نشریه علمی - پژوهشی مرتع و آبخیزداری

نوع مقاله : مقاله پژوهشی

نویسندگان

1 کارشناسی ارشد عمران-آب، باشگاه پژوهشگران جوان و نخبگان، واحد مراغه، دانشگاه آزاد اسلامی، مراغه، ایران.

2 استادیار، مهندسی منابع آب، گروه مهندسی آب، دانشکده کشاورزی، دانشگاه تبریز، ایران.

چکیده

برآورد بار رسوبی معلق رودخانه‌ها با توجه به خسارات ناشی از عدم توجه و لحاظ کردن آن، یکی از مهم‌ترین و اساسی‌ترین چالش‌های مطالعات انتقال رسوب و مهندسی رودخانه می‌باشد. با توجه به اهمیت و نقش رسوب در طراحی و نگهداری سازه‌های هیدرولیکی همچون سدها و همچنین برنامه‌ریزی جهت استفاده بهینه از منابع آبی در پایین‌دست رودخانه‌ها و حفظ منابع مغذی بالادست آن­ها، همواره تلاش‌های بسیاری در زمینه تخمین میزان بار رسوبی معلق رودخانه‌ها انجام گرفته و روش‌های متعددی در این زمینه توسعه یافته است. اما با توجه به هزینه‌بر بودن اکثر روش‌ها و یا عدم دقت کافی در اکثر روش‌های تجربی مرسوم، نیاز به روش نوینی که بتواند بار رسوبی معلق رودخانه را با بیشترین دقت ممکن تخمین زند، امری ضروری به نظر می‌رسد. در این مطالعه میزان بار رسوبی معلق رودخانه لیقوان چای توسط روش‌های رگرسیون بردار پشتیبان و k-نزدیک‌ترین همسایگی برآورد گردیدند. نتایج نشان‌دهندۀ عملکرد مناسب هر دو روش داده‌کاوی بررسی شده در این تحقیق می‌باشد. از میان روش‌های بررسی شده در این تحقیق، روش رگرسیون بردار پشتیبان میزان بار رسوبی معلق رودخانه لیقوان چای را با ارائه مقادیر ضریب همبستگی برابر با 959/0 و ریشه میانگین مربعات خطا برابر با 547/43 (تن در روز) با دقت بیشتری نسبت به روش k-نزدیک‌ترین همسایگی پیش‌بینی کرد.

کلیدواژه‌ها

عنوان مقاله [English]

Comparison of the Efficiency of Support Vector Regression and K-Nearest Neighbor Methods in suspended sediment load Estimation in river (Case Study: Lighvan Chay River)

نویسندگان [English]

  • ali rezazadeh joudi 1
  • Mohammad Taghi Sattari 2

1 Msc. islamic azad university of Maragheh Branch

2

چکیده [English]

Estimation of suspended sediment load or specifying the damages incured as a result of inattention to such estimation is one of the most important and fundamental challenges in river engineering and sediment transport studies. Given the importance and role of sediment in the design and maintenance of hydraulic structures such as dams, as well its significance in planning for efficient tilization of downstream river and also conservation of nutrients at the upstream of river, many attempts have been made to estimate suspended sediment load of rivers and numerical methods have been developed in this regard. But due to the high cost of most procedures or lack of adequate precision in most common experimental methods, a new method is needed that can estimate suspended sediment load with the greatest possible precision. In this study, the amount of suspended sediment load of Lighvan River has been estimated through support vector regression and k-Nearest neighbor methods. Results indicated the appropriateness of both data mining techniques applied in this study. Among examined methods in this study, the support vector regression method predicted the amount of suspended sediment load in LighvanChay River with representing evaluation indexes such as (CC=0.959, RMSE=43.547(ton/day)) more accurately than K-nearest neighbor method

کلیدواژه‌ها [English]

  • k-nearest neighbors
  • LighvanChayriver
  • Data Mining
  • Support Vector Regression
  • Suspended sediment load
[1].        Azmi, M. and Araghi nejed, Sh. (2011). Development of K-Nearest Neighbor Regression Method in Forecasting River Stream Flow, Journal of Water & Wastewater, 2,108-119. (In Persian)
[2].        Dehgani, A.A., Malek Mohammadi, M. and Hezarjaribi, A. (2010). Estimation of Suspended Sediment Load in Behesht Abad River by Using Artificial Neural Network, Journal of Water and Soil Conservation, 17(1), 159-168. (In Persian)
[3].        Eder, A., Strauss a, P., Krueger b, T. and Quinton b, J.N. (2010). A Comparative calculation of suspended sediment loads with respect to hysteresis effects (in the Petzenkirchen catchment, Austria), Journal of Hydrology, 389, 168-176.
[4].        Falamaki, A., Eskandari, M., Baghlani, A. and Ahmadi, S.A. (2013). Modeling total sediment load in rivers using artificial neural networks, journal of water and soil conservation, 2(3), 13-25. (In Persian)
[5].        Iadanza, C. and Napolitano, F. (2006). Sediment transport time series in the Tiber River, Physics and Chemistry of the Earth, 31, 1212-1227.
[6].        Kakaei Lafdani, E., Moghaddam Nia, A. and Ahmadi, A. (2013). Daily Suspended Sediment Load prediction Using Artificial Neural Networks and Support Vector Machines, Hydrology, 478, 50-62.
[7].        Kao, Sh., Lee, T. and Milliman, J.D. (2005). Calculating highly fluctuated suspended sediment fluxes from mountainous rivers in Taiwan, TAO, 16(3), 653-675.
[8].        Khazaie Poul, A. and Talebi, A. (2013). Investigation of Possibility of Suspended Sediment Prediction Using The Combination of Sediment Rating Curve and Artificial Neural Network (Case Study: Ghatorchai River, Yazdakan Bridge), Quarterly Journal of Environmental Erosion Researches, 2(9), 73-82. (In Persian)
[9].        Kia, E., Emadi, A.R. and Fazlola, R. (2013). Investigation and Evaluation of Artificial Neural Networks in Babolroud River Suspended Load Estimation, Journal of Civil Engineering and Urbanism, 3(4), 183-190.
[10].      Nourani, V. (2014). A Review on Applications of Artificial Intelligence-Based Models to Estimate Suspended Sediment Load, International Journal of Soft Computing and Engineering (IJSCE), 3(6), 121-127.
[11].      Onderka, M., Krein, A. and Wrede, S. (2012). Dynamics of storm-driven suspended sediments in a headwater catchment described by multivariable modeling, Journal of Soils Sediments, 12, 620–635.
[12].      Ozturk, F., Apaydin, H. and Walling, D.E. (2001). Suspended Sediment loads through flood events for stream of sakarya Basin, Turkish Journal of Engineering and Environmental Sciences, 25, 643-650.
[13].      Partal, T. and Cigizoglu, H.K. (2008). Estimation and forecasting of daily suspended sediment data using wavelet neural networks, Journal of Hydrology, 358, 317-331.
[14].      Rajabi, M., Feizollahpour, M. and Roustaie, S. (2015). Using NDE model for estimation of suspended sediment load in comparison with ANFIS and RBF case study: Givi Chay, Geography and Development Iranian Journal, 39(2), 1-16. (In Persian)
[15].      Rastgar, H. and Habibi, M. (2011). Assessment of five sediment estimation methods in the Jegin River in Hormozgan province, Journal of Engineering and watershed management, 3(1),12-20. (In Persian)
[16].      Sattari, MT., Rezazazadeh Joudi, A. and Kusiak, A. (2015). Estimation of water quality parameters with data-driven models, American Water Works Association, 108(4): 232-239.
[17].      Sattari, MT., Rezazadeh Joudi, A., Safdari, F. and Ghahramanzadeh, F. (2016). Performance Evaluation of M5 Tree Model and Support Vector Regression Methods in Suspended Sediment Load Modeling, Journal of Water and Soil Resources Conservation, 6(1), 109-124. (In Persian)
[18].      Shafaie, B. (2011). Sediment hydraulic, Shahid Chamran University, Press. (In Persian)
[19].      Shahrabi, J. (2013). Data mining 2, Tehran, Industrial university of amirkabir, Jahad daneshgahi Press. (In Persian)
[20].      Shahrabi, J., Hejazi, T.H. (2011). Data mining. Tehran, Industrial University of amirkabir, Jahad daneshgahi Press. (In Persian)
[21].      Tabatabaei, M., Solaimani, K., Habibnejad Roshan, M. and Kavian, A. (2014). Estimation of Daily Suspended Sediment Concentration using Artificial Neural Networks and Data Clustering by Self-Organizing Map (Case Study: Sierra Hydrometry Station- Karaj Dam Watershed), Journal of Watershed Management Research, 5(10), 98-116.  (In Persian)
[22].      Vali, A., Moayeri, M., Ramsht, M.H. and Movahedinia, N. (2010). Analysis and Comparison of artificial neural networks and regression models in suspended sediment Prediction case study: Eskandari Catchment Area located in Zayanderood Basin, journal of Physical Geography Research Quarterly, 71(1), 21-30. (In Persian)
[23].      Vali, A.A., Ramesht, A., Seif, A. and Ghazavi,R. (2010). An assessment of the Artificial Neural Networks technique to geomorphologic modeling sediment yield (Case study Samandegan river system), Geography and Environmental Planning Journal, 44(4), 19-34. (In Persian)
[24].      Vapnik, V. N. (1995). The nature of statistical learning theory, Newyork: springer-verlag.
[25].      Yang, C.T., Marsooli, R. and Aalami, M.T. (2009). Evaluation of total load sediment transport formulas using ANN, International journal of Sediment Research, 24, 274-286.
[26].      Zhou, Y., Lu, X.X., Huang, Y. and Zhu, Y.M. (2007). Suspended sediment flux modeling with artificial neural network: An example of the Longchuanjiang River in the upper Yangtze catchment, China. Journal of Geomorphology, 84, 111-125.