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

¹ Department of Information Technology, College of Engineering & Computer Science, Lebanese French University, Erbil, Kurdistan, Iraq
² Department of Accounting, College of Administrative and Financial Science, Knowledge University, Erbil, Kurdistan, Iraq

^* Corresponding author: ashish.sharma@lfu.edu.krd

Abstract

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