Estimation of daily suspended sediment load using a new hybrid artificial neural network model combined with observer-teacher-learner- based- optimization method

Subject Areas : Article frome a thesis

Siyamak Doroudi ¹ , Ahmad Sharafati ²

1 - PhD student, Department of Civil Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran
2 - Assistant Professor, Department of Civil Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran

Received: 2023-06-03 Accepted : 2024-07-30 Published : 2025-05-05

Keywords: Suspended sediment load, Optimization algorithm, Artificial neural network,

Abstract :

Introduction: Suspended sediment load (SSL) is one of the complex hydrological phenomena, and its prediction is difficult. This study uses the artificial neural network method to predict suspended sediment load. Since the accuracy of artificial neural networks depends on their parameters, the benefit of meta-heuristic algorithms can be effective in increasing their performance. The case study is the catchment area of the Kosar Dam located in the southwest of Iran.

Methods: River discharge and rainfall were considered as inputs, and features for predicting models. Five input compounds were selected. OTLBO and PSO meta-heuristic algorithms were used to find the optimal ANN values, and ANN-OTLBO and ANN-PSO prediction models were developed. Predicting models were evaluated using different numerical and visual indicators.

Findings: The results show that the ANN-OTLBO model provides higher prediction performance than other models used in this study. Specifically, the ANN-OTLBO-M5 model shows superior values (R=0.96358, RMSE=258.14, PBIAS=2.6752, and NSE=0.92674). Also, based on the Scatter plot, Heat map, and Box plot, the closest predicted data to the observed data belongs to the ANN-OTLBO-M5 model.

References:

[1] B. Choubin, H. Darabi, O. Rahmati, F. Sajedi-Hosseini, and B. Kløve, “River suspended sediment modelling using the CART model: A comparative study of machine learning techniques,” Sci. Total Environ., vol. 615, pp. 272–281, Feb. 2018, doi: 10.1016/j.scitotenv.2017.09.293.
[2] M. Y. A. Khan, F. Tian, F. Hasan, and G. J. Chakrapani, “Artificial neural network simulation for prediction of suspended sediment concentration in the River Ramganga, Ganges Basin, India,” Int. J. Sediment Res., vol. 34, no. 2, pp. 95–107, Apr. 2019, doi: 10.1016/j.ijsrc.2018.09.001.
[3] O. Kisi, “Modeling discharge-suspended sediment relationship using least square support vector machine,” J. Hydrol., vol. 456–457, pp. 110–120, Aug. 2012, doi: 10.1016/j.jhydrol.2012.06.019.
[4] B. Greimann, Y. Lai, and J. Huang, “Two-Dimensional Total Sediment Load Model Equations,” J. Hydraul. Eng., vol. 134, no. 8, pp. 1142–1146, Aug. 2008, doi: 10.1061/(ASCE)0733-9429(2008)134:8(1142).
[5] M. H. Garcia, “Sedimentation engineering: processes, measurements, modeling and practice. ASCE Manuals and Reports on Engineering Practice No. 110. American Society Civil Engineering Publications, Reston, VA, 1150 pp. ISBN 9780784408148.,” no. 110, p. 2008, 2008.
[6] N. E. M. Asselman, “Fitting and interpretation of sediment rating curves,” J. Hydrol., vol. 234, no. 3–4, pp. 228–248, Jul. 2000, doi: 10.1016/S0022-1694(00)00253-5.
[7] K. Vercruysse, R. C. Grabowski, and R. J. Rickson, “Suspended sediment transport dynamics in rivers: Multi-scale drivers of temporal variation,” Earth-Science Reviews, vol. 166. Elsevier B.V., pp. 38–52, Mar. 01, 2017, doi: 10.1016/j.earscirev.2016.12.016.
[8] F. Panahi, M. Ehteram, and M. Emami, “Suspended sediment load prediction based on soft computing models and Black Widow Optimization Algorithm using an enhanced gamma test,” Environ. Sci. Pollut. Res. 2021 2835, vol. 28, no. 35, pp. 48253–48273, Apr. 2021, doi: 10.1007/S11356-021-14065-4.
[9] S. Q. Salih et al., “River suspended sediment load prediction based on river discharge information: application of newly developed data mining models,” Hydrol. Sci. J., vol. 65, no. 4, pp. 624–637, Mar. 2020, doi: 10.1080/02626667.2019.1703186.
[10] F. B. Banadkooki et al., “Suspended sediment load prediction using artificial neural network and ant lion optimization algorithm,” Environ. Sci. Pollut. Res. 2020 2730, vol. 27, no. 30, pp. 38094–38116, Jul. 2020, doi: 10.1007/S11356-020-09876-W.
[11] M. Buyukyildiz and S. Y. Kumcu, “An Estimation of the Suspended Sediment Load Using Adaptive Network Based Fuzzy Inference System, Support Vector Machine and Artificial Neural Network Models,” Water Resour. Manag., vol. 31, no. 4, pp. 1343–1359, Mar. 2017, doi: 10.1007/s11269-017-1581-1.
[12] A. Sharafati, S. B. Haji Seyed Asadollah, D. Motta, and Z. M. Yaseen, “Application of newly developed ensemble machine learning models for daily suspended sediment load prediction and related uncertainty analysis,” Hydrol. Sci. J., pp. 2022–2042, 2020, doi: 10.1080/02626667.2020.1786571.
[13] G. F. Lin, Y. C. Chou, and M. C. Wu, “Typhoon flood forecasting using integrated two-stage support vector machine approach,” J. Hydrol., vol. 486, pp. 334–342, Apr. 2013, doi: 10.1016/j.jhydrol.2013.02.012.
[14] E. Kakaei Lafdani, A. Moghaddam Nia, and A. Ahmadi, “Daily suspended sediment load prediction using artificial neural networks and support vector machines,” J. Hydrol., vol. 478, pp. 50–62, Jan. 2013, doi: 10.1016/j.jhydrol.2012.11.048.
[15] S. Li, Q. Xie, and J. Yang, “Daily suspended sediment forecast by an integrated dynamic neural network,” J. Hydrol., vol. 604, p. 127258, Jan. 2022, doi: 10.1016/J.JHYDROL.2021.127258.
[16] H. A. Afan et al., “Input attributes optimization using the feasibility of genetic nature inspired algorithm: Application of river flow forecasting,” Sci. Reports 2020 101, vol. 10, no. 1, pp. 1–15, Mar. 2020, doi: 10.1038/s41598-020-61355-x.
[17] M. F. Allawi, O. Jaafar, M. Ehteram, F. Mohamad Hamzah, and A. El-Shafie, “Synchronizing Artificial Intelligence Models for Operating the Dam and Reservoir System,” Water Resour. Manag., vol. 32, no. 10, pp. 3373–3389, Aug. 2018, doi: 10.1007/S11269-018-1996-3.
[18] M. Shahrouzi, M. Aghabagloua, and F. Rafiee, “Observer-teacher-learner-based optimization: An enhanced meta-heuristic for structural sizing design,” Struct. Eng. Mech., vol. 62, no. 5, pp. 537–550, 2017, doi: 10.12989/sem.2017.62.5.537.
[19] S. H. H. Lavasani and R. Doroudi, “Meta heuristic active and semi-active control systems of high-rise building,” Int. J. Struct. Eng., vol. 10, no. 3, pp. 232–253, 2020, doi: 10.1504/IJSTRUCTE.2020.108529.
[20] S. H. Hosseini Lavassani, S. A. Mousavi Gavgani, and R. Doroudi, “Optimal control of jacket platforms vibrations under the simultaneous effect of waves and earthquakes considering fluid-structure interaction,” Ocean Eng., vol. 280, p. 114593, Jul. 2023, doi: 10.1016/J.OCEANENG.2023.114593.
[21] Y. S. J. Kennedy, R. C. Eberhart, Swarm Intelligence, First edit. San Francisco: Morgan Kaufmann, 2001.
[22] D. N. Moriasi, J. G. Arnold, M. W. Van Liew, R. L. Bingner, R. D. Harmel, and T. L. Veith, “Model Evaluation Guidelines for Systematic Quantification of Accuracy in Watershed Simulations,” Trans. ASABE, vol. 50, no. 3, pp. 885–900, 2007, doi: 10.13031/2013.23153.
[23] J. E. Nash and J. V. Sutcliffe, “River flow forecasting through conceptual models part I — A discussion of principles,” J. Hydrol., vol. 10, no. 3, pp. 282–290, Apr. 1970, doi: 10.1016/0022-1694(70)90255-6.
[24] C. J. Willmott, “On the validation of models,” Phys. Geogr., vol. 2, no. 2, pp. 184–194, 1981, doi: 10.1080/02723646.1981.10642213.
[25] H. H. C. de Salis et al., “Hydrologic Modeling for Sustainable Water Resources Management in Urbanized Karst Areas,” Int. J. Environ. Res. Public Heal. 2019, Vol. 16, Page 2542, vol. 16, no. 14, p. 2542, Jul. 2019, doi: 10.3390/IJERPH16142542.
[26] D. Kumar, A. Pandey, N. Sharma, and W. A. Flügel, “Daily suspended sediment simulation using machine learning approach,” Catena, vol. 138, pp. 77–90, Mar. 2016, doi: 10.1016/j.catena.2015.11.013.