xu Liu Zhou Zhou Haixiao Cao DSRSS-Net: Improved-Resolution Snow Cover Mapping from FY-4A Satellite Images Using the Dual-Branch Super-Resolution Semantic Segmentation Network Remote Sensing super-resolution cloud and snow identification FY-4A |
| title | DSRSS-Net: Improved-Resolution Snow Cover Mapping from FY-4A Satellite Images Using the Dual-Branch Super-Resolution Semantic Segmentation Network |
| title_full | DSRSS-Net: Improved-Resolution Snow Cover Mapping from FY-4A Satellite Images Using the Dual-Branch Super-Resolution Semantic Segmentation Network |
| title_fullStr | DSRSS-Net: Improved-Resolution Snow Cover Mapping from FY-4A Satellite Images Using the Dual-Branch Super-Resolution Semantic Segmentation Network |
| title_full_unstemmed | DSRSS-Net: Improved-Resolution Snow Cover Mapping from FY-4A Satellite Images Using the Dual-Branch Super-Resolution Semantic Segmentation Network |
| title_short | DSRSS-Net: Improved-Resolution Snow Cover Mapping from FY-4A Satellite Images Using the Dual-Branch Super-Resolution Semantic Segmentation Network |
| title_sort | dsrss net improved resolution snow cover mapping from fy 4a satellite images using the dual branch super resolution semantic segmentation network |
| topic | super-resolution cloud and snow identification FY-4A |
| url | https://www.mdpi.com/2072-4292/15/18/4431 |
| work_keys_str_mv | AT xikan dsrssnetimprovedresolutionsnowcovermappingfromfy4asatelliteimagesusingthedualbranchsuperresolutionsemanticsegmentationnetwork AT zhengsonglu dsrssnetimprovedresolutionsnowcovermappingfromfy4asatelliteimagesusingthedualbranchsuperresolutionsemanticsegmentationnetwork AT yonghongzhang dsrssnetimprovedresolutionsnowcovermappingfromfy4asatelliteimagesusingthedualbranchsuperresolutionsemanticsegmentationnetwork AT linglongzhu dsrssnetimprovedresolutionsnowcovermappingfromfy4asatelliteimagesusingthedualbranchsuperresolutionsemanticsegmentationnetwork AT kennythiamchoylimkamsian dsrssnetimprovedresolutionsnowcovermappingfromfy4asatelliteimagesusingthedualbranchsuperresolutionsemanticsegmentationnetwork AT jiangengwang dsrssnetimprovedresolutionsnowcovermappingfromfy4asatelliteimagesusingthedualbranchsuperresolutionsemanticsegmentationnetwork AT xuliu dsrssnetimprovedresolutionsnowcovermappingfromfy4asatelliteimagesusingthedualbranchsuperresolutionsemanticsegmentationnetwork AT zhouzhou dsrssnetimprovedresolutionsnowcovermappingfromfy4asatelliteimagesusingthedualbranchsuperresolutionsemanticsegmentationnetwork AT haixiaocao dsrssnetimprovedresolutionsnowcovermappingfromfy4asatelliteimagesusingthedualbranchsuperresolutionsemanticsegmentationnetwork |