Image classification is an important technology in the field of computer vision, with the main objective of categorizing input images into different classes. It is used in many areas, such as weather forecasting. The significance of weather forecast image classification spans several areas, including enhancing weather forecast accuracy, aiding agriculture, optimizing the energy sector, ensuring transportation safety, and informing urban planning and construction. In this study, the author investigates the precision and efficiency of three machine learning algorithmsConvolutional Neural Network (CNN), K-Nearest Neighbor (KNN), and Visual Geometry Group 19 (VGG19)in classifying weather forecast images. The research meticulously elucidates the methodologies underlying each algorithm, outlining their distinct architectures, training processes, and feature extraction mechanisms. The research highlights that the self-built CNN model excels in accuracy and efficiency, while VGG19 achieves higher accuracy (93%) with longer training time. In contrast, the KNN model shows shorter training time (32.50 seconds) with slightly lower accuracy (80%).