نوع مقاله : مقاله پژوهشی
نویسندگان
1 دانشجوی دکتری سازه های آبی، گروه مهندسی آب، دانشکده کشاورزی، دانشگاه تبریز، تبریز، ایران
2 استادیار گروه مهندسی آب دانشگاه تبریز
چکیده
با توجه به این‌که رژیم جریان و به‌تبع آن رژیم رسوب در حوزه‌های آبخیز ثابت نیست، پیش‌بینی دبی رسوب کمک شایانی در برآورد و مدیریت رسوب ورودی به سازه‌های آبی می‌نماید. اندازه‌گیری میزان رسوب به شیوه‌ی معمول در دنیای امروز توجیه‌پذیر نبوده و ممکن است خطای انسانی را نیز به همراه داشته باشد. از این‌رو، در این پژوهش، از سه الگوریتم فراابتکاری بهینه‌سازی شامل الگوریتم رقابت استعماری (ICA)، الگوریتم گرگ خاکستری (GWO) و الگوریتم انتخابات (EA) برای برآورد بار رسوبی معلق رودخانه‌‌‌ی زرینه‌رود استفاده شده است. برای محاسبه دبی رسوب توسط مدل‌ها در ابتدا آمار و اطلاعات لازم در دوره‌ی آماری 94-1372 در ایستگاه مورد مطالعه جمع-آوری شده است. پس از پردازش داده‌ها، تعداد 210 داده متناظر دبی و رسوب انتخاب شد. داده‌های دبی- رسوب متناظر ایستگاه مورد مطالعه به‌صورت تصادفی به دو بخش 70 درصد برای واسنجی و 30 درصد برای آزمون تفکیک شدند. برای ارزیابی عملکرد روش‌های پیشنهادی، از چهار آماره شامل ضریب تبیین (R2)، مجذور میانگین مربعات خطا (RMSE)، معیار نش- ساتکلیف (NSE) و میانگین قدرمطلق خطا (MAE) استفاده شده است. نتایج به‌دست آمده نشان داد که الگوریتم GWO با کسب مقادیر RMSE=228.86, R2=0.96 تن در روز، NSE=0.74 وMAE=67.32 تن در روز، در مقایسه با سایر الگوریتم‌های به‌کار گرفته شده، از کارایی بالاتری برخوردار است که این امر می‌تواند به برنامه‌ریزی صحیح و جامع برای طراحی و ساخت سازه‌های آبی منجر شود.
کلیدواژه‌ها
عنوان مقاله [English]
Comparising Performance of Meta-heuristic Algorithms with the Sediment Rate Curve (Case Study: Zarrineh Rood River)
نویسندگان [English]
- Somayeh Emami 1
- Javad Parsa 2
1 Ph.D. Student of Hydraulic Structures, Water Engineering Department, Faculty of Agriculture, Tabriz University
2 Assistant Professor of Tabriz University
چکیده [English]
Due to the flow regime and consequently the sediment regime are not constantly in the watersheds, the prediction of sediment discharge is a great help in estimating and managing the sediment input to hydraulic structures. Measurement of sediment in the usual way is not justified in nowadays and may also lead to human error. Therefore, in this study, three meta-heuristic optimization algorithms, including imperialist competitive algorithm (ICA), grey wolf optimizer algorithm (GWO) and election algorithm (EA), were used to predict the suspended sediment load of the Zarrineh river. In order to calculate the sediment discharge by the models, firstly, the necessary statistics and data were collected from the studied station in the period 1993-2015. After processing the data, 210 corresponding discharge and sediment data were selected. The corresponding discharge-sediment data from the study station were randomly separated into two parts, 70% for training and 30% for testing. In order to evaluate the performance of the algorithms, four statistics consist of R2, RMSE, MAE and the NSE were used. The results showed that GWO algorithm with values of statistical criteria R2=0.96, RMSE=228.86 ton/day, NSE=0.74 and MAE=67.32 ton/day, has a very high accuracy compared to other algorithms used which this would lead to comprehensive planning for the design and construction of hydraulic structures.
کلیدواژه‌ها [English]
- Meta-heuristic Algorithms
- Sediment Transport
- Watershed
- Sediment discharge
- Abdi-Dehkardi, M., M. Meftah-Helghi, A.A. Dehghani and M. Hesam. 2011. Application of genetic algorithm to optimize the sediment rate equation coefficient. 5th National Conference on Watershed Management and Water Resources Management in Iran (in Persian).
- Afan, H.A., A. El-Shafie, Z.M. Yaseen, M.M. Hameed, W.H.M. Wan Mohtar and A. Hussain. 2015. ANN-based sediment prediction model utilizing different input scenarios. Water Resources Management, 29(4): 1231-1245 (in Persian).
- Atashpaz Gargari, A. 2008. Development of social optimization algorithm and its efficiency review. MSc Thesis, Faculty of Electrical and Computer Engineering, University of Tehran, 125 pages.
- Bahmanesh, J., M. Mohammadpour and M. Mehdi Bateni. 2017. Comparison of river suspended sediment load estimation using regression and GA methods. Journal of Watershed Management Research, 8(16): 132-141.
- Chogani, Z. 2016. Suspended sediment and sediment bed loads modeling using Bayesian network and Gene Expression Programming (GEP), case study: Chamryz Kor River Station. MSc Thesis in Hydraulic Structures, Department of Water Engineering, Faculty of Agriculture, Shahid Bahonar University of Kerman, 101 pages (in Persian).
- Emami, H. and F. Derakhshan. 2015. Election algorithm: a new socio-politically inspired strategy. AI Communications, 28: 591–603.
- Fath Abadi, A., S.M. Seyedian and H. Rouhani. 2016. Suspended sediment load using a combination of support vector machines and genetic algorithms. First National Conference on Soil Conservation and Watershed Management, Tehran, 8-10 February (in Persian).
- Ghorbani, M.A. and R. Dehghani. 2017. Comparisons of Bayesian neural networks and artificial neural network to estimate suspended sediments in the rivers, case study: Simineh Rood. Journal of Environmental Science and Technology, 19(2): 1-13.
- Hayatzadeh, M., M.R. Ekhtesasi, H. Malekinezhad, A. Fathzadeh and H.R. Azimzadeh. 2017. Determination of the optimal method to estimate the suspended sediment load in arid regions, case study: Fakhrabad Basin in Mehriz, Yazd. Journal Water Soil Scince, (Science and Technology Agriculture and Natural Resources), 21(1): 113-125 (in Persian).
- http://www.Iran hydrology.net/DATA/i anrivers.htm.
- http://www.shahinpayam.ir/index.as.2siteid=20 and pageid=537 and newsview=10129.
- Keramati Roustami, A. 2013. Optimal estimation of suspended sediment in rivers using data splite method. MSc Thesis, Faculty of Water and Soil Engineering, Gorgan University of Agriculture Sciences and Natural Resources, 154 pages (in Persian).
- Kitsikoudis, V., E. Sidiropoulos and V. Hrissanthou. 2014. Machine learning utilization for bed load transport in gravel-bed Rivers. Water Resources Management, 28(11): 3727-3743.
- Kisi, O. and G. Aytac. 2012. A machine code-based genetic programming for suspended sediment concentration estimation. Advances in Engineering Software, 2: 939–945.
- Larose, D.T. 2005. Discovering knowledge in data: an introduction to data mining. Traduction et Adaptation de Thierry Vallaud, 240 pages.
- Mansoori, B., H. Ahmadzadeh, A. Bavani, S. Massah, M. Morid, M. Delavar and S. Lotfi. 2015. Assessment of climate change impacts on water resources in Zarrinehrud Basin using SWAT model. Journal of Water and Soil, 28(6): 1191-1203 (in Persian).
- Mohamadrezapour, O., P. Haghighatjou and M.J. Zeynali. 2015. Compression of genetic algorithm and particle swarm algorithm models for optimizing coefficients of sediment rating curve in estimation of suspended sediment in Sistan River, case study: Kohak Station. Journal of Irrigation and Water Engineering, 6(2): 76-89 (in Persian).
- Mirjalili, S. and S.M. Mirjalili. 2014. Grey wolf optimizer. Advances in Engineering Software, 69(92): 46-61.
- Mech, L.D. 1999. Alpha status, dominance and division of labor in wolf packs. Canadian Journal of Zoology, 77(8): 1196-1203.
- Muro, C., R. Escobedo, L. Spector and R. Coppinger. 2011. Wolf-pack (canis lupus) hunting strategies emerge from simple rules in computational simulations. Behavioural Processes, 88(3): 192-197.
- F., M. Azari and M.T. Dastorani. 2018. Optimizing coefficients of sediment rating curve equation using genetic algorithm, case study: Ghazaghli and Bagh Abbasi stations. Journal of Irrigation and Water Engineering, 9(35): 82-97.
- Roshangar, K., M.T. Aalami and F. Vojoudi Mehrabani. 2016. Enhancing accuracy of sediment total load prediction using evolutionary algorithms, case study: Gotoorchay River. Journal of Water and Soil, 29(6): 1416-1426.
- Sheikhali Pour, Z., F. Hassan Pour and V. Azimi. 2015. Comparison of artificial intelligence methods in estimation of suspended sediment load, case study: Sistan River. Journal of Water Soil Conservation, 22(2): 41-60 (in Persian).
- Sattari, M.T. and F. Safdari. 2016. Performance evaluation of M5 tree model and support vector regression methods in suspended sediment load modeling. Journal of Water and Soil Resources Conservation, 9(6): 109-124 (in Persian).
- Tabatabaie, M.R., Saleh Pourjam and S.A. Hosseini. 2019. A new approach to increasing the performance of the sediment rate curve model in estimating suspended sediment load of watersheds, case study: Mahabadchay River, Urmia Lake Basin, West Azerbaijan Province. Journal of Watershed Management Research, 2: 15-36 (in Persian).
- Vafaienejad, A.R., Z. Chatrsimab, S. Bloori and F. Mirdar-Harijani. 2017. Optimization of sediment rate curve equation coefficient in estimating of sediment discharge using PSO and SA algorithms, case study: Bijar Station. Journal of Natural Ecosystems of Iran, 8(3): 69-82.
- Yeghaneh-Bakhtiari, A. and A. Kazemi. 2013. Two-pahase bed load transfer modeling using a lagrangian model based on smoothed-particle hydrodynamics methodology. Iran Water Resources Management Company, Applied Research office, Applied Research Project, Iran University of Science and Technology (in Persian).
Zakaria, N.H., M.D. Azamathulla and C.K. Chang. 2010. Gene expression programming for total bed material load estimation, a case study. Science of the Total Environment, 408 pages.
)