Regional Flood Analysis Via Comparison of The M5 Decision Tree Algorithm and Regression Models

Document Type : Research Paper

Authors

1 MSc of Hydrology and Water resource Engineering Department of Shahid Chamran University, Ahvaz, Iran.

2 professor, faculty member of hydrology and water resource engineering Department of Shahid Chamran University, Ahvaz, Iran

3 Assistant professor, faculty member of hydrology and water resource engineering Department of Shahid Chamran University, Ahvaz, Iran

4 Assistant professor, faculty member of Agriculture and Natural Resources University, Ahvaz, Iran

Abstract

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 a replacement to multivariate regressions.

Keywords

Main Subjects


1-البرزی، م. 1381. آشنایی با شبکه های عصبی مصنوعی، انتشارات دانشگاه صنعتی امیر کبیر. 137 صفحه.
 
2-بی‏نام. 1384. اطلس ملی منابع آب ایران. انتشارات معاونت استفاده و مدیریت منابع آب ایران.
 
3-ثروتی، م. ع. قنبری، 1386. برآورد سیلاب در حوضه رودخانه وربند لارستان. فصلنامه جغرافیایی سرزمین، علمی .14(4) 74-55.
 
4-رسول‏زاده، ع، آذرتاج، الف. و پ. فرضی. 1394. ایجاد و بررسی مدل های مختلف تحلیل منطقه ای تناوب سیلاب تابعی از دوره بازگشت(مطالعه موردی: استان اردبیل). نشریه پژوهش های حفاظت آب و خاک، 23(4): 268-261.
 
5-سلیمانی، ک و ا. یوسفی. 1380. بررسی نقش عوامل فیزیوگرافیک حوضه بر دبی های حداکثر در زیر حوضه‏های گرگان رود. مجله علوم کشاورزی و منابع طبیعی. (4)171-164.
 
6-شادمانی، م، معروفی، ص. و ک. محمدی. 1390. مدلسازی منطقه‏ای دبی سیلابی در استان همدان با استفاده از شبکه عصبی مصنوعی. مجله علوم کشاورزی و منابع طبیعی گرگان ، 18(4). 21-42
 
7-شقیعی، م. شیرزاد، م. ن. نیک نیا،1386. تحلیل منطقه ای سیلاب توسط شبکه های عصبی مصنوعی( مطالعه موردی: حوضه ماسال استان گیلان). دومین کنفرانس مدیریت منابع آب، گیلان.
 
8-علیزاده، الف. 1392. هیدرولوژی کاربردی. انتشارات دانشگاه فردوسی مشهد.
 
9-هاشمی،1382. هیدرولوژی مهندسی. انتشارات شعرا، چاپ اول.
 
10.-Aziz.K, Rahman. A , Fang.G,Shrestha.S, (2014) Application of artificial neural networks in regional flood frequency analysis: a case study for Australia, 28: 541-554
 
11-Bhattacharya, B. and D.P. Solomatine. 2005. Neural networks and M5 model trees in modelling water level–discharge relationship Journal of  Neurocomputing, 63(1): 407-412.
 
12-Boughton, W.C.1984. Flood freuency characteristics of some Arizona watersheds. Water Resources Bulletin 20(5): 761-769.
 
13- Chavoshi, S. and Eslamian, S.S., 1999. Regional flood frequency analysis in Zayandeh-Roud watershed using the Hybrid method. JWSS-Isfahan University of Technology, 3(3), pp.1-12.
 
14-Chiari, F et al. 2000; Predidtion of the Hydrologic Behavior of watershed using artificial neural network and Geographic information system. IEEE.1:382-386.
 
15-Dawson, C.W. Abrahart, R.J. Shamseldin, A.Y. and Wilby, R.L. 2006. Flood estimation at ungauged sites using artificial neural networks.  Journal of Hydrology. 319:4.  p 391-409.
 
16-Dayhoff, J.E. 1990. Neural Network Principles. Prentice-Hall International. U.S.A. 197 pp.
 
17-Dibike,Y.B. Solomatine,D. P. 2001. River flow forecasting using artificial neural networks. Physics and Chemistry of the Earth, [Journal]. - [s.l.] : Hydrology, Oceans and Atmosphere,. - 1 : Vol. 26. - pp. 1-7.
 
18- Dimitri, P. Solomatine and Yunpeng Xue. 2004.” M5 Model Trees and Neural Networks: Application to Flood Forecasting in the Upper Reach of the Huai River in China”, Journal of Hydrologic Engineering, Vol. 9, No. 6, P 491-591
 
19-Etemad-Shahidi, A. and L. Bonakdar. 2009. Design of rubble-mound breakwaters using M5′ machine learning method. Journal of Applied Ocean Research. 31(3): 197-201.
 
20-Etemad-Shahidi, A. and J. Mahjoobi. 2009. Comparison between M5′ model tree and neural networks for prediction of significant wave height in Lake Superior. Journal of Ocean Engineering. 36(15): 1175-1181.
 
21-Fausett, L. 1994. Fundamentals of neural networks architectures algorithms and applications. Prentice-Hall Inc. New Jersey. 476 pp.
 
22-Heinz, D.F. and J.R. Stedinger .  1998.  Using regional regression within index flood procedures and an empirical Bayesian estimator. Journal of Hydrology No.210. P 128-145.
 
23-Mehmed, K. 2003. Data Mining: Concepts, Models, Methods, and Algorithms. Journal of IEEE Computer Society, IEEE Press.
 
24-Mitchell, T.M. 1997. Machine Learning McGrow-Hill.
 
25-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.
 
26-Nourani V. M. Komasi. 2013. A geomorphology-based ANFIS model for multi-station modeling of rainfall-runoff process.  Journal of Hydrology,  p. 41-55.
 
27-Kurtulus, B. and M. Razack. 2010. Modeling daily discharge responses of a large karstic aquifer using soft computing methods: artificial neural network and neurofuzzy. Journal of Hydrology, 381: 101-111.
 
28-Quinlan, J.R. 1992. Learning with continuous classe. Paper presented at the Proceedings of the 5th Australian joint Conference on Artificial Intelligence, Hobart, Tasmania. 343-348.
 
29- Riad, S., and Mania, J. 2004. Rainfall Runoff Model Using an Artificial Neural Network Approach, Mathematical and Computer Modeling, 40: 839-846
 
30- Ross, T.J. 1995. Fuzzy logic with engineering application. McGraw Hill Inc. USA. p:585.
 
31-Sadheer.K.P,Gosain.A.K,Ramassastri.K.S. 2002. A data algorithm for consrusting artificial neural network rainfall-runoff models.  Journal of Hydrology. 128(16):1325-1330.
 
32- Tabari, H., Marofi, S., and Savziparvar, A.  2010. “Estimation of daily pan evaporation using artificial neural networks.
 
33-Wang, Y. and I.H. Witten. 1997. Induction of model trees for predicting continuous lasses. In Proceedings of the Poster Papers of the European Conference on Machine Learning, University of Economics. Faculty of Informatics and Statistics, Prague.
 
34-Webster, R. and M.A. Oliver. 2001. Geostatistics for Environmental Scientists. John Wiley and Sons, New York.
 
35-Zare Abyaneh, H. and M. Bayat Varkeshi. 2011. Evaluation of artificial intelligent and empirical models in estimation of annual runoff. Journal of Water and Soil. 25(2): 365-379.
 
36-Zhang, D. and J.P. Tsai. 2007. Advances in Machine Learning Applications in Software Engineering, Idea Group Inc.
Volume 40, Issue 4
February 2018
Pages 183-195
  • Receive Date: 15 July 2016
  • Revise Date: 08 October 2016
  • Accept Date: 19 October 2016
  • Publish Date: 21 January 2018