Estimation of suspended sediment using non-parametric M5 models and spline multivariate adaptive regression (MARS) (Case study: Tireh-Marbareh Rivers of Lorestan)

Document Type : Original Article

Authors

1 Assistant Professor of Water Engineering ,University of Lorestan, Khorramabad, Iran

2 M. Sc. Water structures, Khuzestan Ramin Agriculture and Natural Resources University

3 Associate Professor, Faculty of New Sciences and Technologies, University of Tehran

Abstract

In the present study, the M5 tree algorithm and MARS multivariate comparative regression have been used as new methods for estimating the suspended sediment load in comparison with the sediment measurement curve method. The information used in this study includes water flow and sediment discharge related to four hydrometric stations of Doroud and Tireh Marvak hydrometric stations on Tireh river, as well as Marbareh Doroud and Marbareh Darreh Takht on Marbareh river in Lorestan province. For fabrication and validation of the models, the flow rate with one, two and three days delay and the flow rate of the same day with rain as input parameters and the suspended sediment load flow rate were considered as output parameters. Statistical analyzes were used to evaluate the efficiency of the models and compare their results with conventional methods. In Marbareh Doroud station, the values ​​of RMSE and R2 for the M5 model were 0.47 and 0.71, respectively, and for the MARS model were 0.46 and 0.72, respectively, while in the measurement curve method they were 0.56 and 0.64 The performance of the proposed models indicates an improvement in their accuracy and ability to estimate the suspended sediment load. The results showed that the equations presented by the M5 and MARS tree models are more accurate than the measurement curve. Based on the results, it was observed that the two methods M5 and MARS have provided close answers to each other, but finally, due to the simple and conceptual structure of the M5 model, this method is a more appropriate method for estimating the suspended load in the case range. The study was selected. In addition, the study of the relationships obtained from the two models M5 and MARS showed that among the input parameters, the flow rate of the previous day and the same day were used to estimate the suspended load and the prediction values ​​were affected more than anything. These two factors have been.

Keywords

Main Subjects

References

ابراهیمی ‏محمدی، ش.، س. ح. ر. صادقی و ک. چپی. 1391. تحلیل آورد رواناب، رسوب معلق مغذی ورودی‏های مختلف به دریاچه زریوار در پایه زمانی رگبار و آب پایه. نشریه حفاظت منابع آب و خاک، 2: 74-61.
جباری، ا.، م. صمدی. 1392. کاربرد الگوریتم M5 در پیش‏بینی عمق آبشستگی در پایین دست سریزها. نشریه وزارت نیرو.
حزباوی، ز.، س.ح.ر. صادقی و ح.ا. یونسی. 1391 . تحلیل و ارزیابی تأثیرپذیری مؤلفه های روا نآب از کاربرد سطوح مختلف پلی آکریل آمید. نشریه حفاظت منابع آب و خاک، نشریه حفاظت منابع آب و خاک. 2(2): 14-1.
دهقانی، ا.، م. ملک‏محمدی و ا. هزارجریبی. 1389. تخمین بار معلق رودخانه بهشت آباد با استفاده از شبکه عصبی مصنوعی. مجله پژوهش‏های حفاظت آب و خاک. 1(17): 168-159.
ظهیری، ج. 1394. کاربرد مدل‏های ناپارامتریک CART و M5 در محاسبه عمق آبشستگی اطراف پایه‏های پل. مجله کرمان، 5(20): 50-35.
شاهرخی، س. ح.، ج. ظهیری و ا. جعفری. 1395. کاربرد الگوریتم درختی M5 در برآورد رسوب معلق رودخانه­ها. نشریه علمی پژوهشی مهندسی آبیاری و آب ایران. 6 (4): 28-16.
 
 
 
Abraham, A., D. Steinberg, N. S. Philip. 2001. Rainfall forecasting using soft computing models and multivariate adaptive regression splines IEEE SMC Transactions, Special Issue on Fusion of Soft Computing and Hard.
Achite, M., S. Ouillon. 2007. Suspended sediment transport in a semiarid watershed, Wadi Abd, Algeria (1973–1995). Journal of Hydrology, 343: 187-202.
Adamowski, J., H. F. Chan,  S. O. Prasher, V.N. Sharda. 2012. Comparison of multivariate adaptive regression splines with coupled wavelet transform artificial neural networks for runoff forecasting in Himalayan micro-watersheds with limited data. Journal of Hydroinformatics 14(3): 731-744.
Bahmani, B., B. M. Taha, J. Ouarda. 2020. Groundwater level modeling with hybrid artificial intelligence techniques. Journal of Hydrology, https://doi.org/10.1016/j.jhydrol.2020.125659.
Etemad-Shahidi, A., N. Ghaemi, 2011. Model tree approach for prediction of pile groups scour due to waves. Journal of Ocean Engineering, 38, 1522–1527.
Etemad-Shahidi, A., J. Mahjoobi. 2009. Comparison between M5΄ model tree and neural networks for prediction of significant wave height. Journal of Ocean Engineering, 36(15-16): 1175-1181.
Etemad-Shahidi, A., M. Taghipour. 2012. Predicting longitudinal dispersion coefficient in natural streams using M5′ model tree. Journal of Hydraulic Engineering, 138(6): 542-554.
García-Nietoa, P.J., E. García-Gonzaloa, J.R. Alonso Fernándezb, C. Díaz Muñizb. 2019. Modeling algal atypical proliferation using the hybrid DE–MARS–basedapproach and M5 model tree in LaBarca reservoir: A case study in northernSpain. Journal homepage.
Ghaemi, A., M. Rezaie-Balfa, J. Adamowskib, O. Kisic, J. Quiltyb. 2019. On the applicability of maximum overlap discrete wavelet transformintegrated with MARS and M5 model tree for monthly pan evaporationprediction. Journal homepage. https://doi.org/10.1016/j.agrformet.2019.107647.
Haghiabi, A. H. 2016. Prediction of longitudinal dispersion coefficient using multivariate adaptive regression splines. J Earth Syst Sci 125:985–995.
Heddam, S. 2021.New formulation for predicting soil moisture content using only soil temperature as predictor: multivariate adaptive regression splines versus random forest, multilayer perceptron neural network, M5Tree, and multiple linear regression. Journal Water Engineering Modeling and Mathematic Tools, Pages 45-62, https://doi.org/10.1016/B978-0-12-820644-7.00027-XGet rights and content.
Quinlan, J. R. 1992. Learning with continuous classes. Proc., 5th Australian Joint Conf. on Artificial Intelligence, World Scientific, Singapore, 343–348.
Rachit, S., A.N. Tiwari, V.K. Giri. 2019. Solar radiation forecasting using MARS, CART, M5, and random forestmodel: A case study for India. Journal homepage. https://doi.org/10.1016/j.heliyon.2019.
Rajaee, T., h. Jafari. 2020. Two decades on the artificial intelligence models 2advancement for modeling river sediment concentration: 3State-of-the-art. Journal of Hydrology. https://doi: https://doi.org/10.1016/j.jhydrol.2020.125011.
Sadegh Safar, M. J. 2020. Hybridization of multivariate adaptive regression splines and random forest models with an empirical equation for sediment deposition prediction in open channel flow. Journal Pre-proofs, S0022-1694(20)30852-0, https://doi.org/10.1016/j.jhydrol.2020.125392.
Samadi, M., E. Jabbari, H. M. Azamathulla, M. Mojallal. 2015. Estimation of scour depth below free overfall spillways using multivariate adaptive regression splines and artificial neural networks. Eng ApplComp Fluid 9:291–300. https://doi.org/10.1080/19942060.2015. 1011826.
Wang, Y., I. H. Witten, 1997. Induction of Model Trees for predicting Continuous Classes. Proceedings of the Poster Papers of the European Conference on Machine Learning, University of Economics, Faculty of Informatics and Statistics, Prague.
Yang, C.T., R. Marsooli, M. Taghi Aalami. 2009. Evaluation of total load sediment transport formulas using ann. International Journal of Sediment Research, 24, 274-286.
Yilmaz, B., E. Aras, S. Nacar, M. Kankal. 2018. Estimating suspended sediment load with multivariate adaptive regression spline, teaching-learning based optimization, and artificial bee colony models. Sci Total Environ 639:826–840. https://doi.org/10.1016/j.scitotenv.2018.05.153.
Zahiri1, Z., H. Nezaratian. 2020. Estimation of transverse mixing coefficient in streams using M5, MARS, GA, and PSO approaches. Springer-Verlag GmbH Germany, part of Springer Nature 2020.
Zhang, W., A.T.C. Goh. 2016. Multivariate adaptive regression splines and neural network models for prediction of pile drivability. Geosci Front 7:45–52. https://doi.org/10.1016/j.gsf.2014.10.003.
Zheng, G., W. Zhang, H. Zhou, P. Yang. 2020. Multivariate adaptive regression splines model for prediction of the liquefaction-induced settlement of shallow foundations. Journal homepage https://doi.org/10.1016/j.soildyn.2020.106097.

Files

Share

How to cite

Statistics