An ai approach to ensuring consistency of albedo products from COMS/MI and GK-2A/AMI

Abstract

ABSTRACTSatellite-based surface albedo data are widely used to monitor and analyse the global climate and environmental changes. Korea continuously retrieves surface albedo from the Communication, Ocean and Meteorological Satellite (COMS)/Meteorological Imager sensor (MI) and GEO-KOMPSAT-2A (GK-2A)/Advanced Meteorological Imager sensor (AMI). However, the quality of these surface albedo outputs differs due to differences in the algorithms, input data and resolution, which limits their long-term use as climate data. By analyzing errors in the surface albedo data from COMS/MI and GK-2A/AMI and applying corrections, continuous climate monitoring can be enhanced. This study developed a correction model based on machine learning using multiple linear regression (MLR), random forest (RF) and deep neural network (DNN) models to consider the albedo data error characteristics of each satellite. The best performing RF model was used for correction. The errors of the corrected RF COMS/MI data were reduced; when validated with in-situ data, the Root Mean Square Error (RMSE) of the COMS/MI improved from 0.056 to 0.023, similar to the RMSE of 0.019 of GK-2A/AMI. It also showed stability in the time series validation with GLASS satellite data, with a consistent mean RMSE of 0.036.KEYWORDS: Surface AlbedoGK-2A/AMICOMS/MIAERONETGLASSCorrectionMachine learning Disclosure statementNo potential conflict of interest was reported by the author(s).Notes1. The English in this document has been checked by at least two professional editors, both native speakers of English. For a certificate, please see: (http://www.textcheck.com/certificate/iFW2k3)Additional informationFundingThis work was funded by the Korea Meteorological Administration’s Research and Development Program “Technical Development on Weather Forecast Support and Convergence Service using Meteorological Satellites” under Grant (KMA2020-00120).