Open AccessAnalisa Hujan Limpasan Di Sub Das Gongseng Bojonegoro Menggunakan Jaringan Saraf Tiruan
Author(s) -
Poetri Mustika Chandy,
Ery Suhartanto,
Sri Wahyuni
Publication year - 2019
Publication title -
wahana teknik sipil/wahana teknik sipil
Language(s) - English
Resource type - Journals
eISSN - 2527-4333
pISSN - 0853-8727
DOI - 10.32497/wahanats.v24i2.1730
Subject(s) - watershed , calibration , environmental science , surface runoff , hydrology (agriculture) , computer science , statistics , mathematics , geology , machine learning , ecology , geotechnical engineering , biology
Discharge data or surface runoff data in a watershed need to be known to analyze water availability in the watershed. However, not all watersheds have measurements. Therefore, it needs analysis to transform rainfall data into discharge. This study aims to transform rainfall data into discharge using the Artificial Neural Network (ANN) method. The ANN model uses the Matlab R2014b application program. The research location is in the Gongseng Sub-watershed in Bojonegoro Regency, East Java. The data used are the number of rainy days, rainfall, runoff coefficients, and discharge data (as calibration). The data used are 12 years (2006-2017). Analysis was carried out on three (3) processes, namely calibration, verification and validation. The calculation results of the best calibration process when using 6 years of data (2006-2011) with epoch 2000 that produces an NSE value of 0.69 and an R value of 0.85. As for the verification and validation process when using 1 year of data (2017) with epoch 1000, it produces an NSE value of 0.79 (good) and an R value of 0.92 (a very strong relationship). From these results it was concluded that this method is appropriate to be applied at this research location, and also applied to other locations that have similarity condition with this watershed characteristics.