<![CDATA[Changing climatic patterns are caused by changes in variables, such as rainfalland air temperature that occur continuously in the long term. Rainfall itself isinfluenced by several weather factors such as air humidity, wind speed, airpressure, and temperature. This study experimented to test a combination of9 additional weather parameters such as dew point, wind gusts, cloud cover,humidity, rainfall, air pressure, air temperature, wind direction, and windspeed to predict daily rainfall for one year using the main parameters of therainfall time series. Prediction is done using Artificial Neural Network(ANN). The ANN architecture used is to use 3 to 11 input parameters, 1hidden layer totaling 60 neurons with the ReLu activation function, and 1neuron in the output layer without an activation function. ANN withoutadditional weather parameters obtained an MSE of 0.01654, while predictionusing additional weather parameters obtained an MSE of 0.00884. So thecombination of rainfall time series parameters with additional weatherparameters is proven to provide a smaller MSE value]]>
Copyrights © 2022
