Himawari-8/AHI Aerosol Optical Depth Detection Based on Machine Learning Algorithm
Due to the advantage of geostationary satellites, Himawari-8/AHI can provide near-real-time air quality monitoring over China with a high temporal resolution. Satellite-based aerosol optical depth (AOD) retrieval over land is a challenge because of the large surface contribution to the top of atmosp...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/13/2967 |
| _version_ | 1797408289449836544 |
|---|---|
| author | Yuanlin Chen Meng Fan Mingyang Li Zhongbin Li Jinhua Tao Zhibao Wang Liangfu Chen |
| author_facet | Yuanlin Chen Meng Fan Mingyang Li Zhongbin Li Jinhua Tao Zhibao Wang Liangfu Chen |
| author_sort | Yuanlin Chen |
| collection | DOAJ |
| description | Due to the advantage of geostationary satellites, Himawari-8/AHI can provide near-real-time air quality monitoring over China with a high temporal resolution. Satellite-based aerosol optical depth (AOD) retrieval over land is a challenge because of the large surface contribution to the top of atmosphere (TOA) signal and the uncertainty of aerosol modes. Here, by combining satellite TOA reflectance, sun-sensor geometries, meteorological factors and vegetation information, we propose a data-driven AOD detection algorithm based on a deep neural network (DNN) model for Himawari-8/AHI. It is trained by sample data of 2018 and 2019 and is applied to derive hourly AODs over China in 2020. By comparison with ground-based AERONET measurements, <i>R</i><sup>2</sup> for DNN-estimated AOD is up to 0.8702, which is much higher than that for the AHI AOD product with <i>R</i><sup>2</sup> = 0.4869. The hourly AOD results indicate that the DNN model has a good potential in improving the performance of AOD retrieval in the early morning and in the late afternoon, and the spatial distribution is reliable for capturing the variation of aerosol pollution on the regional scale. By analyzing different DNN modeling strategies, it is found that seasonal modeling can hardly increase the accuracy of AOD retrieval to a certain extent, and <i>R</i><sup>2</sup> increases from 0.7394 to 0.8168 when meteorological features, especially air pressure, are involved in the model training. |
| first_indexed | 2024-03-09T03:56:17Z |
| format | Article |
| id | doaj.art-25463687cd52435d8f04b17a7863e4f5 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T03:56:17Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-25463687cd52435d8f04b17a7863e4f52023-12-03T14:19:35ZengMDPI AGRemote Sensing2072-42922022-06-011413296710.3390/rs14132967Himawari-8/AHI Aerosol Optical Depth Detection Based on Machine Learning AlgorithmYuanlin Chen0Meng Fan1Mingyang Li2Zhongbin Li3Jinhua Tao4Zhibao Wang5Liangfu Chen6University of Chinese Academy of Sciences, Beijing 100101, ChinaState Key Laboratory of Remote Sensing, Aerospace Information Research Institute, Chinese Academy of Sciences (AIR-CAS), Beijing 100101, ChinaUniversity of Chinese Academy of Sciences, Beijing 100101, ChinaState Key Laboratory of Remote Sensing, Aerospace Information Research Institute, Chinese Academy of Sciences (AIR-CAS), Beijing 100101, ChinaState Key Laboratory of Remote Sensing, Aerospace Information Research Institute, Chinese Academy of Sciences (AIR-CAS), Beijing 100101, ChinaSchool of Computer & Information Technology, Northeast Petroleum University, Daqing 163318, ChinaUniversity of Chinese Academy of Sciences, Beijing 100101, ChinaDue to the advantage of geostationary satellites, Himawari-8/AHI can provide near-real-time air quality monitoring over China with a high temporal resolution. Satellite-based aerosol optical depth (AOD) retrieval over land is a challenge because of the large surface contribution to the top of atmosphere (TOA) signal and the uncertainty of aerosol modes. Here, by combining satellite TOA reflectance, sun-sensor geometries, meteorological factors and vegetation information, we propose a data-driven AOD detection algorithm based on a deep neural network (DNN) model for Himawari-8/AHI. It is trained by sample data of 2018 and 2019 and is applied to derive hourly AODs over China in 2020. By comparison with ground-based AERONET measurements, <i>R</i><sup>2</sup> for DNN-estimated AOD is up to 0.8702, which is much higher than that for the AHI AOD product with <i>R</i><sup>2</sup> = 0.4869. The hourly AOD results indicate that the DNN model has a good potential in improving the performance of AOD retrieval in the early morning and in the late afternoon, and the spatial distribution is reliable for capturing the variation of aerosol pollution on the regional scale. By analyzing different DNN modeling strategies, it is found that seasonal modeling can hardly increase the accuracy of AOD retrieval to a certain extent, and <i>R</i><sup>2</sup> increases from 0.7394 to 0.8168 when meteorological features, especially air pressure, are involved in the model training.https://www.mdpi.com/2072-4292/14/13/2967AODDNNAHIHimawari-8machine learning |
| spellingShingle | Yuanlin Chen Meng Fan Mingyang Li Zhongbin Li Jinhua Tao Zhibao Wang Liangfu Chen Himawari-8/AHI Aerosol Optical Depth Detection Based on Machine Learning Algorithm Remote Sensing AOD DNN AHI Himawari-8 machine learning |
| title | Himawari-8/AHI Aerosol Optical Depth Detection Based on Machine Learning Algorithm |
| title_full | Himawari-8/AHI Aerosol Optical Depth Detection Based on Machine Learning Algorithm |
| title_fullStr | Himawari-8/AHI Aerosol Optical Depth Detection Based on Machine Learning Algorithm |
| title_full_unstemmed | Himawari-8/AHI Aerosol Optical Depth Detection Based on Machine Learning Algorithm |
| title_short | Himawari-8/AHI Aerosol Optical Depth Detection Based on Machine Learning Algorithm |
| title_sort | himawari 8 ahi aerosol optical depth detection based on machine learning algorithm |
| topic | AOD DNN AHI Himawari-8 machine learning |
| url | https://www.mdpi.com/2072-4292/14/13/2967 |
| work_keys_str_mv | AT yuanlinchen himawari8ahiaerosolopticaldepthdetectionbasedonmachinelearningalgorithm AT mengfan himawari8ahiaerosolopticaldepthdetectionbasedonmachinelearningalgorithm AT mingyangli himawari8ahiaerosolopticaldepthdetectionbasedonmachinelearningalgorithm AT zhongbinli himawari8ahiaerosolopticaldepthdetectionbasedonmachinelearningalgorithm AT jinhuatao himawari8ahiaerosolopticaldepthdetectionbasedonmachinelearningalgorithm AT zhibaowang himawari8ahiaerosolopticaldepthdetectionbasedonmachinelearningalgorithm AT liangfuchen himawari8ahiaerosolopticaldepthdetectionbasedonmachinelearningalgorithm |