MACHINE LEARNING BASED BIAS CORRECTION FOR MODIS AEROSOL OPTICAL DEPTH IN BEIJING
Aerosol refers to suspensions of small solid and liquid particles in the atmosphere. Although the content of aerosol in the atmosphere is small, it plays a crucial role in atmospheric and the climatic processes, making it essential to monitor. In areas with poor aerosol characteristics, satellite-ba...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2023-04-01
|
| Series: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | https://isprs-archives.copernicus.org/articles/XLVIII-M-1-2023/395/2023/isprs-archives-XLVIII-M-1-2023-395-2023.pdf |
| _version_ | 1797842534167216128 |
|---|---|
| author | M. Wang M. Fan Z. Wang Z. Wang L. Chen L. Bai Y. Chen M. Wang |
| author_facet | M. Wang M. Fan Z. Wang Z. Wang L. Chen L. Bai Y. Chen M. Wang |
| author_sort | M. Wang |
| collection | DOAJ |
| description | Aerosol refers to suspensions of small solid and liquid particles in the atmosphere. Although the content of aerosol in the atmosphere is small, it plays a crucial role in atmospheric and the climatic processes, making it essential to monitor. In areas with poor aerosol characteristics, satellite-based aerosol optical depth (AOD) values often differ from ground-based AOD values measured by instruments like AERONET. The use of 3km DT, 10km DT and 10km DTB algorithms in Beijing area has led to significant overestimation of AOD values, highlighting the need for improvement. This paper proposes the use of machine learning techniques, specifically support vector regression (SVR) and artificial neural network (ANN), to correct the deviation of AOD data. Our approach leverages ground-based monitoring data, meteorological reanalysis data and satellite products to train the models. Our results show that the ANN model outperforms the SVR model achieving R2, RMSE and Slope values of 0.88, 0.12 and 0.97, respectively, when applied to nearly two decades of data from 2001 to 2019. This study significantly improves the accuracy of MODIS AOD values, reducing overestimation and bringing them closer to ground-based AOD values measured by AERONET. Our findings have important applications in climate research and environmental monitoring. |
| first_indexed | 2024-04-09T16:50:32Z |
| format | Article |
| id | doaj.art-c296a771ee5a41689ffb0c30bb495e7c |
| institution | Directory Open Access Journal |
| issn | 1682-1750 2194-9034 |
| language | English |
| last_indexed | 2024-04-09T16:50:32Z |
| publishDate | 2023-04-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj.art-c296a771ee5a41689ffb0c30bb495e7c2023-04-21T17:35:16ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342023-04-01XLVIII-M-1-202339540210.5194/isprs-archives-XLVIII-M-1-2023-395-2023MACHINE LEARNING BASED BIAS CORRECTION FOR MODIS AEROSOL OPTICAL DEPTH IN BEIJINGM. Wang0M. Fan1Z. Wang2Z. Wang3L. Chen4L. Bai5Y. Chen6M. Wang7School of Computer and Information Technology, Northeast Petroleum University, Daqing 163318, ChinaState Key Laboratory of Remote Sensing Science, Aerospace Information Research Institute of Chinese Academy of Sciences, Beijing 100101, ChinaSchool of Computer and Information Technology, Northeast Petroleum University, Daqing 163318, ChinaBohai-Rim Energy Research Institute, Northeast Petroleum University, Qinhuangdao 066004, ChinaState Key Laboratory of Remote Sensing Science, Aerospace Information Research Institute of Chinese Academy of Sciences, Beijing 100101, ChinaSchool of Computing, Ulster University, Belfast BT15 1ED, UKSchool of Computer and Information Technology, Northeast Petroleum University, Daqing 163318, ChinaSchool of Computer and Information Technology, Northeast Petroleum University, Daqing 163318, ChinaAerosol refers to suspensions of small solid and liquid particles in the atmosphere. Although the content of aerosol in the atmosphere is small, it plays a crucial role in atmospheric and the climatic processes, making it essential to monitor. In areas with poor aerosol characteristics, satellite-based aerosol optical depth (AOD) values often differ from ground-based AOD values measured by instruments like AERONET. The use of 3km DT, 10km DT and 10km DTB algorithms in Beijing area has led to significant overestimation of AOD values, highlighting the need for improvement. This paper proposes the use of machine learning techniques, specifically support vector regression (SVR) and artificial neural network (ANN), to correct the deviation of AOD data. Our approach leverages ground-based monitoring data, meteorological reanalysis data and satellite products to train the models. Our results show that the ANN model outperforms the SVR model achieving R2, RMSE and Slope values of 0.88, 0.12 and 0.97, respectively, when applied to nearly two decades of data from 2001 to 2019. This study significantly improves the accuracy of MODIS AOD values, reducing overestimation and bringing them closer to ground-based AOD values measured by AERONET. Our findings have important applications in climate research and environmental monitoring.https://isprs-archives.copernicus.org/articles/XLVIII-M-1-2023/395/2023/isprs-archives-XLVIII-M-1-2023-395-2023.pdf |
| spellingShingle | M. Wang M. Fan Z. Wang Z. Wang L. Chen L. Bai Y. Chen M. Wang MACHINE LEARNING BASED BIAS CORRECTION FOR MODIS AEROSOL OPTICAL DEPTH IN BEIJING The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | MACHINE LEARNING BASED BIAS CORRECTION FOR MODIS AEROSOL OPTICAL DEPTH IN BEIJING |
| title_full | MACHINE LEARNING BASED BIAS CORRECTION FOR MODIS AEROSOL OPTICAL DEPTH IN BEIJING |
| title_fullStr | MACHINE LEARNING BASED BIAS CORRECTION FOR MODIS AEROSOL OPTICAL DEPTH IN BEIJING |
| title_full_unstemmed | MACHINE LEARNING BASED BIAS CORRECTION FOR MODIS AEROSOL OPTICAL DEPTH IN BEIJING |
| title_short | MACHINE LEARNING BASED BIAS CORRECTION FOR MODIS AEROSOL OPTICAL DEPTH IN BEIJING |
| title_sort | machine learning based bias correction for modis aerosol optical depth in beijing |
| url | https://isprs-archives.copernicus.org/articles/XLVIII-M-1-2023/395/2023/isprs-archives-XLVIII-M-1-2023-395-2023.pdf |
| work_keys_str_mv | AT mwang machinelearningbasedbiascorrectionformodisaerosolopticaldepthinbeijing AT mfan machinelearningbasedbiascorrectionformodisaerosolopticaldepthinbeijing AT zwang machinelearningbasedbiascorrectionformodisaerosolopticaldepthinbeijing AT zwang machinelearningbasedbiascorrectionformodisaerosolopticaldepthinbeijing AT lchen machinelearningbasedbiascorrectionformodisaerosolopticaldepthinbeijing AT lbai machinelearningbasedbiascorrectionformodisaerosolopticaldepthinbeijing AT ychen machinelearningbasedbiascorrectionformodisaerosolopticaldepthinbeijing AT mwang machinelearningbasedbiascorrectionformodisaerosolopticaldepthinbeijing |