Temporal Resolution Enhancement of COMS Satellite Using Geo-Kompsat-2A Satellite Through Data-to-Data Translation

Abstract

This study introduces a data-to-data (D2D) translation approach that utilizes a conditional adversarial learning framework to generate hypothetical data at the Meteorological Imager (MI) sensor on the Communication, Ocean, and Meteorological Satellite (COMS). The proposed D2D model produces virtual 10-minute data from actual 30-minute data by exploiting the 10-minute temporal resolution (TR) of the advanced MI (AMI) on GEO-KOMPSAT-2A (GK2A) during the overlapping observation period of the two satellites. Specifically, the D2D model uses one visible (VIS) at 0.64 µm channel and four infrared (IR) channels (3.8, 6.9, 10.8, and 12.3 µm) from AMI of the actual 30minute data from April 2020 to April 2022 to train and test the model. Subsequently, the D2D model is applied to simulate hypothetical 10 min-TR COMS data using the 30-minute COMS observation data from September 2019 to March 2020 during the coexistence period of the two satellites. Regression-calibrated COMS data alleviated the spectral response function differences between MI and AMI sensors. The proposed D2D method exhibits excellent statistical performance, with an average root mean square error of 0.056 for the VIS channel and 3.237 K,