Classification of cloud images by using super resolution, semantic segmentation approaches and binary sailfish optimization method with deep learning model

Abstract

• In this study, the classification of cloud types was performed. • Super Resolution and Semantic Segmentation were used for image enhancement and efficient feature extraction. • ShuffleNet was used for feature extraction and Binary Sailfish Optimization for feature selection. • The efficiency ranking of the features was achieved with the optimization method. • Successful results were obtained with the proposed approach in the CCSN and SWIMCAT-Ext datasets. Clouds are structures formed by ice crystals, water grains, or both that come together in the atmosphere for various reasons. Clouds have a direct impact on areas such as climate, ecological balance, and air traffic. It is now inevitable to knead the devices used to detect cloud types with artificial intelligence technologies. In this process, deep learning models have begun to be used in the detection of cloud types that are the result of meteorological events. In this study, two publicly available datasets of cloud types were used. In the proposed approach, super-resolution and semantic segmentation were applied as pre-processing steps. Then, feature sets were created using the ShuffleNet model. The binary sailfish optimization method was used for efficient feature selection and classification was performed using the linear discriminant analysis method. Overall accuracy successes of 98.56% and 100% were obtained for the two datasets used for cloud type classification. It was concluded that the approach proposed in this study is successful in cloud type detection.