ITM Web Conf.
Volume 42, 20221st International Conference on Applied Computing & Smart Cities (ICACS21)
|Number of page(s)||6|
|Published online||24 February 2022|
Weather Classification Model Performance: Using CNN, Keras-Tensor Flow
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: email@example.com
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.
Key words: Climate / Convolution Neural Network (CNN) / Keras / TensorFlow / Weather Classification Model.
© The Authors, published by EDP Sciences, 2022
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.