Application of the M5 Model Tree in Energy Dissipation Prediction over Gabion-Stepped Weirs

Subject Areas : Article frome a thesis

F. نهرین ¹ , M.T ستاری ² , F. سلماسی ³

1 - دانشجوی کارشناسی ارشد، گروه مهندسی آب، دانشکده کشاورزی، دانشگاه تبریز
2 - عضو هیئت علمی گروه مهندسی آب، دانشکده کشاورزی، دانشگاه تبریز
3 - عضو هیئت علمی گروه مهندسی آب، دانشکده کشاورزی، دانشگاه تبریز

Received: 2014-03-01 Accepted : 2014-03-01 Published : 2014-02-20

Keywords: energy dissipation, Data mining, M5 Model Tree, stepped weir gabion,

Abstract :

Gabion structures are commonly used in water- related projects, especially as weirs. The unique structure of these weirs increases the rate of energy dissipation and reduces the construction costs of stilling basins. The permeable gabion weirs might have less negative impacts on the environment than most of the solid weirs. In this paper, the ability of M5 model in estimating energy dissipation over gabion-stepped weirs has been assessed. The M5 model has two options: M5P and M5Rule, although very similar, they differ in the manner of yielding of outputs. To assess the precision of these 2 models, the data collected on energy dissipation over 8 physical models were analyzed. Results showed that the M5Rule model, as a technique of data mining, had a good performance in predicting energy dissipation over gabion-stepped weirs. Moreover, the discharge and the height of the weirs were the most effective parameters in energy dissipation. Comparing the results of M5 model and the logistic linear regression method proved the rigorous power of M5 method in predicting energy dissipation over and through gabion-stepped weirs.

References:

4- Alberg, D., M. Last, and A. Kandel. 2012.
Knowledge discovery in data streams with
regression tree methods. WIREs Data
Mining Knowl. Discov. 2: 69-78
DOI:10.1002/widm.51.
5- Bhattacharya, B., and D.P. Solomatine.
2004. Neural networks and M5 model
trees in modeling water level-discharge
relationship. Department of
Hydroinformatics and Knowledge
Management,NESCO-IHE Institute for
Water Education, P.O. Box 3015,2601 DA
Delft,the Netherlands.
6- Ditthakit, P., and C.H. Chinnarasri. 2012.
Estimation of pan coefficient using M5
model tree. Am.J.Environ.Sci. 8: 95-103.
7- Kells, J.A. 1993. Discussion of spatially
varied flow over rockfill embankments.
Can. Civ. Eng. 20: 820-827.
8- Mohamed, H.I. 2010. Flow over gabion
weirs. J. Irrig. Drain. Eng. Div. ASCE
136:573-577.
9- Pal, M. 2006. M5 model tree for land
cover classification. Int.J.Remote Sens. 27:
825-831.
10- Pal, M., and S. Deswal. 2009. M5 model
tree based modeling of reference
evapotranspiration. Hydrol. Process 23:
1437-1443.
11- Peyras, L., P. Royet, and G. Degoutte.
1992. Flow and energy dissipation over
stepped gabion weirs. J. Hydraul. Eng.
Div. ASCE. 118: 707-717.
86 پیش تیٌی اتالف کارهایِ در سرریس تَری سٌگی پلِ ای تا استفادُ از شثیِ درختیM5
12- Quinlan, J.R. 1992. Learning with
continuous classes. In N. Adams & L.
Sterling (Eds.), proceedings of the 5th
Australian Joint Conference on artificial
Intelligence, Hobart, TAS, pp. 343-348.
Singapore: World Scientific.
13- Salmasi, F., M.T. Sattari, and M. Pal.
2012. Application of data mining on
evaluation of energy dissipation over low
gabion-stepped weir. Turk. J. Agric. 3695-
106 TUBITAK DOI:10.3906/tar-1011-
1506.
14- Sattari, M.T., A.S. Anli, H. Apaydin, and
S. Kodal 2012. Decision trees to determine
the possible drought periods in Ankara.
Atmosfera 25: 65-83.
15- Singh, K.K., M. Pal, and V.P. Singh. 2010.
Estimation of mean annual flood in Indian
catchment using backpropagation neural
network and M5 model tree. Water resour.
Manage. 24 DOI:10.1007/s11269-009-
9535-x
16- Solomatine, D.P., and Y. Xue. 2004. M5
model trees and neural networks:
Application to flood forecasting in the
upper reach of the Huai River in China. J.
Hydrol. Eng. 9: 491–501.
17- Stephenson, D. 1979. Gabion energy
dissipaters. 13th Int. Cong. on Large Dams.
New Delhi. India. Q.50, R. (3): 33-34.
18- Stravs, L., and M. Brilly. 2007.
Development of a low-flow forecasting
model using the M5 machine learning
method. Hydrolog. Sci. J. 52: 466-477.
19- Yurekli, K., M.T. Sattari, A.S. Anli, and
M.A. Hinis. 2012. Seasonal and annual
regional drought prediction by using datamining approach. Atmosfera 25: 85-105.

_||_