Monthly Rainfall Prediction Using the Backpropagation Neural Network (BPNN) Algorithm in Maros Regency

Purpose: This study aims to identify the right combination of network architecture, learning rate, and epoch in making predictions at each rainfall post Maros Regency. In addition, this also predicts monthly profile 2021-2025 Regency.Methods: The method is backpropagation neural algorithm learn predict data. BPNN one most commonly used non-linear methods recently. data from 2000-2020 as training testing four stations including BPP Batubassi, Staklim Maros, Stamet Hasanuddin, Tanralili.Result: results showed that obtained was different. highest level prediction accuracy on 5 layers rather than 3 or 4 architecture with respectively 76.91%, 72.47%, 75.24%, 76.53%. are following monsoon rain pattern January 2025 964.1 mm, while largest annual 2023 a total 3359.6 mm.Novelty: study, various combinations parameters consisting epoch, different results. Particularly Regency, suitable for use predicting Batubassi rate 0.7, 50000, 11-6-10-7-5, 0.5, 11-5-9-10-5, Hasanuddin 0.8, 20000, 11-5-8-6-5, Tanralili 10000, 11-5-9-9-5 architecture.