An Improved Method Combining ANN and 1D-Var for the Retrieval of Atmospheric Temperature Profiles from FY-4A/GIIRS Hyperspectral Data
In our study, a retrieval method of temperature profiles is proposed which combines an improved one-dimensional variational algorithm (1D-Var) and artificial neural network algorithm (ANN), using FY-4A/GIIRS (Geosynchronous Interferometric Infrared Sounder) infrared hyperspectral data. First, accord...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/3/481 |
| _version_ | 1827596860064268288 |
|---|---|
| author | Pengyu Huang Qiang Guo Changpei Han Chunming Zhang Tianhang Yang Shuo Huang |
| author_facet | Pengyu Huang Qiang Guo Changpei Han Chunming Zhang Tianhang Yang Shuo Huang |
| author_sort | Pengyu Huang |
| collection | DOAJ |
| description | In our study, a retrieval method of temperature profiles is proposed which combines an improved one-dimensional variational algorithm (1D-Var) and artificial neural network algorithm (ANN), using FY-4A/GIIRS (Geosynchronous Interferometric Infrared Sounder) infrared hyperspectral data. First, according to the characteristics of the FY-4A/GIIRS observation data using the conventional 1D-Var, we introduced channel blacklists and discarded the channels that have a large negative impact on retrieval, then used the information capacity method for channel selection and introduced a neural network to correct the satellite observation data. The improved 1D-Var effectively used the observation information of 1415 channels, reducing the impact of the error of the satellite observation and radiative transfer model, and realizing the improvement of retrieval accuracy. We subsequently used the improved 1D-Var and ANN algorithms to retrieve the temperature profiles, respectively, from the GIIRS data. The results showed that the accuracy when using ANN is better than using improved 1D-Var in situations where the pressure ranges from 800 hPa to 1000 hPa. Therefore, we combined the improved 1D-Var and ANN method to retrieve temperature profiles for different pressure levels, calculating the error by taking sounding data published by the University of Wyoming as the true values. The results show that the average error of the retrieved temperature profiles is smaller than 2 K when using our method, this method makes the accuracy of the retrieved temperature profiles superior to the accuracy of the GIIRS products from 10 hPa to 575 hPa. All in all, through the combination of the physical retrieval method and the machine learning retrieval method, this paper can certainly provide a reference for improving the accuracy of products. |
| first_indexed | 2024-03-09T03:17:27Z |
| format | Article |
| id | doaj.art-ed3d37bfb6a54495bb0e37603bf10701 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T03:17:27Z |
| publishDate | 2021-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-ed3d37bfb6a54495bb0e37603bf107012023-12-03T15:17:24ZengMDPI AGRemote Sensing2072-42922021-01-0113348110.3390/rs13030481An Improved Method Combining ANN and 1D-Var for the Retrieval of Atmospheric Temperature Profiles from FY-4A/GIIRS Hyperspectral DataPengyu Huang0Qiang Guo1Changpei Han2Chunming Zhang3Tianhang Yang4Shuo Huang5Key Laboratory of Infrared System Detection and Imaging Technologies, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, ChinaShanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, ChinaKey Laboratory of Infrared System Detection and Imaging Technologies, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, ChinaKey Laboratory of Infrared System Detection and Imaging Technologies, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, ChinaKey Laboratory of Infrared System Detection and Imaging Technologies, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, ChinaKey Laboratory of Infrared System Detection and Imaging Technologies, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, ChinaIn our study, a retrieval method of temperature profiles is proposed which combines an improved one-dimensional variational algorithm (1D-Var) and artificial neural network algorithm (ANN), using FY-4A/GIIRS (Geosynchronous Interferometric Infrared Sounder) infrared hyperspectral data. First, according to the characteristics of the FY-4A/GIIRS observation data using the conventional 1D-Var, we introduced channel blacklists and discarded the channels that have a large negative impact on retrieval, then used the information capacity method for channel selection and introduced a neural network to correct the satellite observation data. The improved 1D-Var effectively used the observation information of 1415 channels, reducing the impact of the error of the satellite observation and radiative transfer model, and realizing the improvement of retrieval accuracy. We subsequently used the improved 1D-Var and ANN algorithms to retrieve the temperature profiles, respectively, from the GIIRS data. The results showed that the accuracy when using ANN is better than using improved 1D-Var in situations where the pressure ranges from 800 hPa to 1000 hPa. Therefore, we combined the improved 1D-Var and ANN method to retrieve temperature profiles for different pressure levels, calculating the error by taking sounding data published by the University of Wyoming as the true values. The results show that the average error of the retrieved temperature profiles is smaller than 2 K when using our method, this method makes the accuracy of the retrieved temperature profiles superior to the accuracy of the GIIRS products from 10 hPa to 575 hPa. All in all, through the combination of the physical retrieval method and the machine learning retrieval method, this paper can certainly provide a reference for improving the accuracy of products.https://www.mdpi.com/2072-4292/13/3/481temperature profilesFY-4A/GIIRSartificial neural network (ANN)one-dimensional variational (1D-Var) |
| spellingShingle | Pengyu Huang Qiang Guo Changpei Han Chunming Zhang Tianhang Yang Shuo Huang An Improved Method Combining ANN and 1D-Var for the Retrieval of Atmospheric Temperature Profiles from FY-4A/GIIRS Hyperspectral Data Remote Sensing temperature profiles FY-4A/GIIRS artificial neural network (ANN) one-dimensional variational (1D-Var) |
| title | An Improved Method Combining ANN and 1D-Var for the Retrieval of Atmospheric Temperature Profiles from FY-4A/GIIRS Hyperspectral Data |
| title_full | An Improved Method Combining ANN and 1D-Var for the Retrieval of Atmospheric Temperature Profiles from FY-4A/GIIRS Hyperspectral Data |
| title_fullStr | An Improved Method Combining ANN and 1D-Var for the Retrieval of Atmospheric Temperature Profiles from FY-4A/GIIRS Hyperspectral Data |
| title_full_unstemmed | An Improved Method Combining ANN and 1D-Var for the Retrieval of Atmospheric Temperature Profiles from FY-4A/GIIRS Hyperspectral Data |
| title_short | An Improved Method Combining ANN and 1D-Var for the Retrieval of Atmospheric Temperature Profiles from FY-4A/GIIRS Hyperspectral Data |
| title_sort | improved method combining ann and 1d var for the retrieval of atmospheric temperature profiles from fy 4a giirs hyperspectral data |
| topic | temperature profiles FY-4A/GIIRS artificial neural network (ANN) one-dimensional variational (1D-Var) |
| url | https://www.mdpi.com/2072-4292/13/3/481 |
| work_keys_str_mv | AT pengyuhuang animprovedmethodcombiningannand1dvarfortheretrievalofatmospherictemperatureprofilesfromfy4agiirshyperspectraldata AT qiangguo animprovedmethodcombiningannand1dvarfortheretrievalofatmospherictemperatureprofilesfromfy4agiirshyperspectraldata AT changpeihan animprovedmethodcombiningannand1dvarfortheretrievalofatmospherictemperatureprofilesfromfy4agiirshyperspectraldata AT chunmingzhang animprovedmethodcombiningannand1dvarfortheretrievalofatmospherictemperatureprofilesfromfy4agiirshyperspectraldata AT tianhangyang animprovedmethodcombiningannand1dvarfortheretrievalofatmospherictemperatureprofilesfromfy4agiirshyperspectraldata AT shuohuang animprovedmethodcombiningannand1dvarfortheretrievalofatmospherictemperatureprofilesfromfy4agiirshyperspectraldata AT pengyuhuang improvedmethodcombiningannand1dvarfortheretrievalofatmospherictemperatureprofilesfromfy4agiirshyperspectraldata AT qiangguo improvedmethodcombiningannand1dvarfortheretrievalofatmospherictemperatureprofilesfromfy4agiirshyperspectraldata AT changpeihan improvedmethodcombiningannand1dvarfortheretrievalofatmospherictemperatureprofilesfromfy4agiirshyperspectraldata AT chunmingzhang improvedmethodcombiningannand1dvarfortheretrievalofatmospherictemperatureprofilesfromfy4agiirshyperspectraldata AT tianhangyang improvedmethodcombiningannand1dvarfortheretrievalofatmospherictemperatureprofilesfromfy4agiirshyperspectraldata AT shuohuang improvedmethodcombiningannand1dvarfortheretrievalofatmospherictemperatureprofilesfromfy4agiirshyperspectraldata |