Evaluation of the Ability of Adaptive Neuro-Fuzzy Interface System, Artificial neural network and Regression to Regional flood analysis.

Document Type : Complete scientific research article


Msc Student in water engineering Department of Shahid Chamran University, Ahvaz, Iran


Background and Objectives: Developing of techniques for regional flood frequency estimation in ungauged sites is one of the foremost goals of contemporary hydrology. The flood frequency evaluation for ungauged catchments is usually approached by deriving suitable statistical relationships (models) between flood statistics and basins characteristics. Already, several equations have been presented to estimate the flood frequency in different areas such as Karkheh basin. However, due to the complexity of this phenomenon, the relationships have not been capable to simulate the flood frequency with desired accuracy. Accordingly, in this study, in addition to the regression method has been used in the previous studies, the ANN and ANFIS models are applied. In fact, these are a type of black box models without any knowledge of processes within the system, in which inputs are converted into outputs (or output). This situation indicates that this type of new models is actually similar to the regression relations, however, there is further flexibility in adjusting the weights and thus can be used as an replacement to multivariate regressions.
Materials and Methods: The study area, including 33 hydrometry stations, is located in the west of Iran. In this study, 27 of the stations for calibration and 6 of the stations for validation were used. To approach a unique model, return period was taken into account as the independent factor.
Results: For achieving the best ANN and ANFIS system, different combinations of physiographic with return periods, as input data, has been used. To find the important input factors of the models, sensitivity analysis has been performed in SPSS software. Accordingly, the most important independent variables were including: Return period, area, height, main stream length and slope. In the ANN model, different combinations of these inputs were compared together. It should be noted that for optimizing the connecting weights among different layers of ANN, Genetic algorithms have been used. Consequently, the best selected network is Feed-forward with the structure of 5-10-1 and R^2=0.95. In the ANFIS system, with increasing the number of input variables for each of the four membership function, including Triangular, Gaussian, Gaussian2 and trapezoidal, simulation accuracy increases. The best simulation is a triangular function with RMSE=0.1514, R^2=0.97and the number of rules is 243. Finally, by comparing models, The ANFIS model was selected as the best model. The ANFIS has the best accuracy especially in high return period. .
Conclusion: Where the sub-basins are small and their flood in different return periods is less than1000 m3/s, the regression model makes a good accordance with real flood. The ANN model has also good performance in low discharges. The regression presents its forecast in the framework of formulas and it is better and more practical for engineers. Generally, The ANFIS model is the best model for all ranges of the discharge and the best tool for prediction enormous flood in Karkheh basin.


1.Alizadeh, A. 2013. Applied hydrology. Ferdowsi University Press, 942p. (In Persian)
2.Alborzi, M. 2002. Introduction to Artificial Neural Networks. Amirkabir University of
Technology. press, 137p. (InPersian)
3.Aziz, K., Rahman, A., Fang, G., and Shrestha, S. 2014. Application of artificial neural
networks in regional flood frequency analysis: a case study for Australia, 28: 3. 541-554.
4.Boughton, W.C. 1984. Flood frequency characteristics of some Arizona watersheds.
Water resources Bulletin. 20: 5. 761-769.
5.Chavoshi, S., and Eslamian, S. 1999. Regional flood frequency analysis in Zayandeh-Roud
watershed using the Hybrid method. J. Sci. Technol. Agric. Natur. Resour. Water Soil Sci.
3: 3. 1-12.
6.Chiari, F. 2000. Predidtion of the Hydrologic Behavior of watershed using artificial neural
network and Geographic information system. IEEE. 1: 1. 382-386.
7.Dawson, C.W., Abrahart, R.J., Shamseldin, A.Y., and Wilby, R.L. 2006. Flood estimation at
ungauged sites using artificial neural networks. J. Hydrol. 319: 4. 391-409.
8.Dayhoff, J.E. 1990. Neural Network Principles. Prentice-Hall International, U.S.A., 197p.
9.Dibike,Y.B., and Solomatine, D.P. 2001. River flow forecasting using artificial neural
networks. Physics and Chemistry of the Earth. 26: 1. 1-7.
10.Dimitri, P., Solomatine., T., and Yunpeng Xue. 2004. M5 Model Trees and Neural
Networks: Application to Flood Forecasting in the Upper Reach of the Huai River in China.
J. Hydrol. Engin. 9: 6. 491-591.
11.Fausett, L. 1994. Fundamentals of Neural Networks Architectures Algorithms and
Applications. Prentice-Hall Inc, New Jersey, 476p.
12.Heinz, D.F., and Stedinger, J.R. 1998. Using regional regression within index flood
procedures and an empirical Bayesian estimator. J. Hydrol. 210: 4. 128-145.
13.Kurtulus, B., and Razack, M. 2010. Modeling daily discharge responses of a large karstic
aquifer using soft computing methods: artificial neural network and neurofuzzy. J. Hydrol.
381: 3. 101-111.
14.Nassajian Zavareh, M.H., Vafakhah, M., and Telvari, A.R. 2011. Regional Flood Frequency
Analysis in the Part of Large Central Watershed of Iran. Watershed Management Science
and Engineering. 16: 2. 49-52. (In Persian)
15.Nourani, V., and Komasi, M. 2013. A geomorphology-based ANFIS model for multi-station
modeling of rainfall-runoff process. J. Hydrol. 402: 3. 41-55.
16.Rasoulzadeh, A., Azartaj, E., and Farzi, P. 2014. Derivation and investigation of regional
flood analysis models as a function of return period (Case study: Ardabil province). J. Water
Soil Cons. 22: 4. 261-268. (In Persian)
17.Riad, S., and Mania, J. 2004. Rainfall Runoff Model Using an Artificial Neural Network
Approach,Mathematical and Computer Modeling, Delft, Netherlands, 147p.
18.Ross, T.J. 1995. Fuzzy logic with engineering application. McGraw Hill Inc. USA. 585p.
19.Sadheer, K.P., Gosain, A.K., and Ramassastri, K.S. 2002. A data algorithm for consrusting
artificial neural network rainfall-runoff models. J. Hydrol. 128: 16. 1325-1330.
20.Servati, M., and Ghanbari, A. 2007. Flood estimation for Larestan basin. Scientific -
Research Quarterly of Geographical Data. Pp: 5-74. (In Persian)
21.Shafi, M., and Serzad, M. 2006. Regional Flood Analysis using Artificial Neural Network.
second Water Resources Management Conference.
22.Shadmani, M., Marofi, S., Mohammadi, K., and Sabziparvar, A.A. 2011. Regional flood
discharge modeling in Hamedan province using Artificial Neural Network. J. Water Soil
Cons. 18: 4. 21-42.
23.Subramanya, K. Engineering hydrology. 2003. Mc Graw-Hill international edition,
New York, 126p.
24.Solaimani, K., and Yoosofi, A. Investigation of the role of physiographic factors on
investantaneous peak discharges in gorgan river sub basins for the regional flood modeling.
J. Water Soil Cons. 22: 1. 164-171. (In Persian)
25.Tabari, H., Marofi, S., and Savziparvar, A. 2010. “Estimation of daily pan evaporation using
artificial neural networks. J. Food Agric. Org. United Nations. 16: 1. 47-59.
26.The ministry of Energy. 2004. Atlas of Iranian National Water Resources. Deputy utilization
and management of water resources Press. (In Persian)
27.Zare Abyaneh, H., and Bayat Varkeshi, M. 2011. Evaluation of artificial intelligent and
empirical models in estimation of annual runoff. J. Water Soil. 25: 2. 365-379. (In Persian)