برآورد میزان بار معلق رسوبات در رودخانه‌ سفیدرود با استفاده از الگوریتم‌‌های فراابتکاری

نوع مقاله : مقاله کامل پژوهشی

نویسندگان

1 دانشجوی دکتری، گروه مهندسی آب، واحد لاهیجان، دانشگاه آزاد اسلامی، لاهیجان، ایران

2 گروه آب،واحد لاهیجان،دانشگاه آزاد اسلامی،لاهیجان،ایران

3 استادیار، گروه کشاورزی، واحد لاهیجان، دانشگاه آزاد اسلامی، لاهیجان، لاهیجان، ایران

چکیده

این پژوهش کاربرد تلفیق شبکه عصبی مصنوعی با الگوریتم‌های بهینه‌سازی را به‌منظور برآورد کمی بار معلق رسوبی ایستگاه آستانه رودخانه سفیدرود نشان داد. داده‌های ورودی این شبیه‌سازی شامل دبی جریان و بار رسوب معلق رودخانه‌ مذکور طی دوره آماری 1386 تا 1401 بود. شش مدل شبیه‌سازی نظیر، شبکه عصبی مصنوعی، نسخه‌های ترکیبی آن با مدل‌های ژنتیک، ازدحام ذرات و رقابت استعماری، و همچنین دو مدل یادگیری ماشین شامل، جنگل تصادفی و بردار پشتیبان به‌کار گرفته شد. داده‌ها به‌صورت تصادفی به دو بخش آموزش (70 درصد) و آزمایش (30 درصد) تقسیم شدند، تا کارایی و عملکرد مدل‌ها به‌درستی اعتبارسنجی شود. نتایج نشان داد که مدل ANN-ICA، عملکرد مطلوبی را با کمترین مقدار RMSE (14/4 میلی‌گرم بر لیتر) و ضریب تعیین 86/0 در مرحله آزمایش، بهترین قابلیت تعمیم را در بین مدل‌های بررسی‌شده نشان داد. همچنین مدل ANN-GA با ضریب تعیین 86/0 عملکرد مشابهی داشت. اگرچه مدل جنگل تصادفی در مرحله آموزش بالاترین دقت را نشان داد (R²=0.90 و RMSE برابر با 49/3 میلی‌گرم بر لیتر)، اما کاهش عملکرد آن در مرحله آزمایش (R²=0.83 و RMSE برابر با 6/4 میلی‌گرم بر لیتر) احتمال بیش‌برازش را نشان داد. همچنین، نتایج آزمون ناپارامتری فریدمن وجود اختلاف آماری معنادار بین عملکرد مدل‌ها را تأیید کرد (p<0.05) و آزمون تعقیبی بونفرونی نشان داد که اختلاف معنادار عمدتاً بین مدل پایه ANN و سایر مدل‌های پیشرفته مشاهده شد، درحالی که بین مدل‌های پیشرفته اختلاف آماری معناداری وجود نداشت. تحلیل الگوی خطا و آزمایش‌های آماری نیز بیانگر نبود بایاس زمانی و فقدان خطای ساختاری در شبیه‌سازی بود.

کلیدواژه‌ها

موضوعات

مراجع

  • Aires, U. R. V., da Silva, D. D., Fernandes Filho, E. I., Rodrigues, L. N., Uliana, E. M., Amorim, R. S. S., ... and Campos, J. A. 2023. Machine learning-based modeling of surface sediment concentration in Doce river basin. Journal of Hydrology, 619, 129320. doi:10.1016/j.jhydrol.2023.129320
  • AlDahoul, N., Ahmed, A.N., Allawi, M.F., Sherif, M., Sefelnasr, A., Chau, K.W., and El-Shafie, A. 2022. A comparison of machine learning models for suspended sediment load classification. Engineering Applications of Computational Fluid Mechanics, 16(1), 1211-1232. doi:10.1080/19942060.2022.2073565
  • AlDahoul, N., Essam, Y., Kumar, P., Ahmed, A.N., Abdullaitif, M., El-Shafie, A., Sherif, M., and Sefelnasr, A. 2021. Suspended sediment load prediction using long short-term memory neural network. Scientific Reports, 11, 7826. doi:10.1038/s41598-021-87415-4
  • Allawi, M.F., Sulaiman, S.O., Sayl, K.N., Sherif, M., and El-Shafie, A. 2023. Suspended sediment load prediction modelling based on artificial intelligence methods: The tropical region as a case study. Heliyon, 9(8), e18506. doi:10.j.heliyon.2023.e18506
  • Azari, A., Soori, S., and Bonakdari, H. 2017. The Application of Imperialist Competitive Algorithm in Determining the Optimal Parameters of Empirical Area Reduction Method to Predict the Sedimentation Process in Dez Dam. Geography and Environmental Sustainability, 7(3), 1-14.
  • Baazi, H., Kalla, M., and Tebbi, F.Z. 2014. PSO-ANN’s based suspended sediment concentration in Ksob basin, Algeria. Journal of Engineering and Technology Research, 6(5), 98-107. doi:10.5897/JETR2014.0549
  • Bezak, N., Lebar, K., Bai, Y., and Rusjan, S. 2025. Using machine learning to predict suspended sediment transport under climate change. Water Resources Management, 39, 3311-3326. doi:10.1007/s11269-025-04108-7
  • Biazar, S. M., Fard, A.F., Singh, V.P. et al. 2020. Estimation of Evaporation from Saline-Water with More Efficient Input Variables. Pure Appl. Geophys.177, 5599–5619.  doi:1007/s00024-020-02570-5
  • Collins, A. L., Zhang, Y., Walling, D. E., Grenfell, S. E., and Smith, P. 2010. Tracing sediment loss from eroding farm tracks using a geochemical fingerprinting procedure combining local and genetic algorithm optimisation. Science of the Total Environment, 408(22), 5461-5471. doi: 10.1016/j.scitotenv.2010.07.066
  • Darabi, H., Mohamadi, S., Karimidastenaei, Z., Kisi, O., and Ehteram, M. 2021. Prediction of daily suspended sediment load (SSL) using new optimization algorithms and soft computing models. Soft Computing, 25, 7609-7626
  • Dethier, E.N., Magilligan, F.J., Renshaw, C.E., and Nislow, K.H. 2022. Rapid changes to global river suspended sediment flux by human activities. Science, 376(6595), 1447-1451. doi:10.1126/science.abn7980
  • Dinpazhoh, Y., Sattari, M., E, S., and Darbandi, S. 2017. 'Optimum Operation of Reservoir Using the Genetic Algorithm and Particle Swarm Optimization (Case Study: Alavian Dam)', Water and Soil Science, 27(2), pp. 17-29.
  • Ebtehaj, I., and Bonakdari, H. 2017. Design of a fuzzy differential evolution algorithm to predict non-deposition sediment transport. Applied Water Science, 7, 4287-4299. doi:10.1007/s13201-017-0562-0
  • Emami, S., and Choopan, Y. 2019. An application of imperialist competitive algorithm in estimating sediment suspended load. Hydrogeology, 4(1), 70-79. doi:10.22034/hydro.2019.7310 [In Persian]
  • Emami, S., Choopan, Y., and Parsa, J. 2018. Modeling the groundwater level of the Miandoab plain using artificial neural network method and election and genetic algorithms. Journal of Ecohydrology, 5(4), 1175-1189. doi:10.22059/ije.2018.258644.889 [In Persian]
  • Emami, S.K., Saadat, A.M., and Hamidifar, H. 2024. Microplastic pollution: Analytical techniques, policy landscape, and integrated strategies for sustainable environmental stewardship. In S.C. Izah, M.C. Ogwu, A. Loukas, and H. Hamidifar (Eds.), Water crises and sustainable management in the Global South (pp. 237-270). Springer. doi:10.1007/978-981-97-4966-9_11
  • Essam, Y., Huang, Y.F., Birima, A.H. et al. 2022. Predicting suspended sediment load in Peninsular Malaysia using support vector machine and deep learning algorithms. Sci Rep 12, 302. doi:1038/s41598-021-04419-w
  • Fardadi Shilsar, M.J., Mazaheri, M., and Mohammad Vali Samani, J. 2021. Analytical solution of the pollutant transport equation with variable coefficients in rivers using the Laplace transform. Water and Irrigation Management, 11(4), 683–698. doi:10.22059/jwim.2021.329149.911 [In Persian]
  • Fardadi Shilsar, M.J., Mazaheri, M., and Mohammad Vali Samani, J. 2022a. Analytical solution of mass transport equation in river networks. Sharif Journal of Mechanical Engineering, 38.3(1), 35–49. doi:10.24200/j40.2021.58767.1613 [In Persian]
  • Fardadi Shilsar, M.J., Mazaheri, M., and Mohammad Vali Samani, J. 2022b. Analytical solution of pollutant transport equation in different types of river networks considering distributed source term. Iranian Journal of Soil and Water Research, 53(5), 1057–1077. doi:10.22059/ijswr.2022.341884.669250 [In Persian]
  • Fardadi Shilsar, M.J., Mazaheri, M., and Mohammad Vali Samani, J. 2023. A semi-analytical solution for one-dimensional pollutant transport equation in different types of river networks. Journal of Hydrology, 619, 129287. doi:10.1016/j.jhydrol.2023.129287
  • Fawell, J., and Nieuwenhuijsen, M.J. 2003. Contaminants in drinking water: Environmental pollution and health. British Medical Bulletin, 68(1), 199-208. doi:10.1093/bmb/ldg027
  • Gul, E., Safari, M.J.S., Torabi Haghighi, A., and Danandeh Mehr, A. 2021. Sediment transport modeling in open channels using machine learning algorithms. PLOS ONE, 16(10), e0258125. doi:10.1371/journal.pone.0258125
  • Gulliver, J.S. 2007. Introduction to chemical transport in the environment. Cambridge University Press.
  • Hasanpour Kashani, M., Ghorbani, M.A., Dinpashoh, Y. et al. 2014. Comparison of Volterra Model and Artificial Neural Networks for Rainfall–Runoff Simulation. Nat Resour Res 23, 341–354. doi:1007/s11053-014-9235-y
  • Hoffmann, T., Thorndycraft, V.R., Brown, A.G., Coulthard, T.J., Damnati, B., Kale, V.S., Middelkoop, H., Notebaert, B., and Walling, D.E. 2023. Pristine levels of suspended sediment in a large river. Earth Surface Dynamics, 11, 287-301. doi:10.5194/esurf-11-287-2023
  • Joshi, B., Singh, V.K., Vishwakarma, D.K., Ghorbani, M.A., Kim, S., Gupta, S., Chandola, V.K., Rajput, J., Chung, I.M., Yadav, K.K., Mirzania, E., Al-Ansari, N., and Mattar, M.A. 2024. A comparative survey between cascade correlation neural network (CCNN) and feedforward neural network (FFNN) machine learning models for forecasting suspended sediment concentration. Scientific Reports, 14, 10638. doi:10.1038/s41598-024-61339-1
  • Jothiprakash, V., and Garg, V. 2009. Reservoir sedimentation estimation using artificial neural network. Journal of Hydrologic Engineering, 14(9), 1035-1040. doi:10.1061/(ASCE)HE.1943-5584.0000075
  • Khanduzi, R., Ebrahimzadeh, A., and Ebrahimzadeh, Z. 2024. A combined Bernoulli collocation method and imperialist competitive algorithm for optimal control of sediment in the dam reservoirs. AUT Journal of Mathematics and Computing, 5(1), 71-80. doi:10.22060/ajmc.2023.21635.1109
  • Kisi, O. 2007. Evapotranspiration modelling from climatic data using a neural computing technique. Hydrological Processes, 21(14), 1925-1934. doi:10.1002/hyp.6403
  • Kisi, O., and Ozkan, C. 2017. A new approach for modeling sediment-discharge relationship: Local weighted linear regression. Water Resources Management, 31(1), 1-23. doi:10.1007/s11269-016-1481-9
  • 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. doi:10.1016/j.cageo.2012.02.007
  • Kisi, O., Heddam, S., Parmar, K.S., Malik, A., and Karimi, B. 2024. Improved monthly streamflow prediction using integrated multivariate adaptive regression spline with K-means clustering: Implementation of reanalyzed remote sensing data. Stochastic Environmental Research and Risk Assessment, 38, 2489-2519. doi:10.1007/s00477-024-02692-5
  • Knighton, D. 2014. Fluvial forms and processes: A new perspective. Routledge.
  • Latif, S. D., Chong, K. L., Ahmed, A. N., Huang, Y. F., Sherif, M., and El-Shafie, A. 2023. Sediment load prediction in Johor river: deep learning versus machine learning models. Applied Water Science, 13(3), 79. doi: 10.1007/s13201-023-01874-w
  • Le, X.H., Ho, H.V., Lee, G., and Jung, S. 2024. Quantifying predictive uncertainty and feature selection in machine learning river bed load predictions. Water, 16(14), 1945. doi:10.3390/w16141945
  • Li, S., and Yang, J. 2022. Modelling of suspended sediment load by Bayesian optimized machine learning methods with seasonal adjustment. Engineering Applications of Computational Fluid Mechanics, 16(1), 1883-1901. doi:10.1080/19942060.2022.2121944
  • Melesse, A.M., Ahmad, S., McClain, M.E., Wang, X., and Lim, Y.H. 2011. Suspended sediment load prediction of river systems: An artificial neural network approach. Agricultural Water Management, 98(5), 855-866. doi:10.1016/j.agwat.2010.12.012
  • Meshram, S.G., Singh, V.P., Kisi, O., Karimi, V., and Meshram, C. 2020. Application of artificial neural networks, support vector machine and multiple model-ANN to sediment yield prediction. Water Resources Management, 34(15), 4561-4575. doi:10.1007/s11269-020-02672-8
  • Moradinejad, A. 2024. Modeling estimation of river suspended sediment amount using support vector regression and data control group method. Water and Soil Science, 34(2), 203-222. doi:10.22034/ws.2023.57435.2526 [In Persian]
  • Naseri F, Azari M, and Dasturani M T. 2019. Optimizing coefficients of Sediment rating curve equation using Genetic Algorithm (Case study: Ghazaghli and Bagh‌ abbasi stations), Irrigation and Water Engineering, 9(3), pp. 82-98. doi: 10.22125/iwe.2019.88672 [In Persian]
  • Nda, M., Shabako, J.G., Yakubu, M., Godwin, A., and Justice, A.N. 2023. Riverbank erosion, sediment transport and reservoir sedimentation: An overview. Savannah Journal of Science and Engineering Technology, 1(4), 210-216.
  • Nikoo, M., Razavi, S. A., and Hadzima-Nyarko, M. 2018. Artificial Neural Network Combined with Imperialist Competitive Algorithm for Determination of River Sediments. Fresenius Environ Bull, 27(7), 4658-4667.
  • Noori, R., Karbassi, A.R., Ashrafi, K., Farokhnia, A., and Sabahi, M.S. 2012. Active and online prediction of BOD5 in river systems using reduced-order support vector machine. Environmental Earth Sciences, 67, 141-149. doi:10.1007/s12665-011-1487-9
  • Parsons, A.J., Cooper, J., and Wainwright, J. 2015. What is suspended sediment? Earth Surface Processes and Landforms, 40(10), 1417-1420. doi:10.1002/esp.3730
  • Razavizadeh, S., and Dargahian, F. 2018. Optimization of artificial neural network structure in prediction of sediment discharge using Taguchi method. Journal of Water Management Science and Engineering, 12(43), 89-97. doi:20.1001.1.20089554.1397.12.43.10.3 [In Persian]
  • Saadat, A.M., and Mazaheri, M. 2022. Backward solution (in-time) of the pollution transport equation in river using group preserving scheme. Journal of Ferdowsi Civil Engineering, 35(4), 35-52. doi:10.22067/jfcei.2022.77645.1165 [In Persian]
  • Saadat, A.M., and Mazaheri, M. 2023. Application of one-step group preserving scheme in various contaminant transport modeling in rivers. Iranian Journal of Soil and Water Research, 54(11), 1627–1646. doi:10.22059/ijswr.2023.365226.669572 [In Persian]
  • Saadat, A.M., and Mazaheri, M. 2024a. Forward and inverse river contaminant transport modeling using group preserving scheme. Physics of Fluids, 36(9), 094102. doi:10.1063/5.0221578
  • Saadat, A.M., and Mazaheri, M. 2024b. Using one-step group preserving schemes for contaminant transport modeling in rivers. Iranian Journal of Soil and Water Research, 54(11), 1627-1646. doi:10.22059/ijswr.2023.365226.669572 [In Persian]
  • Saadat, A.M., Emami, S.K., and Hamidifar, H. 2024. A review on storage process models for improving water quality modeling in rivers. Hydrology, 11(11), 187. doi:10.3390/hydrology11110187
  • Saadat, A.M., Emami, S.K., and Mazaheri, M. 2025b. Evaluating the impact of storage zones on backward contaminant transport: A comparative study of the classic advection-dispersion equation and storage zone models in riverine systems. Science of The Total Environment, 973, 179176. doi:10.1016/j.scitotenv.2025.179176
  • Saadat, A.M., Emami, S.K., Hamidifar, H., and Fardadi Shilsar, M.J. 2025a. Microplastic pollution in water systems of the Global South: A review. Journal of Contaminant Hydrology, 267, 104729. doi:10.1016/j.jconhyd.2025.104729
  • Saadat, A.M., Mazaheri, M., and Mohammad Vali Samani, J. 2022. Backward (in-time) inverse solution of river contaminant transport equation using the group preserving scheme. Journal of Ferdowsi Civil Engineering, 35(4), 35–52. doi:10.22067/jfcei.2022.77645.1165 [In Persian]
  • Sanikhani, H., Kisi, O., Nikpour, M.R. et al. 2012. Estimation of Daily Pan Evaporation Using Two Different Adaptive Neuro-Fuzzy Computing Techniques. Water Resour Manage 26, 4347–4365. doi:1007/s11269-012-0148-4
  • Seyedian, S.M., Rohani, H., Fathabadi, A., and Javadi Alinezhad, M. 2017. Stochastic modeling of sediment yield using random forest and quantile regression. Journal of Water and Soil Conservation, 24(4), 103–122. doi:10.22069/jwsc.2017.12600.2732 [In Persian]
  • Shahi Nejad, B., and Dehghani, R. 2017. Evaluation of support vector machine model performance in estimating suspended sediment. Irrigation and Water Engineering, 8(1), 30–42. [In Persian]
  • Sharafati, A., Haji Seyed Asadollah, S. B., Motta, D., and Yaseen, Z. M. 2020. Application of newly developed ensemble machine learning models for daily suspended sediment load prediction and related uncertainty analysis. Hydrological Sciences Journal, 65(12), 2022–2042. doi:1080/02626667.2020.1786571
  • Smits, A.J.M., Nienhuis, P.H., and Leuven, R.S.E.W. 2000. New approaches to river management. Backhuys Publishers.
  • Syed, A.U., Konieczny, J.T., and Wright, S.A. 2005. A pre-dam-removal assessment of sediment transport for four dams on the Klamath River using sediment transport modeling. U.S. Geological Survey Scientific Investigations Report 2004-5178.
  • Teixeira, L.C., Mariani, P.P., Pedrollo, O.C., and Avila, L.F. 2020. Artificial neural network and fuzzy inference system models for forecasting suspended sediment and turbidity in basins at different scales. Water Resources Management, 34, 3709-3723. doi:10.1007/s11269-020-02647-9
  • Vanoni, V.A. (Ed.). 2006. Sedimentation engineering. American Society of Civil Engineers. doi:10.1061/9780784408230
  • Vázquez-Tarrío, D., Ruiz-Villanueva, V., Garrote, J., Benito, G., Calle, M., Lucía, A., and Díez-Herrero, A. 2024. Effects of sediment transport on flood hazards: Lessons learned and remaining challenges. Geomorphology, 446, 108976. doi:10.1016/j.geomorph.2023.108976
  • Yadav, A., Chatterjee, S., and Equeenuddin, S.M. 2018. Suspended sediment yield estimation using genetic algorithm-based artificial intelligence models: Case study of Mahanadi River, India. Hydrological Sciences Journal, 63(8), 1162-1182. doi:10.1080/02626667.2018.1483581
  • Yadav, A., Hasan, M. K., Joshi, D., Kumar, V., Aman, A. H. M., Alhumyani, H., Alzaidi, M. S., and Mishra, H. 2022. Optimized Scenario for Estimating Suspended Sediment Yield Using an Artificial Neural Network Coupled with a Genetic Algorithm. Water, 14(18), 2815. doi:10.3390/w14182815
  • Zangeneh Asadi, M.A., Goli Mokhtari, L., Zandi, R., and Naemitabar, M. 2025. Modeling, evaluation and forecasting of suspended sediment load in Kal-e Shur River, Sabzevar Basin, in northeast of Iran. Applied Water Science, 15, 44. doi:10.1007/s13201-025-02361-0
  • Zhou, Y., Wang, H., and Yan, Y. 2023. Sediment transport trend and its influencing factors in a large river basin. Frontiers in Marine Science, 10, 1220331. doi:10.3389/fmars.2023.1220331
دانش آب و هیدرولیک
دوره 36، شماره 1
فروردین 1405
صفحه 65-81

فایل ها

هم رسانی

ارجاع به این مقاله

آمار