Comparison of Artificial Neural Network Models for Rainfall Prediction in Palu City

Arya Zaki Ramadhan
Febby Debora Abigael
Muhammad Fany Nur Wibowo

Journal of Technomaterial Physics
Vol. 7 No. 1 (2025): Journal of Technomaterial Physics

Rainfall prediction is crucial to support natural disaster mitigation and water resource management, especially in areas like Palu City with dynamic rainfall patterns. This study evaluated the performance of three Artificial Neural Network (ANN) models with different architectures to identify the most accurate model in predicting rainfall in 2023. To obtain the model, the historical data of nine meteorological parameters in Palu City from 2018 to 2022 was processed using the Python programming language through pre-processing, processing, post-processing, and verification stages. All three models obtained are designed with hidden layers and different nodes. The best model obtained was Model A with one hidden layer, 8 nodes, and a MAPE value of 9.42%, putting it in the excellent category. Meanwhile, Model B and Model C are in a suitable category with MAPE values of 14.43% and 10.23%. The challenge of using the ANN method in predicting rainfall is its tendency to equalize extreme rain. Therefore, complete data is needed to improve ANN performance.