Application of Whale Optimization Algorithm Combined with Adaptive Neuro-Fuzzy Inference System for Estimating Suspended Sediment Load

Document Type : Regular Article

Authors

1 Assistant Professor of Computer Engineering, Faculty of Engineering, University of Bonab, Bonab, Iran

2 Ph.D. Candidate of Hydraulic Structures, Department of Water Engineering, University of Tabriz, Tabriz, Iran

Abstract

In Iran, no detailed information on the amount of erosion, sediment transport, and sedimentation of rivers, and in many cases, there are many differences between measurements. Since the flow regime and consequently the sediment regime in the drainage basins are not constant, estimation of sediment discharge can help estimate the sediment accumulated behind the water structures, especially the dams, and determining the dead volume of reservoirs in the coming months, and by adopting timely arrangements, the management of discharge will be facilitated to a certain extent during sedimentation. In this study, a hybrid method of the Whale optimization algorithm and the neuro-fuzzy inference system was used to estimate the suspended sediment load (SLL) of the Zarinehrood river. The performance of the proposed methods was evaluated by two statistics, including determination coefficient (R2) and normal root mean square error (NRMSE). SSL of the Zarinehrood river during 10 years with flow discharge was used as inputs. The results showed the high accuracy of the WOA-ANFIS with values R2=0.962 and NRMSE=0.051. In general, a comparison of the results obtained from the hybrid method used in this study showed the high ability and accuracy of the WOA-ANFIS method in estimating the SLL of the Zarinhrood river.

Graphical Abstract

Application of Whale Optimization Algorithm Combined with Adaptive Neuro-Fuzzy Inference System for Estimating Suspended Sediment Load

Highlights

  • We optimized and estimated suspended sediment load.
  • Whale optimizations meta-heuristic method (WOA) based on the neuro-fuzzy inference system (ANFIS), were used to estimate the suspended sediment load (SLL) of the Zarinehrood river.
  • Discharge in t days (Qrt), suspended sediment load in t days (Srt) were considered as input parameters.
  • Based on the modeling results, the SSL of the Zarinehrood river using the WOA-ANFIS method is predicted with high accuracy and is in good agreement with observed data.
  • Model W3 (Qrt-1, Srt-1Qrt) also models the SSL values with less error according to the input parameters.
  • The results showed the high accuracy of the WOA-ANFIS with values R2=0.962 and NRMSE=0.051.

Keywords

Main Subjects


[1]     Öztürk F, Apaydin H, Walling DE. Suspended sediment loads through flood events for streams of Sakarya River basin. Turkish J Eng Environ Sci 2001;25:643–50.
[2]     Kuok KK, Harun S, Shamsuddin SM. Particle swarm optimization feedforward neural network for modeling runoff. Int J Environ Sci Technol 2010;7:67–78. doi:10.1007/BF03326118.
[3]     Kalteh AM, Hjorth P, Berndtsson R. Review of the self-organizing map (SOM) approach in water resources: Analysis, modelling and application. Environ Model Softw 2008;23:835–45. doi:10.1016/j.envsoft.2007.10.001.
[4]     Guo W, Wang H. PSO optimizing neural network for the Yangtze River sediment entering estuary prediction. Proc - 2010 6th Int Conf Nat Comput ICNC 2010 2010;4:1769–72. doi:10.1109/ICNC.2010.5584412.
[5]     Gholami V, Darvari Z, Mohseni Saravi M. Artificial neural network technique for rainfall temporal distribu-tion simulation (‍‍Case study: Kechik region). Casp J Environ Sci 2015;13:53–60.
[6]     Chen XY, Chau KW. A Hybrid Double Feedforward Neural Network for Suspended Sediment Load Estimation. Water Resour Manag 2016;30:2179–94. doi:10.1007/s11269-016-1281-2.
[7]     Kisi O, Zounemat-Kermani M. Suspended Sediment Modeling Using Neuro-Fuzzy Embedded Fuzzy c-Means Clustering Technique. Water Resour Manag 2016;30:3979–94. doi:10.1007/s11269-016-1405-8.
[8]     Buyukyildiz M, Kumcu SY. 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 2017;31:1343–59. doi:10.1007/s11269-017-1581-1.
[9]     Harun MA, Ab Ghani A, Mohammadpour R, Chan NW. Stable channel analysis with sediment transport for rivers in Malaysia: A case study of the Muda, Kurau, and Langat rivers. Int J Sediment Res 2020;35:455–66. doi:10.1016/j.ijsrc.2020.03.008.
[10]    Engineering W, Volume M, Tabatabaei M, Salehpour Jam A, Mosaffaie J. Improvement of the efficiency of artificial neural network model in suspended sediment simulation using particle swarm optimization algorithm. Watershed Eng Manag 2020;12:756–70. doi:10.22092/ijwmse.2019.125871.1638.
[11]    Ebtehaj I, Bonakdari H. Assessment of evolutionary algorithms in predicting non-deposition sediment transport. Urban Water J 2016;13:499–510. doi:10.1080/1573062X.2014.994003.
[12]    Adnan RM, Liang Z, El-Shafie A, Zounemat-Kermani M, Kisi O. Prediction of suspended sediment load using data-driven models. Water (Switzerland) 2019;11. doi:10.3390/w11102060.
[13]    Ebtehaj I, Bonakdari H. No-Deposition Sediment Transport in Sewers Using Gene Expression Programming. J Soft Comput Civ Eng 2017;1:29–53. doi:10.22115/scce.2017.46845.
[14]    Rezaie-Balf M, Attar NF, Mohammadzadeh A, Murti MA, Ahmed AN, Fai CM, et al. Physicochemical parameters data assimilation for efficient improvement of water quality index prediction: Comparative assessment of a noise suppression hybridization approach. J Clean Prod 2020;271:122576. doi:10.1016/j.jclepro.2020.122576.
[15]    Tabari MMR, Soltani J. Multi-Objective Optimal Model for Conjunctive Use Management Using SGAs and NSGA-II Models. Water Resour Manag 2013;27:37–53. doi:10.1007/s11269-012-0153-7.
[16]    Naderpour H, Rafiean AH, Fakharian P. Compressive strength prediction of environmentally friendly concrete using artificial neural networks. J Build Eng 2018;16:213–9. doi:10.1016/j.jobe.2018.01.007.
[17]    Ghanizadeh AR, Heidarabadizadeh N, Heravi F. Gaussian process regression (Gpr) for auto-estimation of resilient modulus of stabilized base materials. J Soft Comput Civ Eng 2021;5:80–94. doi:10.22115/SCCE.2021.269187.1273.
[18]    Kumar P, Pandey S, Maiti PR. A modified genetic algorithm in c++ for optimization of steel truss structures. J Soft Comput Civ Eng 2021;5:95–108. doi:10.22115/SCCE.2021.242552.1249.
[19]    Darabi H, Mohamadi S, Karimidastenaei Z, Kisi O, Ehteram M, ELShafie A, et al. Prediction of daily suspended sediment load (SSL) using new optimization algorithms and soft computing models. Soft Comput 2021;25:7609–26. doi:10.1007/s00500-021-05721-5.
[20]    Mirjalili S, Mirjalili SM, Lewis A. Grey Wolf Optimizer. Adv Eng Softw 2014;69:46–61. doi:10.1016/j.advengsoft.2013.12.007.
[21]    Jang JSR. ANFIS: Adaptive-Network-Based Fuzzy Inference System. IEEE Trans Syst Man Cybern 1993;23:665–85. doi:10.1109/21.256541.
[22]    Kia E, Emadi AR, Fazlola R. Investigation and Evaluation of Artificial Neural Networks in Babolroud River Suspended Load Estimation. J Civ Eng Urban 2013;3:183–90.
[23]    Pour OMR, Shui LT, Dehghani AA. Genetic algorithm model for the relation between flow discharge and suspended sediment load (Gorgan River in Iran). Electron J Geotech Eng 2011;16 E:539–53.
[24]    Sattari MT, Mirabbasi R, Sushab RS, Abraham J. Prediction of Groundwater Level in Ardebil Plain Using Support Vector Regression and M5 Tree Model. Groundwater 2018;56:636–46. doi:10.1111/gwat.12620.