ANALISA LIMPASAN BERDASARKAN CURAH HUJAN MENGGUNAKAN MODEL ARTIFICAL NEURAL NETWORK (ANN) DI SUB DAS BRANTAS HULU

Abstract

Discharge data is usually less available than rainfall data, so it is necessary to find a relationship between river flows that are applied in the period available rainfall data in a watershed area. The purpose of this study is to determine the suitability of the method based on the analysis of data validation between the observed discharge and the model discharge. The method is done by modeling the discharge based on rainfall with the Artificial Neural Network (ANN) MATLAB R2014b program. The Upper Brantas Watershed is used as a case study because it often has runoff problems. Validation of the ANN method was tested with Root Mean Square Error (RMSE), Nash-Sutcliffe Efficiency (NSE), Correlation Coefficient (R) and Relative Error (KR). From the results of calibration using the ANN Model, the best data is found in the five years data of epoch 500. Verification results based on the value of R have a relatively good relationship between observation discharges with model discharges. The validation results show the validity in a year data of epoch 500.