PEMODELAN PENELUSURAN BANJIR MENGGUNAKAN METODE ADAPTIVE NEURO FUZZY INFERENCE SYSTEM PADA SUNGAI ROKAN KANAN

Abstract

Flood is an occurence that marked with the increase in the water exceeds the capacity of volume water reservoir
such as a river or water channel, factors that cause flooding in terms of meteorology are high rainfall and sea
water was high, resulting in high water level increases. Flood predictable with see natural phenomena such as
rainfall. One of method for flood prediction is with flood routing method.
Flood routing is done as a means to reduce an adverse impact by flooding, Flood Routing is a hydrograph flow
omputation in a downstream stream based on hydrograph flow of an upstream location. The purpose of this study
is to develop flood routing model in the Rokan Kanan river with use softcomputing Adaptive Neuro Fuzzy Inference
System (ANFIS).
The data used in this research is secondary data 2014 to 2016 year, Data of Rokan Kanan river were collected
from BWS Sumatera III in Pekanbaru. The Scenarios date used in this research is Q t+0, Q t+4, Q t+8, Q t+12
and Q t+16 with used variation of data comparison training and testing 70% : 30%, 60% : 40%, 80% : 20% and
50% : 50%. The results of this flood routing study in Rokan Kanan river, produce a correlation value of R =
0,6074 obtained during the use of data scenarios Q t+12 with used variation of data 80% : 20% and is classified
as a strong correlatioan.