Spectral replacement using machine learning methods for continuous mapping of the Geostationary Environment Monitoring Spectrometer (GEMS)
-
Published:2023-01-13
Issue:1
Volume:16
Page:153-168
-
ISSN:1867-8548
-
Container-title:Atmospheric Measurement Techniques
-
language:en
-
Short-container-title:Atmos. Meas. Tech.
Author:
Lee YeeunORCID, Ahn Myoung-HwanORCID, Kang Mina, Eo Mijin
Abstract
Abstract. Earth radiances in the form of hyperspectral measurements
contain 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 spectral range over the Asia–Pacific region. After completion of the in-orbit test of GEMS in October 2020, bad pixels are found as one of remaining calibration issues resulting in obvious spatial gaps in the measured radiances as well as retrieved properties. To solve the fundamental cause of the issue, this study takes an approach reproducing the defective
spectra with machine learning models using artificial neural network (ANN)
and multivariate linear regression (Linear). Here the models are trained
with defect-free measurements of GEMS after dimensionality reduction with
principal component analysis (PCA). Results show that the PCA-Linear model
has small reproduction errors for a narrower spectral gap and is less
vulnerable to outliers with an error of 0.5 %–5 %. On the other hand, the PCA-ANN model shows better results emulating strong non-linear relations with an error of about 5 % except for the shorter wavelengths around 300 nm. It is demonstrated that dominant spectral patterns can be successfully
reproduced with the models within the level of radiometric calibration
accuracy of GEMS, but a limitation remains when it comes to finer spectral
features. When applying the reproduced spectra to retrieval processes of
cloud and ozone, cloud centroid pressure shows an error of around 1 %, while total ozone column density shows relatively higher variance. As an
initial step reproducing spectral patterns for bad pixels, the current study provides the potential and limitations of machine learning methods to
improve hyperspectral measurements from the geostationary orbit.
Funder
National Research Foundation of Korea
Publisher
Copernicus GmbH
Subject
Atmospheric Science
Reference48 articles.
1. Bajorski, P.: Statistical inference in PCA for hyperspectral images, IEEE J. Sel. Top. Signa., 5, 438–445, https://doi.org/10.1109/JSTSP.2011.2105244, 2011. 2. Bak, J., Baek, K.-H., Kim, J.-H., Liu, X., Kim, J., and Chance, K.: Cross-evaluation of GEMS tropospheric ozone retrieval performance using OMI data and the use of an ozonesonde dataset over East Asia for validation, Atmos. Meas. Tech., 12, 5201–5215, https://doi.org/10.5194/amt-12-5201-2019, 2019. 3. Boersma, K. F., Eskes, H. J., and Brinksma, E. J.: Error analysis for
tropospheric NO2 retrieval from space, J. Geophys. Res.-Atmos., 109, D04311, https://doi.org/10.1029/2003jd003962, 2004. 4. Bovensmann, H., Burrows, J. P., Buchwitz, M., Frerick, J., Noël, S.,
Rozanov, V. v., Chance, K. V., and Goede, A. P. H.: SCIAMACHY: Mission
objectives and measurement modes, J. Atmos. Sci., 56, 127–150,
https://doi.org/10.1175/1520-0469(1999)056<0127:SMOAMM>2.0.CO;2, 1999. 5. Choi, H., Liu, X., Gonzalez Abad, G., Seo, J., Lee, K.-M., and Kim, J.: A
Fast Retrieval of Cloud Parameters Using a Triplet of Wavelengths of Oxygen
Dimer Band around 477 nm, Remote Sens.-Basel, 13, 152,
https://doi.org/10.3390/rs13010152, 2021.
Cited by
6 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|