مدل‌سازی جامدات محلول با استفاده از روش‌های هیبریدی محاسبات نرم (مطالعۀ موردی: حوضۀ آبریز نازلوچای)

نوع مقاله : پژوهشی

نویسندگان

1 دانشجوی دکتری مهندسی منابع آب دانشگاه ارومیه

2 دانشیار گروه مهندسی آب دانشگاه ارومیه

3 استادیار گروه مهندسی آب دانشگاه کردستان

چکیده

رودخانه‏ها اهمیت بسیار زیادی در تأمین آب آشامیدنی و کشاورزی دارند. در این مطالعه، قابلیت روش‏‏های منفرد و هیبریدی‌ـ موجکی شبکه‏های عصبی، سامانۀ استنتاجی عصبی‌ـ فازی تطبیقی و برنامه‏ریزی بیان ژن برای مدل‌سازی میزان جامدات محلول حوضۀ آبریز نازلوچای ارزیابی شدند. به این منظور از داده‏های کیفیت آب با طول دورۀ آماری 19 ساله (1372-1390)، چهار ایستگاه هیدرومتری واقع در حوضۀ آبریز نازلوچای استفاده شد. پس از بررسی صحت داده‏ها و ایستگاه‏های منتخب، با استفاده از تبدیل موجک دابچیز نوع چهارم، سیگنال‏های داده‏های مربوط به آن آنالیز شد. در مدل‌سازی از 80 درصد داده‏ها برای آموزش و 20 درصد داده‏ها برای آزمون مدل‏ها استفاده شده است. ارزیابی عملکرد مدل‏های به‌کار‌رفته بر اساس آزمون‏های آماری مختلف، ضریب همبستگی، ریشۀ میانگین مربعات خطا و میانگین قدر مطلق خطا انجام گرفت. نتایج بیان‌کنندۀ عملکرد قابل قبول همۀ روش‏های منفرد و هیبریدی‌ـ موجکی شبکۀ‏ عصبی مصنوعی، سامانۀ استنتاجی عصبی‌ـ فازی تطبیقی و برنامه‏ریزی بیان ژن برای مدل‌سازی میزان جامدات محلول در حوضۀ آبریز نازلوچای است؛ ولی به‌ترتیب اولویت WGEP، GEP، WANFIS، ANFIS-SC،WANN، ANFIS-GP و ANN عملکرد بهتری دارند. همچنین مدل هیبریدی برنامه‏ریزی بیان ژن‌ـ موجکی با داشتن کمترین میزان RMSE به مقدار 078/21 بهترین عملکرد را در بین سایر مدل‏های منفرد و هیبریدی دارد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Moldeling Of Dissolved Solids By Using Hybrid Soft Computing Methods (Case Study: Nazluchay Basin)

نویسندگان [English]

  • Sarvin Zamanzad Ghavidel 1
  • Majid Montaseri 2
  • Hadi Sanikhani 3
1 Ph.D Student, Water Resources Engineering, Urmia University
2 Assistant Professor, Department of Water Engineering, Urmia University
3 Assistant Professor, Department of Water Engineering, Kurdistan University
چکیده [English]

Rivers has important roles in providing drinking and agricultural water supply. In this study, single and hybrid-wavelet methods of artificial neural networks, adaptive neuro fuzzy inference system and Gene expression programming were validated total dissolved solids modelling of Nazluchay Basin. Therefore, water quality data with 19 years length (1993-2011), four hydrometric stations at Nazluchay Basin, were used. After validating of data and selected stations, the data were analyzed by using Daubechies-4 wavelet transform. For modelling 80% of data for training and 20% of data for testing of the model were used. The evaluation of models performance is applied based on different statistical tests, correlation coefficient, and mean root of error squares and mean absolute error. The results indicate acceptable performance of all single and hybrid-wavelet methods of artificial neural networks, adaptive neuro fuzzy inference system and Gene expression programming for modeling the total dissolved solids in the Nazluchay basin. Based on WGEP, GEP, WANFIS, ANFIS-SC, WANN, ANFIS-GP and ANN have best performance, respectively. In addition Gene expression programming-wavelet hybrid model with the minimum RMSE amounted 21.078 has best performance compared with other single and hybrid models.

کلیدواژه‌ها [English]

  • gene expression
  • Wavelet transform
  • Dissolved Solids
  • Nazluchay
1. Rajaee T, Jafari H. Prediction of Water Sodium Absorption Ratio (SAR) using ANN and Wavelet Conjunction Model (Case Study: Rudbar Station of Sefidrud River). Journal pf water and soil. 2016; 26(2.2): 189-205.
2. Banejad H, Kamali M, Amirmoradi K, Olyaie E. Forecasting Some of the Qualitative Parameters of Rivers Using Wavelet Artificial Neural Network Hybrid (W-ANN) Model (Case of study: Jajroud River of Tehran and Gharaso River of Kermanshah). Iran. J. Health & Environ. 2012; 6(3).[Persian]
3. Guang-ming Z, Hong-wei L, Xiang-can J, XU M. Assessment of the water quality and nutrition of the Dongting lake with wavelet neural network. Journal of Hunan University. 2005; 32:91-94.
4. Sengorur B, Dogan E, Koklu R, Samandar A. Dissolved oxygen estimation using artificial neural network for water quality control. Fresenius Environmental Bulletin. 2006; 15:1064–1067.
5. Noorani V, Salehi K. Modeling of rainfall - runoff using fuzzy neural network and adaptive neural networks and fuzzy inference methods compare. Prosceedings of 4th National Congress on Civil Engineering. 2008; Tehran. [Persian]
6. Zhou HC, Peng Y, Liang G-H. The research of monthly discharge predictor-corrector model based on wavelet decomposition. Water Resour Manag. 2008; 22(2):217–227.
7. Najah A, Elshafie A, Karim O, Jaffar O. Prediction of Johor river water quality parameters using artificial neural networks. European Journal of Scientific Research. 2009; 28: 422-35.
8. Sighn KP, Basant A, Malik A, Jain G. Artificial neural network modeling of the river water quality-A case study. Ecological Modelling. 2009; 220: 888–895.
9. Rajaee T. Wavelet and neuro-fuzzy conjunction approach for suspended sediment prediction. Clean-Soil Air Water. 2010; 38(3):275–286. [Persian]
10. Kisi O, Shiri J. Precipitation forecasting using wavelet-genetic programming and wavelet-neuro-fuzzy conjunction models. Water Resour Manag. 2011; 25:3135–3152.
11. Xu L, Liu S. Study of short-term water quality prediction model based on wavelet neural network. Mathematical and Computer Modelling. 2013; 58.(3-4):807-813.
12. Moosavi V, Vafakhah M, Shirmohammadi B, Ranjbar M. Optimization of wavelet-ANFIS and wavelet-ANN hybrid models by Taguchi method for groundwater level forecasting. Arab. J. Sci. Eng. 2013b; DOI 10.1007/s13369-013-0762-3.
13. Ghavidel S.Z.Z, Montaseri M. Application of different data-driven methods for the prediction of total dissolved solids in the Zarinehroud basin. Stochastic environmental research and risk assessment. 2014; 28(8): 2101-2118.
14. Yarar A. A hybrid wavelet and neuro-fuzzy model for forecasting the monthly streamflow data. Water Resour Manag. 2014; 28:553–565.
15. Alizadeh MJ, Kavianpour MR. Development of wavelet-ANN models to predict water quality parameters in Hilo Bay, Pacific Ocean. Marine Pollution Bulletin. 2015; 98(1-2):171-178.
16. Özger M, Burak Kabataş M. Sediment load prediction by combined fuzzy logic-wavelet method. Journal of Hydroinformatcs. 2015; 17 (6): 930-942.
17. Ravansalar M, Rajaee T, Ergil M. Prediction of dissolved oxygen in River Calder by noise elimination time series using wavelet transform. Journal of Experimental & Theoretical Artificial Intelligence. 2015; DOI:10.1080/0952813X.2015.1042531.
18. Shafaei M, Kisi O. Lake Level Forecasting Using Wavelet-SVR Wavelet-ANFIS and Wavelet-ARMA Conjunction Models. Water Resources Management. 2015; DOI:10.1007/s11269-015-1147-z.
19. National Geographical Organization.The Gazetter Of Rivers In The I.R Of Iran, Orumiyeh Lake Watershed. National Geographical Organization Publication. 2016; First Volume, p 67 and 77.
20. Toufani P, Mosaedi A, Fakheri Fard A. Prediction of Precipitation Applying Wavelet Network Model (Case study: Zarringol station, Golestan province, Iran). Journal of Water and Soil. 2011; 25(5): 1217-1226.
21. Jain SK, Das A, Srivastava DK. Application of ANN for reservoir inflow prediction and operation. Journal of Water Resources Planning and Management, ASCE. 1999; 125(5) 263-271.
22. Caudill M. Neural networks primer: Part I. AI Expert. 1987; 2(12): 46-52.
23. Shafaei Y, Farzaneh M, Teshnehlab M. Modeling of producting trip by using Adaptive Neuro-Fuzzy. Issue of Engineering Faculty. 2002; 36(3): 361-170. [Persian]
24. Aalami M.T, Sadeghfam S, Fazelifard M.H, Naghipour L. Data Series Modeling. 2013; Tabriz, University of Tabriz.
25. Barzegar R, Adamowski J, Asghari Moghaddam A. Application of wavelet-artificial intelligence hybrid models for water quality prediction: a case study in Aji-Chay River, Iran. Stoch Environ Res Risk Assess. 2016; DOI 10.1007/s00477-016-1213-y.