Comparison of CCA and MICCA Approaches for Choice of Optimum Rainfall Inputs Rainfall-Runoff Modeling in a Catchment (Case study: Kermanshah Qarasoo Catchment)

Document Type : Original Article

Authors

1 Water Resources Engineering, University of Shahid Bahonar, Kerman, Iran

2 Graduate of Hydraulic Structures, Department of Water Engineering, University of Tabriz, Tabriz

3 Assistant Professor, Department of Water Engineering, University of Tabriz, Tabriz

Abstract

In this study, two different input selection methods cross-correlation analysis (CCA), and a combination of mutual information and cross-correlation analyses (MICCA) were used to develop adaptive network-based fuzzy inference system (ANFIS) in Qarasoo basin, in Kermanshah province, Iran. Sixteen daily rainfall-runoff events 10-yearly (2006-2015) were selected which 12 events were used for calibration (training) and the remaining 4 events were reserved for validating (testing) the models. Then, the results of ANFIS models then were compared against the HEC-HMS conceptual model. Investigation statistical indices showed that ANFIS model developed based on MICCA input (ANFIS-MICCA) better performance (CE=0.99 and RPE=10.09%) than the developed based on CCA inputs (ANFIS-CCA) (CE=0.88 and RPE=15.41%). ANFIS-CCA and ANFIS-MICCA were able to perform comparably to HEC-HMS model where rainfall data of all 8 stations; however, in peak estimation, ANFIS-MICCA was the suitable model. Also, the results show that the HEC-HMS model performance deteriorates by reducing the number of rainfall stations to two and three stations 59.8% and 54.6% percent, respectively. In general, ANFIS was found to be a reliable alternative for HEC-HMS in cases whereby not all rainfall stations are functioning.

Keywords

References

simulation for an overland plane: Journal of Hydrology. 357.3: 337-348.
Coulibaly,P., Anctil,F and Bob,B. 2000. Daily reservoir inflow forecasting using artificial neural networks with stopped training approach. Journal of Hydrology. 230.4:244-257.
Da Costa Couto,M.P. 2009. Review of input determination techniques for neural network models based on mutual information and genetic algorithms. Neural Computing and Applications. 18.8:891-901.
Dawson,C.W., See,L.M., Abrahart,R.J and Heppenstall,A.J. 2006. Symbiotic adaptive neuro-evolution applied to rainfall–runoff modelling in northern England. Neural Networks. 19.2:236-247.
El Hassan,A.A., Sharif,H.O., Jackson,T. Chintalapudi,S. 2013. Performance of a conceptual and physically based model in simulating the response of a semi-urbanized watershed in San Antonio, Texas. Hydrological Processes.
27:3394-3408.
Ghose,D., Panda,P., Swain,P. 2013. Prediction and optimization of runoff via ANFIS and GA. Alexandria Engineering Journal. 52.2: 209-220.
He,J., Valeo,C., Chu,A and Neumann,N.F. 2011. Prediction of event-based stormwater runoff quantity and quality by ANNs developed using PMI-based input selection: Journal of Hydrology. 400.1: 10-23.
Hosseini,S.M and Mahjouri,N. 2016. Integrating support vector regression and a geomorphologic artificial neural network for daily rainfall-runoff modeling. Applied Soft Computing. 31.38:329-345.
Jang,J.S.R. 1993. ANFIS: adaptive-network-based fuzzy inference system: Systems, Man and Cybernetics, IEEE Transactions on. 23.3:665-685.
Moon,Y.I., Rajagopalan,B and Lall,U. 1995 Estimation of mutual information using kernel density estimators. Physics Review. 52.3:2318-2321.
Motahari,M and Mazandaranizadeh,H. 2017. Development of a PSO-ANN Model for Rainfall-Runoff Response in Basins, Case Study: Karaj Basin. Civil Engineering Journal. 3.1:35-44.
Mukerji,A., Chatterjee,C and Singh Raghuwanshi,N. 2009. Flood forecasting using ANN, neuro-fuzzy, and neuro-GA models. Journal of Hydrologic Engineering. 14:647-652.
Iranian Journal of Irrigation & Drainage
Volume 11, Issue 5 - Serial Number 65
January and February 2018
Pages 923-934

Files

Share

How to cite

Statistics