Premium
RESERVOIR DAILY INFLOW SIMULATION USING DATA FUSION METHOD
Author(s) -
Ababaei Behnam,
Mirzaei Farhad,
Sohrabi Teymour,
Araghinejad Shahab
Publication year - 2013
Publication title -
irrigation and drainage
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.421
H-Index - 38
eISSN - 1531-0361
pISSN - 1531-0353
DOI - 10.1002/ird.1740
Subject(s) - inflow , streamflow , computer science , precipitation , calibration , artificial neural network , fusion , simulation modeling , environmental science , meteorology , artificial intelligence , statistics , mathematics , drainage basin , cartography , geography , linguistics , physics , philosophy , mathematical economics
Information about the parameters defining water resource availability is a key factor in its management which improves the operation policies for water resource systems. One of the most important parameters in this area is river streamflow. In this research, two different strategies of data fusion were tested for daily inflow simulation of the Taleghan Reservoir. Four artificial neural network models as well as two Hammerstein–Wiener models were used as individual simulation models. The results showed that the data fusion method has the capacity to improve substantially the results of individual simulation models. The individual models were also tested in combination with a weather generator model which was used to generate 100 yr of daily temperature and precipitation data. The results demonstrated that although some models performed well in calibration and validation phases, in combination with a weather generator they could result in eccentric outcomes. This research also showed that the data fusion method can combine the results of single simulation models to improve the final estimate and decrease the bandwidth of errors. Copyright © 2013 John Wiley & Sons, Ltd.