Cloud Classification of Ground-based Cloud Images based on Convolutional Neural Network

Abstract

Cloud is a crucial meteorological factor, and also a key factor affecting solar radiation variables for solar energy, especially the attenuation of different cloud types on solar radiation. However, there are few researches on the cloud classification based on the ground-based cloud image in order to predict solar energy. In this paper, the ground-based cloud images were collected, and then they were classified into five classes based on colour, texture and the attenuation on the theoretical clear-sky solar radiation. The ResNet18 model was trained to classify the ground-based cloud images automatically. The experimental results show that the classification accuracy of the ResNet18 is up to 91%, which is higher than the other two convolutional neural networks (AlexNet and VGG16) and is also much higher than the traditional machine learning classifiers. This work provides a new perspective and important supporting data for solar radiation forecast.