نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجوی دکترای مهندسی آب، دانشگاه ارومیه، اومیه، ایران

2 استادیار، مرکز آموزش و تحقیقات کشاورزی و منابع طبیعی استان کردستان، سنندج، ایران

3 کارشناس ارشد آبیاری و زهکشی، دانشگاه بوعلی سینا همدان، همدان، ایران

4 استادیار، گروه مهندسی آب، دانشکده کشاورزی، دانشگاه ارومیه، ارومیه، ایران

چکیده

بار رسوب جریان، شاخص مفیدی در پیش‌بینی فرسایش خاک در حوزه‌های آبخیز است؛ بنابراین تدوین مدلی برای برآورد بار رسوب می‌تواند در مدیریت و اجرای پروژه‌های آبخیزداری و مهندسی رودخانه مفید باشد. در این پژوهش روش دسته‌بندی داده‌ها به‌عنوان راه‌کاری برای افزایش دقت شبکه عصبی مصنوعی در تدوین مدل برآورد رسوب معلق بررسی شد. بدین منظور، میزان آورد رسوبات معلق رودخانه‌های خلیفه‌ترخان و چهل‌گزی در حوضۀ قشلاق در استان کردستان در سه حالت با روش شبکه عصبی مصنوعی با ساختار پرسپترون چندلایه برآورد شد. ابتدا داده‌های اندازه‌گیری شده، بدون هیچ‌گونه تفکیکی مدل‌سازی شدند. سپس داده‌های رواناب برمبنای وضعیت جریان به زیرمجموعه‌های پرآب و کم‌آب و داده‌های رسوب برمبنای غلظت رسوبات به زیرمجموعه‌های غلظت کم‌وزیاد دسته‌بندی شدند. از داده‌های مشاهده‌ای رواناب و رسوب برای واسنجی مدل‌ها استفاده شد. سپس مقادیر برآورد شده با داده‌های ثبت‌شده مقایسه و عملکرد این مدل‌ها با استفاده از معیارهای آماری مورد ارزیابی قرار گرفت. نتایج بیانگر نقش مؤثر دسته‌بندی داده‌ها در بهبود عملکرد روش شبکه عصبی مصنوعی در برآورد رسوب است. به‌طوری‌که دسته‌بندی برمبنای غلظت رسوبات کارآیی مدل را در ایستگاه‌های چهل‌گزی و خلیفه‌ترخان به ترتیب 6/16 و 5/30 درصد افزایش داد. مقایسه دسته‌بندی‌های انجام‌شده نیز نشان داد که دسته‌بندی داده‌ها برمبنای غلظت رسوبات نسبت شدت‌جریان رودخانه مؤثرتر است. نتایج این پژوهش می‌تواند با تخمین دقیق‌تر میزان رسوبات معلق رودخانه‌های منتهی به دریاچۀ سد قشلاق، در بهبود مدیریت حوضه مورداستفاده قرار گیرد.

کلیدواژه‌ها

عنوان مقاله [English]

Assessing the Artificial Neural Network Efficiency to Estimate Suspended Sediment Load using Classified Data

نویسندگان [English]

  • Homayoun Faghih 1
  • Ata Amini 2
  • Farzane Haidari 3
  • Keivan Khalili 4

1 PhD. Scholar, Department of Water Engineering, Urmia University, Urmia, Iran

2 Assistant Prof. Kurdistan Agricultural and Natural Resources Research Center, AREO, Sanadaj, Iran

3 Department of Irrigation and Drainage, Faculty of Agriculture, University of Bu-Ali Sina, Hamadan, Iran

4 Assistant Professor, Department of Water Engineering, Faculty of Agriculture, Urmia University, Urmia, Iran

چکیده [English]

Flow sediment load is a useful indicator in predicting soil erosion in watersheds. As a result, developing a model to estimate sediment load can be useful in the management and operations of watersheds and river engineering projects. In this study, the data classification was studied as a way to increase the accuracy of Artificial Neural Network (ANN) model for estimating suspended sediment. For this purpose, the amount of suspended sediments in the Khalifa-Tarkhãn and Chehelgazi Rivers in Gheshlagh watershed, Kurdistan, Iran was predicted in three modes using an ANN with multilayer configurations. The measured data were also modeled without such classification. Then the runoff data were classified as high and low flows and the sediment data based on sediment concentration were classified as high and low concentrations. The observed runoff and sediment data were used to calibrate the models. Then the calculated values were compared with observed data and the models efficiency was examined using statistical tests. The findings indicate the effective role of data classification in improving the ANN efficiency in sediment estimation. So that classification based on sediment concentration promoted the model efficiency in Chehelgazi and Khalifa-Tarkhān by 16.6 and 30.5% respectively. The comparison of classifications showed that in comparison with flow, the sediment classification has more affective role on models estimations. The results of this study can be used to improve the management of the basin by more accurately estimating suspended sediments transporting in the rivers leading to Gheshlagh Dam Reservoir.

کلیدواژه‌ها [English]

  • Hydrometry
  • ANN
  • Gheshlagh Watershed
  • Sediment Concentration
  • Kurdistan
Arabkhedri M. (2005). Investigation of suspended load in Iran’s watershed basin. Iranian J. Water Resour., 20(2), 51-60.
 
Asefa T., Kemblowski M., Mc Kee M. and Khalil A. (2006). Multi-time scale stream flow predictions, the support vector machines approach. J. Hydrol., 318(1–4), 7–16.
 
Asselman N. (2000). Fitting and interpretation of sediment rating curves. J. Hydrol., 23(4), 228-248.
 
Dehghani A. A., Zanganeh M. A., Mosaedi A. and Kohestani N. (2009). Comparison of suspended sediment estimation by artificial neural network and sediment rating curve methods (Case study: Doogh River in Golestan Province). J. Agric. Sci. Natur. Resour., 1(16), 266-276 [In Persian].
 
Faghih, H. (2010). Evaluating artificial neural network and its optimization using genetic algorithm in estimation of monthly precipitation data (Case study: Kurdistan Region), J. Wat. Soil Sci., 14(51), 27-42 [In Persian].
 
Falamaki A., Eskandari M., Baghlani A. and Ahmadi S. A. (2013). Modeling total sediment load in rivers using artificial neural networks. J. Wat. Soil Resource Conservation, 3(3), 13-25 [In Persian].
 
Fatahi M, Tousi S. and Ahmadi M. Z. (2006). Sedimentation estimation of Neka River using artificial neural network, The 7th International Seminar on River Engineering, Shahid Chamran University, Ahvaz, Iran [In Persian].
 
Hagan M. T. and Menhaj M. B. (1994). Training feed forward networks with the Marquardt algorithm. IEEE, ransom neural networks 5.
 
Harma N., Zakaullah M.D., Tiwari H. and Kumar D. (2015). Runoff and sediment yield modeling using ANN and support vector machines: a case study from Nepal watershed. Earth Sys., 1(1),14- 23.
 
Hassanzadeh Zardkhooni M., Sedghi Asl M. and Prvizi M. (2015). Evaluation of the hydrological methods for predicting suspended sediment load in rivers (Case study: Chamsiah River). Iran Wat. Res. J., 9(1), 41-48 [In Persian].
 
He Z., Wen X., Liu H. and Du J. (2014). A comparative study of artificial neural network, adaptive neuro fuzzy inference system and support vector machine for forecasting river flow in the semiarid mountain region. J. Hydrol., 509(5), 379–386.
 
Joorabian M. and Zare-Omid-Ostovar T. (2009). Artificial neural networks. Shahid Chamran University Press, Ahvaz, Iran [In Persian].
 
Juston J., Jansson P. E. and Gustafsson D. (2014). Rating curve uncertainty and change detection in discharge time series, case study with 44-Year historic data from the Nyangores River, Kenya. Hydrol. Process. 28(10), 2509–2523.
 
Kalteh A. M. (2013). Monthly river flow forecasting using artificial neural network and support vector regression models coupled with wavelet transform. Comput. Geosci., 54(5), 1–8.
 
Karami A., Homaee M., Neyshabouri M. R., Afzalinia S. and Basirat S. (2012). Large scale evaluation of single storm and short/long term erosivity index models. Turkish J. Agricul. Forestry, 36(2), 207-216.
 
Kerem Cigizoglu H. and Kisi O. (2006). Methods to improve the neural network performance in suspended sediment estimation. J. Hydrol., l317(3–4), 221–238.
 
Kisi O. (2010). River suspended sediment concentration modeling using a neural differential evolution approach. J. Hydrol., l389 (1), 227–235.
 
Lin L., Xiaolong Z., Kai Z. and Jun L. (2014). Bilinear grid search strategy based support vector machines learning method. Informatica, 38(8), 51–58.
 
Mirzaei M. (2002). Comparison of statistical estimating methods of the rivers suspended loads, M.Sc. Dissertation, Faculty of Natural Resources, University of Tehran, Iran [In Persian].
 
Mustafa M., Isa R. M. H. and Rezaur R. B. (2011). A Comparison of Artificial Neural Networks for Prediction of Suspended Sediment Discharge in River, A Case Study in Malaysia. World Academy of Sci., Eng. Technol. (WASET)., 81(9), 372-376.
 
Raghavendra N. S. and Deka P. C. (2014). Support vector machine applications in the field of hydrology: a review. Appl. Soft. Comput., 19(6), 372–386.
 
Razavizadeh S., Kavian A. and Vafakhah M. (2014). Estimation of suspended sediment discharge by optimal structure of artificial neural network in Taleghan Watershed. J. Wat. Soil Sci., 2(68), 79-87 [In Persian].
 
Rezaei Pazhand H. (2001). Application of statistic and probability in water resources, SokhanGostar Publisher, Tehran, Iran [In Persian].
 
Sadeghi H. (2005). Development of sediment rating curve equations for rising and falling limbs of hydrograph using regression models. Iranian J. Wat. Resour., 1(1), 101-103.
 
Samadzadeh R., Khayyam M. and Fazeli A. (2013). Modelling of estimation of the suspended load in Ardabil Darehrud basin, Geog. Environ. Plan., 2(51), 153-178 [In Persian].
 
Sarangi A. and Bhattacharya A. K. (2005). Comparison of Artificial Neural Network and regression models for sediment yield prediction from Banha watershed in India. J. Agricul. Water Manag. 78(9), 195-208.
 
Shafaei Bajestan M. (2011). Theoretical and practical fundamental of sediment transfer hydraulic, Shahid Chmran University Publisher, Ahvaz, Iran [In Persian].
Singh A., Imtiyaz M., Isaac R. and Denis D. (2012). Comparison of soil and water assessment tool (SWAT) and multilayer perceptron (MLP) artificial neural network for predicting sediment yield in the Nagwa agricultural watershed in Jharkhand, India. Agric Water Manag, 104(2), 113–120
 
Tan Y. and Van Cauwenberghe A. (1999). Neural-Network-Based d-step-ahead predictors for nonlinear systems with time delay. Eng. Appl. Artificial Intell,12 (2), 21-35.
 
Telvari A. (2001). The relation of suspended sediment with some of the watershed characteristics in Dez and Karkhe in Lorestan province. J. Res. Construc., 15 (56), 47-56.
 
Teshnehlab M. and Monshi M. (2003). Climatic forecasting of meteorological parameters using fuzzy-neural networks based on the Tally education parameters. The 3rd Regional Conference on Climatic Changes, Isfahan, Iran [In Persian].
 
Yu X. Y., Liong S. Y. and Babovic V. (2004). EC-SVM approach for realtime hydrologic forecasting. J. Hydroinform., 6(3), 209–223.
 
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. Geomorphology, 84(8), 111-125.