SUSPENDED SEDIMENT LOAD PREDICTION IN RIVERS BY USING HEURISTIC REGRESSION AND HYBRID ARTIFICIAL INTELLIGENCE MODELS

Year 2020, Volume: 38 Issue: 2, 703 - 714, 01.06.2021

Banu Yılmaz Egemen Aras Murat Kankal Sinan Nacar

Abstract

Accurate prediction of amount of sediment load in rivers is extremely important for river hydraulics. The solution of the problem has been become complicated since the explanation of hydraulic phenomenon between the flow and the sediment on the river is dependent many parameters. The usage of different regression methods and artificial intelligence techniques allows the development of predictions as the traditional methods do not give enough accurate results. In this study, data of the flow and suspended sediment load (SSL) obtained from Karşıköy Gauging Station, located on Çoruh River in the north-eastern of Turkey, modelled with different regression methods (multiple regression, multivariate adaptive regression splines) and artificial neural network (ANN) (ANN-back propagation, ANN teaching-learning-based optimization algorithm and ANN-artificial bee colony). When the results were evaluated, it was seen that the models of ANN method were close to each other and gave better results than the regression models. It is concluded that these models of ANN method can be used successfully in estimating the SSL.

Keywords

Artificial intelligence, Çoruh river basin, regression analysis, river hydraulics, suspended sediment load

References

• [1] Olive, L.J., and Rieger, W.A., (1988) An examination of the role of sampling strategies inmthe study of the suspended sediment transport. Sediment Budgets, Proceedings of the Porto alegre Symposium. IAHS Publ. No. 174, 259-267.
• [2] Öztürk, F., (2002) Determination of Surface Flow and Sediment Amount by AGNPS Model (In Turkish), Scientific Research Project Final Report, Ankara University Scientific Research Projects, Ankara.
• [3] Kisi, Ö., Karahan M.E. ve Şen, Z., (2003) Fuzzy logic modeling of suspension material amount in rivers (In Turkish), İTÜ Journal, 2, 34, 43-54.
• [4] Yilmaz, B., Aras, E., Nacar, S., Kankal, M., (2018) Estimating suspended sediment load with multivariate adaptive regression spline, teaching-learning based optimization, and artificial bee colony models. Science of The Total Environment, 639, 826-840.
• 5] Jain, S. K., (2001) Development of integrated sediment rating curves using ANNs. Journal of Hydraulic Engineering, 127(1):30-37.
• [6] Tayfur, G., (2002) Artificial neural networks for sheet sediment transport. Hydrological Sciences Journal, 47(6): 879-892.
• [7] Cigizoglu, H. K., (2004) Estimation and forecasting of daily suspended sediment data by multi-layer perceptrons, Advances in Water Resources 27(2):185-195.
• [8] Tayfur, G., and Guldal, V., (2006) Artificial neural networks for estimating daily total suspended sediment in natural streams. Hydrology Research 37(1):69-79.
• [9] Alp, M., and Cığızoğlu H. K., 2007. Suspended sediment load estimation by two artificial neural network methods using hydrometeorological data. Environmental Modelling & Software, 22, 2-13.
• [10] Zhu, Y. M., Lu, X. X., Zhou, Y., (2007) Suspended sediment flux modeling with artificial neural network: An example of the Longchuanjiang River in the Upper Yangtze Catchment, China. Geomorphology 84(1):111-125.
• [11] Ardıclıoglu, M., Kişi, Ö., Haktanır, T., (2007) Suspended sediment prediction using two different feed-forward back-propagation algorithms. Canadian Journal of Civil Engineering 34(1):120-125.
• [12] Kisi, Ö., (2008) Constructing neural network sediment estimation models using a datadriven algorithm. Mathematics and Computers in Simulation 79(1):94-103.
• [13] Cobaner, M., Unal, B., and Kisi, O., (2009) Suspended sediment concentration estimation by an adaptive neuro-fuzzy and neural network approaches using hydro-meteorological data. Journal of hydrology, 367(1-2), 52-61.
• [14] Rajaee, T., Mirbagheri, S. A., Zounemat-Kermani, M., Nourani, V., (2009) Daily suspended sediment concentration simulation using ANN and neuro-fuzzy models. Science of The Total Environment 407(17):4916-4927.
• [15] Kisi, O., and Shiri, J., (2012) River suspended sediment estimation by climatic variables implication: Comparative study among soft computing techniques. Computers & Geosciences 43:73-82.
• [16] Lafdani, E. K., Nia, A. M., Ahmadi, A., (2013) Daily suspended sediment load prediction using artificial neural networks and support vector machines. Journal of Hydrology 478:50-62.
• [17] Altunkaynak, A., (2009) Sediment load prediction by genetic algorithms. Advances in Engineering Software, 40(9), 928-934.
• [18] Karaboga, N., (2009) A new design method based on artificial bee colony algorithm for digital IIR filters. Journal of the Franklin Institute 346(4):328-348
• [19] Zhang C, Ouyang D, Ning, J (2010) An artificial bee colony approach for clustering. Expert Systems with Applications 37(7):4761-4767
• [20] Pour, O. M. R., Shui, L. T., and Dehghani, A. A., (2011) Genetic algorithm model for the relation between flow discharge and suspended sediment load (Gorgan river in Iran). Electronic Journal of Geotechnical Engineering, 16, 539-553.
• [21] Uzlu, E., Akpınar, A., Özturk, H. T., Nacar, S., Kankal, M., (2014a) Estimates of hydroelectric generation using neural networks with the artificial bee colony algorithm for Turkey. Energy 69:638-647.
• [22] Uzlu, E., Kömürcü, M, İ., Kankal, M., Dede, T., and Öztürk, H. T., (2014b) Prediction of berm geometry using a set of laboratory tests combined with teaching–learning-based optimization and artificial bee colony algorithms. Applied Ocean Research 48:103-113.
• [23] Bayram, A., Uzlu, E., Kankal, M., & Dede, T. (2015) Modeling stream dissolved oxygen concentration using teaching–learning based optimization algorithm. Environmental Earth Sciences, 73(10), 6565-6576.
• [24] Kankal, M., Uzlu, E., (2017) Neural network approach with teaching–learning-based optimization for modeling and forecasting long-term electric energy demand in Turkey. Neural Computing and Applications 1-11.
• [25] Baki, O.T., and Aras, E., (2018) Estimation of BOD in Wastewater Treatment Plant by Using Different ANN Algorithms. Membrane Water Treatment, An International Journal, 9(6), 455-462.
• [26] EİE, (2005) General Directorate of Electrical Works, Suspended sediment observation and transport in Turkey’s rivers (In Turkish), EİE Press, Ankara.
• [27] Buyukyildiz, M., and Kumcu, S. Y., (2017) An estimation of the suspended sediment load using adaptive network based fuzzy inference system, support vector machine and artificial neural network models. Water resources management, 31(4), 1343-1359.
• [28] Nacar, S., Hınıs, M. A., & Kankal, M. (2018a) Forecasting Daily Streamflow Discharges Using Various Neural Network Models and Training Algorithms. KSCE Journal of Civil Engineering, 22(9), 3676-3685.
• [29] Kisi, O., and Parmar, K. S., (2016) Application of least square support vector machine and multivariate adaptive regression spline models in long term prediction of river water pollution. Journal of Hydrology, 534, 104-112.
• [30] Nacar, S., Kankal, M., and Hinis, M. A., (2018b) Estimation of Daily Stream Flows with Multivariable Adaptive Regression Curves -Haldizen Creek Case (In Turkish), Gumushane University Journal of the Institute of Science and Technology, 8(1), 38-47.
• [31] Bayram, A., Kankal, M., and Önsoy, H., (2012) Estimation of suspended sediment concentration from turbidity measurements using artificial neural networks. Environmental monitoring and assessment, 184(7), 4355-4365.
• [32] Sudheer, K. P., Nayak, P. C., & Ramasastri, K. S. (2003). Improving peak flow estimates in artificial neural network river flow models. Hydrological Processes, 17(3), 677-686.