TITLE:
A Comparison of ANN and HSPF Models for Runoff Simulation in Balkhichai River Watershed, Iran
AUTHORS:
Farzbod Amirhossien, Faridhossieni Alireza, Javan Kazem, Sharifi Mohammadbagher
KEYWORDS:
HSPF Model, Artificial Neural Network (ANN), Runoff Simulation, Balkhichai River Watershed
JOURNAL NAME:
American Journal of Climate Change,
Vol.4 No.3,
May
18,
2015
ABSTRACT: In this study, the capability of two
different types of models including Hydrological Simulation Program-Fortran
(HSPF) as a process-based model and ANN as a data-driven model in simulating
runoff was evaluated. The considered area is the Balkhichai River watershed in
northwest of Iran. HSPF is a semi-distributed deterministic, continuous and
physically-based model that can simulate the hydrologic cycle, associated water
quality and quantity and process on pervious and impervious land surfaces and
streams. Artificial neural network (ANN) is probably the most successful
learning machine technique with flexible mathematical structure which is
capable of identifying complex non-linear relationships between input and
output data without attempting to reach the understanding of the nature of the
phenomena. Statistical approach depending on cross-, auto- and
partial-autocorrelation of the observed data is used as a good alternative to
the trial and error method in identifying model inputs. The performances of ANN
and HSPF models in calibration and validation stages are compared with the
observed runoff values in order to identify the best fit forecasting model
based upon a number of selected performance criteria. Results of runoff
simulation indicated that the simulated runoff by ANN was generally closer to
the observed values than those predicted by HSPF.