<![CDATA[This study aims to optimize the architecture of Artificial Neural Networks (ANN) for rainfall prediction using meteorological data from Indonesia, which is known for its complex and highly variable climate patterns. Climatic variables such as temperature, humidity, air pressure, wind speed, and historical rainfall records serve as the main input features to evaluate the performance of various network configurations. Optimization is carried out by determining the appropriate number of neurons, hidden layers, activation functions, and training algorithms to enhance prediction accuracy. Model evaluation employs indicators such as Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) to ensure output stability. The findings indicate that a multilayer architecture combined with optimized parameters significantly improves the network’s ability to capture non-linear patterns in Indonesia’s tropical rainfall data. The optimized model produces more stable and accurate predictions compared to standard configurations. These results highlight the importance of ANN architecture optimization in supporting early warning systems, agricultural planning, water resource management, and hydrometeorological disaster mitigation across Indonesia.]]>
Copyrights © 2025
