CloudNet: Ground-Based Cloud Classification With Deep Convolutional Neural Network

Clouds have an enormous influence on the Earth's energy balance, climate, and weather. Cloud types have different cloud radiative effects, which is an essential indicator of the cloud effect on radiation. Therefore, identifying the cloud type is important in meteorology. In this letter, we propose a new convolutional neural network model, called CloudNet, for accurate ground-based meteorological cloud classification. We build a ground-based cloud data set, called Cirrus Cumulus Stratus Nimbus, which consists of 11 categories under meteorological standards. The total number of cloud images is three times that of the previous database. In particular, it is the first time that contrails, a type of cloud generated by human activity, have been taken into account in the ground-based cloud classification, making the Cirrus Cumulus Stratus Nimbus data set more discriminative and comprehensive than existing ground-based cloud databases. The evaluation of a large number of experiments demonstrates that the proposed CloudNet model could achieve good performance in meteorological cloud classification. Plain Language Summary With the recent progress of deep learning, an investigation is performed using convolutional neural networks (CNNs) to classify 10 typical cloud types and contrails. Although CNNs have obtained remarkable results in image classification, few works evaluate their efficiency and accuracy of cloud classification. Highly accurate and automated cloud classification approaches, especially the technology of convective cloud identification, are essential to discover a hazardous weather process. Moreover, an explicit recognition of contrails would promote the study of how the contrails impact global warming. Therefore, a discriminative and comprehensive ground-based cloud database is built for the CNNs training. The database consists of 10 categories with meteorological standards and contrails. As far as we know, it is the first time that contrails are taken into consideration as one new type of cloud in ground-based cloud classification. The total number of cloud images in our database is three times as many as that of the previously studied database. The public of this database will promote more and more research based on cloud classification. What is more, we propose the CloudNet, a new framework of CNNs, which can achieve exceeding progress compared with the conventional approaches in the ground-based cloud classification.