MODEL PREDIKSI TIGGI MUKA AIR SUNGAI KALI GARANG SEMARANG DENGAN JARINGAN SYARAF TIRUAN

Abstract

One of the big rivers flowing in center of Semarang city is Garang river with watershed area about 220km2 and having characteristic such as big flood discharge and flash flood. Where flash flood on January25th 1990, caused more than 45 people died and goods losses until 8.5 billion rupiahs. One of some modelsto pedict water level is used black box model. Artificial Neural Network one’s of the black bock model . Inthis research, Artificial Neural Network (ANN) with back propagation method is used to predict waterlevel in Garang river where as input are rainfall in upstream of Garang river during two days, while asoutput is water level in downstream of Garang river for two hour later. Result of optimum predicting haveMSE 0.0037 and average of error 1.18 %.