Preprints
https://doi.org/10.5194/amt-2022-37
https://doi.org/10.5194/amt-2022-37
 
17 Feb 2022
17 Feb 2022
Status: a revised version of this preprint is currently under review for the journal AMT.

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

Yeeun Lee, Myoung-Hwan Ahn, Mina Kang, and Mijin Eo Yeeun Lee et al.
  • Department of Climate and Energy Systems Engineering, Ewha Womans University, Seoul, 03760, Republic of Korea

Abstract. Earth radiance in the form of hyperspectral data contains useful information on atmospheric constituents and aerosol properties. The Geostationary Environment Monitoring Spectrometer (GEMS) is an environmental sensor measuring such hyperspectral data in the ultraviolet and visible (UV/VIS) spectral range over the Asia-Pacific region. After successful completion of the in orbit test of GEMS in October 2020, bad pixels are found as a remaining calibration issue to be updated with follow-up treatment. Currently, one-dimensional interpolation in the spatial direction is performed in operation to replace the erroneous pixels of GEMS, which causes high interpolation error for a wider defect area on a detector array. To resolve the issue, this study suggests machine learning methods with artificial neural network (ANN) and multivariate linear regression (Linear) to fill in a spectral gap of defective spectra. The machine learning models are trained with normal measurements to emulate spectral relations between input and output radiances in a spectrum. For efficient training, dimensionality reduction for the input radiances is applied with principal component analysis (PCA) prior to the training process. The results show that the defect area at the wavelengths of strong absorption lines is better replaced with PCA-ANN with the error of 5 %, while PCA-Linear is better for reproducing radiances having strong correlation with input radiances. The shorter the spectral range of output radiances is, the smaller the prediction error is with PCA-Linear (0.5–5 %). Spectral and spatial discontinuity caused by real bad pixels can be significantly improved with the trained machine learning models especially for wide defect areas. This study verifies that spectral relations of radiances in the UV/VIS spectrum are successfully reproduced with a simple machine learning model, which has high potential to be investigated further for enhancing measurement quality of environmental satellite measurements.

Yeeun Lee et al.

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on amt-2022-37', Glen Jaross, 25 Feb 2022
    • AC1: 'Reply on RC1', Yeeun Lee, 06 May 2022
  • RC2: 'Comment on amt-2022-37', Anonymous Referee #2, 10 Mar 2022
    • AC2: 'Reply on RC2', Yeeun Lee, 06 May 2022

Yeeun Lee et al.

Yeeun Lee et al.

Viewed

Total article views: 530 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
371 138 21 530 9 9
  • HTML: 371
  • PDF: 138
  • XML: 21
  • Total: 530
  • BibTeX: 9
  • EndNote: 9
Views and downloads (calculated since 17 Feb 2022)
Cumulative views and downloads (calculated since 17 Feb 2022)

Viewed (geographical distribution)

Total article views: 512 (including HTML, PDF, and XML) Thereof 512 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 05 Dec 2022
Download
Short summary
This study aims to verify that a partly defective hyperspectral measurement can be successfully reproduced with concise machine learning models with artificial neural network (ANN) and multivariate linear regression. Considering that GEMS is the first geostationary UV/VIS hyperspectral spectrometer, we expect our findings can be introduced further to similar geostationary instruments to be launched soon such as Tropospheric Emissions: Monitoring Pollution (U.S.A.) or Sentinel-4 (Europe).