Rainfall Prediction Using Backpropagation with Parameter Tuning

Rainfall is one of the important elements in process weather and climate. The high intensity rainfall every year can hamper mobility population distribution goods, especially port area. prediction needed to handle impacts caused by rainfall. data was obtained from website dataonline.bmkg.go.id with observations made Tanjung Perak Surabaya Maritime Meteorological Station. method uses an artificial neural network Backpropagation. Autocorrelation function used determine number input neurons best features Artificial Neural Network. divided into two parts,: January 2008 December 2019 for training August 2020 testing data. validation technique 10-Fold Cross Validation. experiment parameter tuning iteration learning rate. rate 0.2 1000 iterations a MSE score 0.02591.Finally, has Mean Square Error value 0.02769 percentage true rain character 62.5%.