Modeling Estimation of Suspended Sediment Rate in Pasikhan River Using Decision Tree Artificial Neural Network

Subject Areas : Farm water management with the aim of improving irrigation management indicators

سیدسامان Nasiri ¹ , Ebrahim Amiri ² , محبوبه shadabi ³

1 - Department of Water Engineering, Lahijan Branch, Islamic Azad University, Lahijan, Iran
2 - Professor, Department of Water Engineering, Lahijan Branch, Islamic Azad University, Lahijan, Iran
3 - Department of Water Engineering, Lahijan Branch, Islamic Azad University, Lahijan, Iran.

Received: 2019-09-25 Accepted : 2020-07-01 Published : 2021-02-19

Keywords: Suspended sediment, Psikhan river, Artificial Neural Network, Modeling, Decision tree,

Abstract :

Accurate estimation of sediment transport in rivers due to erosion is an important factor for the management of hydrological projects. Artificial neural networks are of great importance for many reasons, such as the ability to detect patterns, the good relationship between input and output, and the need for less input data to predict suspended sedimentation. Accordingly, the present study attempts to model the estimation of suspended sediment content in the Pasikhan River using the artificial neural network of the M5 decision tree. The amount of sediment in rivers is subject to many parameters of river geometry, hydraulic flow and sediment properties. For this reason, in this study, it has been tried to reduce the number of effective parameters by first dimensioning the effective parameters on sediment transport capacity. The results showed that the initial decision tree, the M5 tree, does not require pruning and is suitable for use. Three parameters of determination coefficient (R2), mean relative error (ME) and mean squared error (RMSE) were used to evaluate the accuracy of the prediction model. The obtained values for these three parameters were 0.851, 1037.64 and 941.32, respectively, indicating the suitability of these three parameters. Comparison of suspended sediment yield from decision tree model with Pasikhan River measurement data showed that the coefficient of determination was 0.8953 which is a very good value. The results showed that this model is effective in predicting suspended sediment content in the Pasikhan River.

References:

سالاری جزی. م، قربانی. خ، احمدیانفرو ا، 1398، تحلیل کارایی مدل های شبکه عصبی پرسپترون چندلایه و مدل درخت تصمیم M5 در تخمین بار رسوب معلق روزانه، دانشکده علوم کشاورزی و منابع طبیعی گرگان.

معتمدی خیاوی, فرید و خسرو نظام خیاوی، ۱۳۹۴، استفاده از مدل درختی M5 در تخمین رسوبات معلق رودخانه درهرود، دومین کنفرانس ملی توسعه پایدار در علوم جغرافیا و برنامه ریزی، معماری و شهرسازی، بصورت الکترونیکی، مرکز راهکارهای دستیابی به توسعه پایدار.

Alcayaga, H.A., Mao, L., Belleudy, P., 2018. Predicting the geomorphological responses of gravel-bed rivers to flow and sediment source perturbations at the watershed scale: an application in an Alpine watershed. Earth Surf. Process. Landf. 43, 894–908.

Arab Khadri, M., Hakim Khani, Sh., And Khojini, A., 2016, Necessity of revision of conventional methods for estimating suspended load of rivers, 5th River Engineering Seminar, Ahvaz, 437-429.

Bhattacharya, B., and Solomatine, D.P. 2016. Machine learning in sedimentation modelling, Neural Networks, 19: 208 –214.

Chang, C.K., Azamathulla, H.Md., Zakaria, N.A.,Ab Ghani,A. 2016.Appraisal of soft computing echniques in prediction of total bed material load in tropical rivers, J. Earth Syst. Sci. 121(1), 125–133.

Danandeh Mehr,A, Aliyayi,A and Ghorbani,M. 2015, Suspension Suspension Risks Forecasting Based on Fluid Flow Using Genetic Planning. Watershed Research (Research and Development), No. 88, p. 54-44.[in persian]

Diop, L., Bodian, A., Djaman, K., Yaseen, Z.M., Deo, R.C., El-Shafie, A., Brown, L.C., 2018. The influence of climatic inputs on stream-flow pattern forecasting: case study of Upper Senegal River. Environ. Earth Sci. 77, 182.

Javernick, L.A., Redolfi, M., Bertoldi, W., 2018. Evaluation of a numerical model's ability to predict bed load transport observed in braided river experiments. Adv. Water Resour. 115, 207–218. https://doi.org/10.1016/j.advwatres.2018.03.012.

Lopes, C.L., Bastos, L., Caetano,M., Martins, I., Santos, M.M., Iglesias, I., 2019. Development of physical modelling tools in support of risk scenarios: a new framework focused on deep-sea mining. Sci. Total Environ. 650, 2294–2306.

Miller, K.A., Thompson, K.F., Johnston, P., Santillo, D., 2018. An overview of seabed mining including the current state of development, environmental impacts, and knowledge gaps. Front. Mar. Sci. 4, 418.

Pan, Y., Chen, J., Zhou, H., Tam, N.F.Y., 2018. Changes in microbial community during removal of BDE-153  in four types of aquatic sediments. Sci. Total Environ. 613–614, 644–652.

Quinlan, J. R. 1992. Learning with continuous classes. Proceedings of Fifth Australian joint conference on artificial intelligence, Singapore, pp. 343–348.

Sadegh, M., Majd, M. S., Hernandez, J., and Haghighi, A. T. The quest for hydrological signatures: Effects of data transformation on bayesian inference of watershed models. Water Resources Management (2018), 1 –15.

Tuttle-Raycraft, S., Morris, T.J., Ackerman, J.D., 2017. Suspended solid concentration reduces feeding in freshwater mussels. Sci. Total Environ. 598, 1160–1168.

Walling, D.E., and D.W. Webb. 2017. The reliability of suspended sediment load data, In: Erosion and sediment transport (Proc. of Florence Symp), IAHS. Publ., No. 133, pp. 177-194.

Wisser, D., Frolking, S., Hagen, S., Bierkens, F.P.M., 2016. Beyond peak reservoir storage? A global estimate of declining water storage capacity in large reservoirs. Water Resour. Res. 49, 5732–5739.

Zangane, Z., Ab. Ghani, Abu Hasan, Z. 2011. Prediction of bed load transport in Kurau River based on genetic programming. 3rd International Conference on Managing Rivers in the 21st century, Malaysia.