Evaluation of the Efficiency of Different Artificial Intelligence and Statistical Methods in Estimating the Amount of Runoff 
(Case Study: Shahid Noori Watershed of Kakhk, Gonabad)

Zarei, Mohammad mehdi; Dastorani, Mohammad taghi; Mesdaghi, Mansour; Eshghizadeh, Masoud

doi:10.29252/jwmr.8.16.11

Volume 8, Issue 16 (2-2018) jwmr 2018, 8(16): 11-21 | Back to browse issues page

‎ 10.29252/jwmr.8.16.11

Mendeley

Zotero

RefWorks

Zarei M M, Dastorani M T, Mesdaghi M, Eshghizadeh M. (2018). Evaluation of the Efficiency of Different Artificial Intelligence and Statistical Methods in Estimating the Amount of Runoff (Case Study: Shahid Noori Watershed of Kakhk, Gonabad) . jwmr. 8(16), 11-21. doi:10.29252/jwmr.8.16.11
URL: http://jwmr.sanru.ac.ir/article-1-900-en.html

Evaluation of the Efficiency of Different Artificial Intelligence and Statistical Methods in Estimating the Amount of Runoff (Case Study: Shahid Noori Watershed of Kakhk, Gonabad)

Mohammad mehdi Zarei

, Mohammad taghi Dastorani

, Mansour Mesdaghi

, Masoud Eshghizadeh

Abstract: (4197 Views)

Rainfall-runoff models are used in the field of hydrology and runoff estimation for many years, but despite existing numerous models, the regular release of new models shows that there is still not a model that can provide sophisticated estimations with high accuracy and performance. In order to achieve the best results, modeling and identification of factors affecting the output of the model is necessary. In this regard, in present study, it has been tried to identify the factors and estimating the amount of runoff using a variety of methods of artificial intelligence and multiple regression. Then, to evaluate the efficiency of the implemented models and choose the best model, some performance criteria including the correlation coefficient (R), Nash-Sutcliffe coefficient (NSE), the root mean square error (RMSE) and the mean absolute error (MAE) were used . The data used in this study were 9 rainfall events data measured in time period of 2011- 2015 taken from the Khakh watershed of Gonabad. Artificial intelligence models used in this study were: normal feedforward neural networks, feedforward Cascade neural networks, feedbackward Elman neural networks, Adaptive Neuro Fuzzy Inference System (ANFIS) and regression decision tree model (Regerssion Tree) that were implemented in MATLAB software environment and also step multiple regression as statistical methods which was implemented in Minitab software. The results of this study showed that the used statistical and artificial intelligence methods are considered acceptable with almost similar performance and with relatively appropriate accuracy and low error they are able to estimate the amount of runoff. In the meantime, Cascade and normal feedforward neural models with 5 input parameters, presented better performance comparing to the other models, as the performance criteria of R, RMSE, NSE and MAE in these models were the similar values of 0.88 , 0.76, 2 and 1.5, respectively. Overall, the findings indicate better estimations of the artificial intelligence models comparing to the regression model.

Keywords: Modeling, Neural Networks, Decision trees, ANFIS, Backpropagation, Feedforward, Feedbackward

Full-Text [PDF 557 kb] (3010 Downloads)

Type of Study: Research | Subject: Special
Received: 2018/01/29 | Revised: 2018/02/25 | Accepted: 2018/01/29 | Published: 2018/01/29

References

1. Akbari, Z., A. Talebi, M.T. Dastorani, J. Mahjubi and B. Akbari, 2013. The impact of sediment flows classification on accurately suspended sediment estimation using decision tree models. The first national conference on achieving sustainable development in agriculture, natural resources and environment sectors, Tehran (In Persian).

2. Asadi, S., J. Shahrabi, P. Abbaszadeh and S. Tabanmehr. 2013. A new hybrid artificial neural networks for rainfall-runoff process modeling. Neurocomputing, 121: 470-480. [DOI:10.1016/j.neucom.2013.05.023]

3. Babanejad, T. 2012. The use of genetic algorithms in adaptive fuzzy-neural system to estimate the sediment in the river, Ninth International River Engineering Seminar, Shahid Chamran University of Ahvaz, Iran, February 2012, (In Persian).

4. Bhattacharya, B., R.K. Price and D.P. Solomatine. 2007. Machine learning approach to modeling sediment transport. Journal of Hydraulic Engineering. 133(4): 440-450. [DOI:10.1061/(ASCE)0733-9429(2007)133:4(440)]

5. Chen, J.C., S.K. Ning, H.W. Chen and C.S. Shu. 2008. Flooding probability of urban area estimated by decision tree and artificial neural networks, Journal of Hydroinformatics, 10(1): 57-67. [DOI:10.2166/hydro.2008.009]

6. Dastorani, M.T, A. Habibpour, M.R. Ekhtesasi, A. Talebi and J. Mahjubi, 2013. Evaluation of the Decision Tree Model in Precipitation Prediction (Case study: Yazd Synoptic Station), Iran Water Resources Research, No: 3, pp. 14-27. (In Persian).

7. Dastorani M.T., Kh. Azimi Fashi, A. Talebi and M.R. Ekhtesasi, 2012. Estimation of Suspended Sediment Using Artificial Neural Network (Case Study: Jamishan Watershed in Kermanshah). Journal of watershed management research, 6: 61-74 (In Persian).

8. Dastorani M.T., H. Sharifi Darani, A.Talebi and A.R. Moghaddamnia, 2011. "Evaluation of the application of artificial neural networks and adaptive neuro-fuzzy inference systems for rainfall-runoff modeling in Zayandeh_rood dam basin, Journal of Water and Wastewater, 4: 114-125 (In Persian).

9. Dorum, A., A. Yarar, M. Faik Sevimli and M. Onüçyildiz. 2010. "Modelling the rainfall-runoff data of susurluk basin." Expert Systems with Applications 37(9): 6587-6593. [DOI:10.1016/j.eswa.2010.02.127]

10. Ekhtessasi, M., M .Yusefi and M. Tavakkoli, 2015. Comparing the Best Input Combining Artificial Neural Networks and Decision Tree Method to Identify Factors that Influence the Phenomenon of Dust Storm (Case Study Yazd Province), Journal of Watershed Science and Engineering. 9 (28), 33-40, (In Persian).

11. Eshghi, P., J. Farzadmehr, M.T. Dastorani and Z. Arab Asadi. 2016. The effectiveness of intelligent models in estimating the river suspended sediments (Case study: Babaaman basin, Northern Khorasan), Journal of watershed management research, No. 14, 88-95 (In Persian). [DOI:10.29252/jwmr.7.14.95]

12. Eshghizadeh, M. 2011, The Review of the pair watersheds of Kakhk, Gonabad, Department of Natural Resources and Watershed Management of Gonabad (In Persian)

13. Fathollahi, S., D. Mirshahi and B. Abbaspoor, 2015. Prediction of runoff resulted from rainfall in Ajichai river basin, using neural networks. The first International Congress on Irrigation and Drainage, Ferdowsi University of Mashhad. Iran. (In Persian)

14. Goswami, M and K.M. O'Connor, 2005. Application of Artificial Neural Networks for river flow simulation in three French catchments.4th Inter-Celtic Colloquium on Hydrology and Management of Water Resource. National University of Ireland, Galway, Ireland.

15. Habibipour, A., M.T. Dastorani, M.R. Ekhtesasi, H. Afkhami, 2011. Evaluation of the Effects of Data range Modification on Efficiency of Regression Decision Tree and Artificial Neural Networks for Drought Prediction, Journal of watershed management research, 3: 63-79 (In Persian).

16. Hajjahbakhsh, C., 1390. Estimation of bed load sediment using regression decision trees, and comparing with experimental methods, MSC Thesis, Department of Civil Engineering, Yazd University, Iran, 103 pp. (In Persian).

17. Hamzaçebi, C. 2008. Improving artificial neural network's performance in seasonal time series forecasting. Information Sciences 178 (23): 4550-4559. [DOI:10.1016/j.ins.2008.07.024]

18. Hung, N. Q., M. S. Babel, S.Weesakul, and N. K. Tripathi. 2008. An articial neural network model for rainfall forecasting in Bangkok, Thailand. Hydrology and Earth System Sciences Discussions, 5(1): 183-218. [DOI:10.5194/hessd-5-183-2008]

19. Jang, J. S.R. 1993. ANFIS: Adaptive-network-based fuzzy inference system. J. of IEEE. Trans. Syst. Man, Cyber, 23(3): 665-685. [DOI:10.1109/21.256541]

20. Janikow, Z and M. Fajfer, 2000. Bottom- up Fuzzy Partitioning in Fuzzy Decision Trees. Fuzzy Information Processing Society, NAFIPS. 19th International Conference of the North American.

21. Jeong, C.S., W.J. Koh and J.H. Heo. 2000. A study on real-time forecasting of reservoir inflow based on artificial neural network. Proceedings of Watershed Management and Operations Management 2000 conference, American Society of Civil Fngineers, USA [DOI:10.1061/40499(2000)82]

22. Karamouz, M and S. Araghinejad. 2011. Advanced Hydrology. Amirkabir University of Technology Press. Tehran. Iran. (In Persian).

23. Kia, M. 2010. Neural networks in MATLAB, Third Edition, published by Kian-Rayaneh-Sabz, 229 p. (In Persian).

24. Meshkani, A. and A.Nazemi. 2009. Introduction to Data Mining, Ferdowsi University of Mashhad Press, Mashhad (In Persian).

25. Nourani, V., Ö. Kisi and M. Komasi. 2011. "Two hybrid Artificial Intelligence approaches for modeling rainfall-runoff process." Journal of Hydrology 402(1-2): 41-59. [DOI:10.1016/j.jhydrol.2011.03.002]

26. Nourani, V., M.A. Kynejad and L. Malekani. 2010. "The use of Adaptive Neural - fuzzy systems in Modeling of rainfall - runoff." Journal of Civil and Environmental Engineering, University of Tabriz 39(4): 75-81. (In Persian).

27. Qaderi, M. 2012. Development of hydrological model for simulation of rainfall-runoff from hill slopes and small catchments (Case study: Sanganeh station, Khorasan Razavi), MSc thesis, Faculty of Natural Resources, Yazd University, Iran (In Persian).

28. Senthil Kumar, A., C. Ojha, M. Goyal, R.Singh and P. Swamee, 2012, "Modeling of Suspended Sediment Concentration at Kasol in India Using ANN, Fuzzy Logic, and Decision Tree Algorithms". Journal of Hydrologic Engineering, 17(3), 393-404. [DOI:10.1061/(ASCE)HE.1943-5584.0000445]

29. Sharpley, A. and P. Kleinman. 2003. Effect of rainfall simulator and plot scale on overland flow and phosphorustransport. Journal of Environtal Quality 32: 2172- 2179 [DOI:10.2134/jeq2003.2172]

30. Shayegh, M. 1390. Cloud seeding project evaluation using decision trees regression model (case study: in central Iran, Fars province), MSc thesis, Water and Power Industry University, Tehran. Iran. (In Persian).

31. Solgi, A., F. Radmanesh, A. Pourhaghi and M. Bagherian. 2014. Evaluation of Artificial Intelligence Systems Performance in Precipitation Forecasting. TI Journals Agriculture Science Developments. 3 (7): 256-264.

32. Talei, A., L.H.C. Chua, C. Quek and P.E. Jansson. 2013."Runoff forecasting using a Takagi-Sugeno neuro-fuzzy model with online learning." Journal of Hydrology 488(0): 17-32. [DOI:10.1016/j.jhydrol.2013.02.022]

33. Tamari, S., J. H. M. Wosten and J. C. Ruz-suarez, 1996. Testing an artificial neural network -for predicting soil hydraulic conductivity. Journal of Soil Science Society of America, 60, 1732 .1741. [DOI:10.2136/sssaj1996.03615995006000060018x]

34. Vahabi, J. and M.H. Mahdian. 2008. Rainfall simulation for the study of the effects of efficient factors on runoff rate. Current Sci. 95: 1439-1445.

35. Yousefi, M. and F. Barzegar, 2013. Suspended sediment comparative study using a decision tree model and sediment curve (Case Study: Lorestan) Journal of Watershed management Research (Pajoohesh and Sazandegi), in press. (In Persian).