A new snow cover mapping algorithm for Chinese geostationary meteorological satellite FY-4A AGRI data

Abstract

ABSTRACT China’s second generation of geostationary meteorological satellites Fengyun-4 (FY-4) are equipped with the Advanced Geosynchronous Radiation Imager (AGRI) which has the advantages of large number of spectral bands and high temporal resolution. To fully leverage these features, a new snow cover (SC) mapping algorithm was proposed, which firstly derives SC map from a single scene image and then combines multi-temporal SC results within one day into a daily SC composite. The novelty of the proposed algorithm includes the utilization of small spatial and temporal divisions to avoid the use of complex kernel-driven models for the correction of bidirectional effects of surface reflectance and a novel framework to merge multi-temporal SC maps by weighting the solar illumination conditions. The SC results were validated against in-situ snow depth measurements, Landsat 8 derived SC data and MODIS SC products. Results indicate that merging multi-temporal SC data can reduce cloud obscuration with the average daily cloud coverage percentage decreasing from about 47.03% for single scene to 35.62% for merged one and slightly improve snow detection accuracy. The overall accuracy (OA) ranges from 95.00% to 96.19%, and the F-score (FS) varies from 77.78% to 87.14% when compared to different reference data, suggesting an overall good performance.