Cloud Classification by Machine Learning for Geostationary Radiation Imager

To enhance the accuracy of cloud classification, this study proposes cloud classification models based on machine learning algorithms. The models take as input the observed reflectance or brightness temperature of 12 channels of the Advanced Geostationary Radiation Imager (AGRI) on Fengyun-4A satellite and multichannel clear sky brightness temperature. The classification results of the cloud profiling radar (CPR)-Cloud-Aerosol Lidar with Orthogonal Polarization (CALIOP) merged product are used as the truth for training and validating the models. These models are developed to reliably detect and classify the clouds during daytime as well as for all-time (including both day and night). The results obtained from the developed models show better accuracies relative to those of the Fengyun 4A Level-2 cloud products in terms of cloud detection and classification. The models provide a feasible method for the detection of multilayer clouds and the classification of clouds at night. The applicability of cloud classification results based on CPR-CALIOP from the perspective of spectral sensitivity is analyzed on AGRI observations, providing valuable prior knowledge for cloud classification methods based on geostationary satellite imagers. The accuracies of single-layer cloud-type classification during the day and all-time are 83.4% and 79.4%, respectively. Compared with the International Satellite Cloud Climatology Project (ISCCP) classification method, the model's identification of Nimbostratus and the deep convection (Ni/DC) clouds have better consistency with precipitation observed by GPM satellite, which helps to track and monitor precipitation processes. This study also evaluates the model results using Cloud-Aerosol Lidar and Infrared Pathfinder Observation (CALIPSO) products and ground-based cloud radar, demonstrating that they can obtain accurate and robust results in different time periods and regions.