Deep Learning-Generated Nighttime Reflectance and Daytime Radiance of the Midwave Infrared Band of a Geostationary Satellite

Abstract

Midwave infrared (MWIR) band of 3.75 μm is important in satellite remote sensing in many applications. This band observes daytime reflectance and nighttime radiance according to the Earth’s and the Sun’s effects. This study presents an algorithm to generate no-present nighttime reflectance and daytime radiance at MWIR band of satellite observation by adopting the conditional generative adversarial nets (CGAN) model. We used the daytime reflectance and nighttime radiance data in the MWIR band of the meteoritical imager (MI) onboard the Communication, Ocean and Meteorological Satellite (COMS), as well as in the longwave infrared (LWIR; 10.8 μm) band of the COMS/MI sensor, from 1 January to 31 December 2017. This model was trained in a size of 1024 × 1024 pixels in the digital number (DN) from 0 to 255 converted from reflectance and radiance with a dataset of 256 images, and validated with a dataset of 107 images. Our results show a high statistical accuracy (bias = 3.539, root-mean-square-error (RMSE) = 8.924, and correlation coefficient (CC) = 0.922 for daytime reflectance; bias = 0.006, RMSE = 5.842, and CC = 0.995 for nighttime radiance) between the COMS MWIR observation and artificial intelligence (AI)-generated MWIR outputs. Consequently, our findings from the real MWIR observations could be used for identification of fog/low cloud, fire/hot-spot, volcanic eruption/ash, snow and ice, low-level atmospheric vector winds, urban heat islands, and clouds.