Weather Classification Model Performance: Using CNN, Keras-Tensor Flow

Nowadays, automation is at its peak. The article provides a base to examine the weather through machine without human intervention. This study offers thorough classification model forecast type. Here, facilitates defining best results for prediction any climatic zones and categorizes climate into four types: cloud, rain, shine, sunrise. designs reveals using convolution neural networks (CNN) algorithms with Keras framework TensorFlow library. For practical implementations, use images dataset available from kaggle.com website. As result, this research presents performance of designed developed model. It shows accuracy, validation losses, losses approximately 94%, 92%, 18%, 22%, respectively.