Rainfall prediction using artificial neural network with historical weather data as supporting parameters
A H Pratomo, Budi Santosa, S P Tahalea, E T Paripurno, J D Peasetyo, Herlina Jayadianti, M F Pitayandanu
Abstract
Changing climatic patterns are caused by changes in variables, such as rainfall and air temperature that occur continuously in the long term. Rainfall itself is influenced by several weather factors such as air humidity, wind speed, air pressure, and temperature. This study experimented to test a combination of 9 additional weather parameters such as dew point, wind gusts, cloud cover, humidity, rainfall, air pressure, air temperature, wind direction, and wind speed to predict daily rainfall for one year using the main parameters of the rainfall time series. Prediction is done using Artificial Neural Network (ANN). The ANN architecture used is to use 3 to 11 input parameters, 1 hidden layer totaling 60 neurons with the ReLu activation function, and 1 neuron in the output layer without an activation function. ANN without additional weather parameters obtained an MSE of 0.01654, while prediction using additional weather parameters obtained an MSE of 0.00884. So the combination of rainfall time series parameters with additional weather parameters is proven to provide a smaller MSE value
