Articles | Volume 16, issue 1
https://doi.org/10.5194/amt-16-153-2023
https://doi.org/10.5194/amt-16-153-2023
Research article
 | 
13 Jan 2023
Research article |  | 13 Jan 2023

Spectral replacement using machine learning methods for continuous mapping of the Geostationary Environment Monitoring Spectrometer (GEMS)

Yeeun Lee, Myoung-Hwan Ahn, Mina Kang, and Mijin Eo

Data sets

GEMS Level 2 products NIER-ESC https://nesc.nier.go.kr/product/view/

Download
Short summary
This study aims to verify that a partly defective hyperspectral measurement can be successfully reproduced with concise machine learning models coupled with principal component analysis. Evaluation of the approach is performed with radiances and retrieval results of ozone and cloud properties. Considering that GEMS is the first geostationary UV–VIS hyperspectral spectrometer, we expect our findings can be introduced further to similar geostationary environmental instruments to be launched soon.