<![CDATA[This research focuses on developing a rainfall prediction system using the Backpropagation Artificial Neural Network (JST) method. The system is designed to predict future rainfall intensity by utilizing four main parameters: air temperature, air humidity, wind speed, and air pressure. Accurate rainfall prediction is essential in various fields, such as agriculture, transportation, and industry. Traditional systems for predicting rainfall are often unable to provide accurate and timely information. Backpropagation JST offers a promising solution to overcome this limitation. The rainfall prediction system developed using Backpropagation JST shows satisfactory performance. The system is able to predict rainfall intensity with a high degree of accuracy. These findings suggest that the Backpropagation JST-based rainfall prediction system can be a valuable tool for various sectors that require accurate and timely rainfall information. The system has the potential to improve efficiency and effectiveness in various activities, such as irrigation planning, disaster risk management, and industrial operations. This research can be extended by exploring other JST methods to improve prediction accuracy. In addition, this research can be implemented in other regions with different climatic conditions to test the generalizability of the system.]]>
Copyrights © 2024
