Severe convective weather has the characteristics of short life cycle, sudden strong,destructive,and often accompanied by a variety of catastrophic weather,to economic development, environmental protection, people′s lives and property security and other great threats.At present,the vi sual interpretation of satellite cloud images is dependent on human experience and knowledge,and there are some proble ms such as difficulty in defining the boundary of convective cloud clusters,insufficient use of multi-s pectral information in cloud images, and easy to miss and misdetect small scale convective clouds.In this paper,bas ed on FY-2G satellite′s infrared channel 1cloud image and the bright temperature difference between water vapor and infrared channel,and referring to the accurate positioning ability of U-net network in image segment ation,a new convective cloud detection method based on multi-channel feature fusion Y-type full convolution network is proposed.In this method,U-net network is transformed into Y-type full convolution network with double-channel input,and infrared channel 1cloud image and bright temperature difference image are taken as the two-channel input of Y-type network respectively.After convolution and down-sampling processing,c haracteristic information of different channels is extracted.In order to enable the network to have fine tar get detection ability,the Y-type full-convolution network retains the convolution and up-sampling structure of U-net network,and at the same time, the feature graphs of two input branches at different levels are fused through c onvolution and up-sampling,so as to realize a multi-level and multi-channel feature fusion convective cloud detect ion method.The visualization of feature maps at different levels and the comparison with fused feature maps show the effectiveness of the constructed Y-type network in utilizing feature information of different channe ls in cloud maps. The experimental results show that the accuracy,accuracy, recall and F1-measure in this paper a re 87.34%, 89.77%,82.10% and 84.82%,respectively.The performance indexes of the method in this paper are be tter than those in traditional network models such as DeconvNet and U-net.Compared with the traditional conve ctive cloud detection methods such as threshold method,bright temperature difference method and SVM,the meth od in this paper not only has obvious advantages in the edge definition of the convective cloud and the detect ion of small scale convective cloud, but also has significantly improved the detection accuracy and computational eff iciency.