Acta Optica Sinica, Volume. 43, Issue 24, 2401006(2023)
Aerosol Retrieval Using Deep Learning and Radiative Transfer Model
Fig. 1. Solar (red) and satellite (blue) geometry of Landsat-8 OLI data for study period in Beijing
Fig. 2. Information fitting relationship of satellite geometric parameters in the study area
Fig. 3. Fitting of statistical relationship information between adjacent bands. (a) B1-B2; (b) B2-B3; (c) B3-B4; (d) B4-B5; (e) B5-B6; (f) B6-B7
Fig. 4. DBN structure
Fig. 5. Scatter distribution of aerosol inversion results matched with AERONET measured data. (a) Beijing; (b) Beijing_CAMS; (c) Beijing_RADI; (d) XiangHe; (e) total
Fig. 6. TOA of Landsat-8 changing with the increase of AOD
Fig. 7. Spatial distribution of aerosol optical depth inversion results. (a)(b) RGB map and AOD map obtained by Lansat-8 on 2017-11-15; (c)(d) RGB map and AOD map obtained by Lansat-8 on 2019-09-02; (e)(f) RGB map and AOD map obtained by Lansat-8 on 2019-11-05; (g)(h) RGB map and AOD map obtained by Lansat-8 on 2017-07-10
|
|
Get Citation
Copy Citation Text
Xiaohu Sun, Lin Sun, Chen Jia, Feng Zhou. Aerosol Retrieval Using Deep Learning and Radiative Transfer Model[J]. Acta Optica Sinica, 2023, 43(24): 2401006
Category: Atmospheric Optics and Oceanic Optics
Received: Mar. 14, 2023
Accepted: May. 19, 2023
Published Online: Dec. 8, 2023
The Author Email: Sun Lin (sunlin6@126.com)