Preprints
https://doi.org/10.5194/amt-2023-255
https://doi.org/10.5194/amt-2023-255
06 Dec 2023
 | 06 Dec 2023
Status: this preprint is currently under review for the journal AMT.

AOD data fusion with Geostationary Korea Multi-Purpose Satellite (Geo-KOMPSAT) instruments GEMS, AMI, and GOCI-II: Statistical and deep neural network methods

Minseok Kim, Jhoon Kim, Hyunkwang Lim, Seoyoung Lee, Yeseul Cho, Yun-Gon Lee, Sujung Go, and Kyunghwa Lee

Abstract. Aerosol optical depth (AOD) data fusion of aerosol datasets from the Geostationary Korea Multi-Purpose Satellite (GEO-KOMPSAT, GK) series was undertaken using both statistical and deep neural network (DNN)-based methods. The GK mission includes an Advanced Meteorological Imager (AMI) onboard GK-2A and a Geostationary Environment Monitoring Spectrometer (GEMS) and Geostationary Ocean Color Imager-II onboard GK-2B. The statistical fusion method corrected the bias of each aerosol product by assuming a Gaussian error distribution. The Maximum Likelihood Estimation (MLE) fusion technique accounted for pixel-level uncertainties by weighting the root-mean-square error of each AOD product for every pixel. A DNN-based fusion model was trained to target Aerosol Robotic Network AOD values using fully connected hidden layers. The statistical and DNN-based fusion results generally outperformed individual GEMS and AMI AOD datasets in East Asia (R = 0.888; RMSE = −0.188; MBE = −0.076; 60.6 % within EE for MLE AOD; R = 0.905; RMSE = 0.161; MBE = −0.060; 65.6 % within EE for DNN AOD). The selection of AOD around Korean peninsula, which is incorporating all aerosol products including GOCI-II resulted in much better results (R = 0.911; RMSE = 0.113; MBE = −0.047; 73.3 % within EE for MLE AOD; R = 0.912; RMSE = 0.102; MBE = −0.028; 78.2 % within EE for DNN AOD). The DNN AOD effectively addressed the rapid increase in uncertainty at higher aerosol loadings. Overall, fusion AOD (particularly DNN AOD) most closely matched the performance of the Moderate Resolution Imaging Spectroradiometer Dark Target algorithm, with slightly less variance and a negative bias. Both fusion algorithms stabilized diurnal error variations and provided additional insights into hourly aerosol evolution. The application of aerosol fusion techniques to future geostationary satellite projects such as TEMPO, ABI, and GeoXO may facilitate the production of high-quality global aerosol data.

Minseok Kim, Jhoon Kim, Hyunkwang Lim, Seoyoung Lee, Yeseul Cho, Yun-Gon Lee, Sujung Go, and Kyunghwa Lee

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • CC1: 'Comment on amt-2023-255', Ding Li, 18 Dec 2023
  • RC1: 'Comment on amt-2023-255', Anonymous Referee #1, 07 Jan 2024
  • RC2: 'Comment on amt-2023-255', Anonymous Referee #2, 19 Jan 2024
Minseok Kim, Jhoon Kim, Hyunkwang Lim, Seoyoung Lee, Yeseul Cho, Yun-Gon Lee, Sujung Go, and Kyunghwa Lee
Minseok Kim, Jhoon Kim, Hyunkwang Lim, Seoyoung Lee, Yeseul Cho, Yun-Gon Lee, Sujung Go, and Kyunghwa Lee

Viewed

Total article views: 359 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
260 82 17 359 9 8
  • HTML: 260
  • PDF: 82
  • XML: 17
  • Total: 359
  • BibTeX: 9
  • EndNote: 8
Views and downloads (calculated since 06 Dec 2023)
Cumulative views and downloads (calculated since 06 Dec 2023)

Viewed (geographical distribution)

Total article views: 369 (including HTML, PDF, and XML) Thereof 369 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 02 Mar 2024
Download
Short summary
Information of aerosol loading in the atmosphere can be measured from various satellite instruments. Aerosol products from various satellite instruments have their own error characteristics. This study statistically merged aerosol optical depth datasets from multiple instruments onboard geostationary satellites considering uncertainties. Also, deep neural network technique is adopted for aerosol data merging.