عملکرد شبکۀ عصبی مصنوعی در پیش ‏بینی و تحلیل فرایندهای هیدرولوژیک (مطالعۀ موردی: کمبود آب حوضۀ آبخیز نازلوچای در استان آذربایجان غربی)

نوع مقاله : پژوهشی

نویسندگان

1 استادیار، گروه مهندسی آب و سازه‏ های هیدرولیکی، دانشکدۀ مهندسی عمران، دانشگاه سمنان‌

2 استادیار، گروه مهندسی آب و سازه‏های هیدرولیکی، دانشکدۀ مهندسی عمران، دانشگاه سمنان‌

3 دانشجوی کارشناسی ارشد مهندسی و مدیریت منابع آب، دانشکدۀ مهندسی عمران، دانشگاه سمنان

چکیده

بارش یکی از فرایند‏های هیدرولوژیک است که تأثیر زیادی در کنترل مدیریت منابع آب دارد. کمبود بارش سبب به‌وجود‌آمدن مشکلات فراوانی از جمله کمبود آب شرب می‏شود. به‌علت اهمیت مسئلۀ کمبود آب، استفاده از روش‏های نوین به‏منظور پیش‏بینی فرایند‏های هیدرولوژیک تأثیر زیادی در برنامه‏ریزی و مدیریت منابع آب خواهد داشت. از این‌رو، در تحقیق حاضر کمبود آب ماهانه در حوضۀ نازلوچای طی یک دورۀ آماری 39ساله (1352‌ـ 1391) با استفاده از مدل شبکۀ عصبی مصنوعی و مدل بهبودیافتۀ موجک‌ـ شبکۀ عصبی، شبیه‏سازی، پیش‏بینی و تحلیل شده است. عملکرد این دو مدل توسط معیار‏های خطای ضریب همبستگی، ضریب تبیین و جذر میانگین مربعات خطا ارزیابی شد. بنا بر نتایج به‌دست‌آمده، مدل موجک‌ـ شبکۀ عصبی با ضریب همبستگی 96/0 و 945/0 که به‌ترتیب مختص به حالت آموزش و آزمون است، نسبت به شبکۀ عصبی مصنوعی توانایی بیشتری برای پیش‏بینی کمبود آب داشت. در ادامه، مقادیر کمبود آب ماهانه در این حوضه طی سال‏های 1392 تا 1399 پیش‏بینی شده است. نتایج نشان می‌‏دهند روند کمبود آب همچنان مانند گذشته باقی است. البته، متوسط میزان کمبود در 8 سال آینده تقریباً 95/2 میلیون متر‌مکعب تخمین زده شد. در حالی که همین پارامتر برای 39 سال گذشته 04/4 میلیون متر‌مکعب بوده است. از این‌‏رو، نیاز است که برای سال‏های آینده اقدامات لازم انجام شود و با برنامه‏ریزی مدیریتی دقیق برای بهره‏برداری از منابع آب (کشاورزی، صنعت، شرب و...)، کاهش میزان کمبود آب در سال‏های آتی ممکن شود.
 

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

The performance of Artificial Neural Network in prediction and analysis of hydrological processes (Case study: Water shortage in Nazloo-chai watershed, West Azerbaijan province)

نویسندگان [English]

  • Saeed Farzin 1
  • Hojat Karami 2
  • Mahsa Doostmohammadi 3
  • Anese Ghanbari 3
  • Elham Zamiri 3
1 Assistant Professor, Faculty of Civil Engineering, Semnan University, Semnan, Iran
2 Assistant Professor, Faculty of Civil Engineering, Semnan University, Semnan, Iran
3 M.Sc. Student, Faculty of Civil Engineering, Semnan University, Semnan, Iran.
چکیده [English]

Precipitation is one of the hydrological processes that play an important role in controlling water resources management. Shortage of rain causes some problems such as lack of drinking water. Due to the importance of the issue of water shortage, using modern methods to predict hydrological processes will play an important role in planning and management of water resources. Therefore, in this study, monthly shortage of water in Nazloo-chai watershed was predicted using Artificial Neural Network (ANN) and improved wavelet-neural network (IWNN) models, for the past 39 years (1973-2012). Performance of these two models was evaluated using statistical indicators including correlation coefficient (R), determination coefficient (R2) and root mean square error (RMSE). According to the results of IWNN model, the obtained correlation coefficient was 0.960 and 0.945 for testing and training modes, respectively, and this model has greater ability for predicting the shortage of water in comparison with ANN. Accordingly, the amount of monthly water shortage in this watershed was predicted for 2013 to 2020. Results indicated that shortage of water still remains as in the past years. The average water shortage was estimated nearly as 2.95 million cubic meters (MCM) in the next 7 years, while, this parameter for the past 39 years was 4.04 MCM. Therefore, it is required to take necessary measures for future years, and with careful management plans for exploitation of water resources (agriculture, industry, urban, etc.), it is possible to reduce water shortage in the coming years.
 
 
 
 
 
 
 
 
 
 

کلیدواژه‌ها [English]

  • Water shortage
  • Artificial Intelligence
  • Wavelet algorithm
  • De-noising
  • Optimized network
مراجع
1. Water and Wastewater Department of Energy Office Planning. Report begin updating the master plan studies of water in watersheds grade 2 Tehran. 2008. [In Persian]
2. Menhaj M. Computational Intelligence (first volume: Foundations of Neural Networks). Amirkabir University Publishers. 2014. Page 716. [In Persian]
 3. Hall T, Brooks HE, Doswell III CA. Precipitation forecasting using a neural network. Weather and forecasting. 1999 Jun;14(3):338-45.
4. Sahai AK, Soman MK, Satyan V. All India summer monsoon rainfall prediction using an artificial neural network. Climate dynamics. 2000 1;16(4):291-302.
5. Ramirez M.C.V, Velho H.F, Ferreira N.J. Artificial neural network technique for rainfall forecasting applied to the Sa˜o Paulo region. Journal of Hydrology. 2005; 301,146–162.
6. Sahoo GB, Ray C. Flow forecasting for a Hawaii stream using rating curves and neural networks. Journal of hydrology. 2006 5;317(1):63-80.
7. Bustami R, Bessaih N, Bong C, Suhaili S. Artificial neural network for precipitation and water level predictions of Bedup River. IAENG International Journal of computer science. 2007 1; 34(2):228-33.
8. Yang ZP, Lu WX, Long YQ, Li P. Application and comparison of two prediction models for groundwater levels: A case study in Western Jilin Province, China. Journal of arid Environments. 2009; 73(4):487-92.
9. Nastos PT, Moustris KP, Larissi IK, Paliatsos AG. Rain intensity forecast using artificial neural networks in Athens, Greece. Atmospheric Research. 2013 31; 119:153-60.
10. Antonopoulos VZ, Gianniou SK, Antonopoulos AV. Artificial neural networks and empirical equations to estimate daily evaporation: application to lake Vegoritis, Greece. Hydrological Sciences Journal. 2016 Jan 16(just-accepted).
11. Faghih H. Evaluating artificial neural network and its optimization using genetic algorithm in estimation of monthly precipitation data (Case Study: Kurdistan Region). JWSS - Isfahan University of Technology. 2010; 14 (51):27-44. [In Persian]
12. Safshekan F, PirMoradian N, Afshin Sharifan R. Simulation of rainfall-runoff hydrograph according to the pattern of rainfall and the use of artificial neural network in kasilian basin. Iran-Watershed Management Science & Engineering. 2011; 5(15):1-10. [In Persian]
13. Fatahi A, Delavar M, Noohi K. North Karun river flow forecasting using artificial neural network. Geographical Research Publishers. 2012; 51-78. [In Persian]
14. Khazaei M, Mirzaei MR. Comparison prediction performance of monthly discharge using ANN and time series. Watershed Engineering and Management. 2013; 5(2): 74-84. [In Persian]
15. Rahmati E, Montazeri M, Gandomkar A, Lashanizand M. Evaporation Predict Using Climate Signals and Artificial Neural Network in Dez Basin. Geographical Research Journal. 2015 30(2):261-274. [In Persian]
16. Jahangir M, Khoshmashraban M, Yousefi H. Drought monitoring and forecasting network using standard precipitation index and multilayer perceptron Neural Network (Case Study: Tehran and Alborz provinces). Iranian Journal of Ecohydrology. 2016; 417-428. [In Persian]
17. Haghizadeh A, Mohammadlou M, Noori F. Simulation of rainfall-runoff process using multilayer perceptron and adaptive neuro-fuzzy interface system and multiple regressions (Case study: Khorramabd watershed). Iranian Journal of Ecohydrology. 2015; 233-243. [In Persian]
18. Hajiabadi R, Farzin S, Hassanzadeh Y. Intelligent Models Performance Improvement Based on Wavelet Algorithm and Logarithmic Transformations in Suspended Sediment Estimation. Journal of Water and Soil. 2016;30(1):112-124. [In Persian]
19. Lotfollahi-Yaghin MA, Koohdaragh M. Examining the function of wavelet packet transform (WPT) and continues wavelet transform (CWT) in recognizing the crack specification. KSCE Journal of Civil Engineering. 2011; 497-506. [In Persian]
20. Sifuzzaman M, Islam MR, Ali MZ. Application of wavelet transform and its advantages compared to Fourier transform.2009; 121-134.
21. Kim TW, Valdés JB. Nonlinear model for drought forecasting based on a conjunction of wavelet transforms and neural networks. Journal of Hydrologic Engineering. 2003 Nov; 8(6):319-28.
22. Kişi Ö. Neural networks and wavelet conjunction model for intermittent streamflow forecasting. Journal of Hydrologic Engineering. 2009 19; 14(8):773-82.
23. Shafaei M, Kisi O. Predicting river daily flow using wavelet-artificial neural networks based on regression analyses in comparison with artificial neural networks and support vector machine models. Neural Computing and Applications. 2016: 1-4.
24. Hassanzadeh Y, Abdi Kordani A, Fakheri Fard A. Drought Forecasting Using Genetic Algorithm and Conjoined Model of Neural Network-Wavelet. Journal of Water and Wastewater. 2012; 23(3): 48-59. [In Persian]
25.shafaei M, Fakhei Fard A, Darbandi S, ghorbani M. Predicrion Daily Flow of Vanyar Station Using ANN and Wavelet Hybrid Procedure. Journal of Irrigation and Water.2014; 113-128. [In Persian]
26. Roshangar K, Zarghaami M, Tarlaniazar M. Forecasting Daily Urban Water Consumption using Conjunctive Evolutionary Algorithm and Wavelet Transform Analysis, A Case Study of Hamedan City, Iran. Journal of Water and Wastewater. 2015; 26(4): 110-120. [In Persian]
27. Zhang G, Patuwo BE, Hu MY. Forecasting with artificial neural networks: The state of the art. International journal of forecasting. 1998; 14(1):35-62.
28. French MN, Krajewski WF, Cuykendall RR. Rainfall forecasting in space and time using a neural network. Journal of hydrology. 1992 Aug 15;137(1-4):1-31.
29. Silverman D, Dracup JA. Artificial neural networks and long-range precipitation prediction in California. Journal of applied meteorology. 2000 Jan;39(1):57-66.
30. Choubin B, Khalighi-Sigaroodi S, Malekian A, Kişi Ö. Multiple linear regression, multi-layer perceptron network and adaptive neuro-fuzzy inference system for forecasting precipitation based on large-scale climate signals. Hydrological Sciences Journal. 2016 Apr 25; 61(6):1001-9.
31. De Vos NJ. Rainfall-run off modelling using artificial neural networks. Doctoral dissertation, TU Delft, Delft University of Technology. 2003.
32. Safshekan F, Pirmoradian N, Afshin Sharifan R. Simulation of rainfall-runoff according to the pattern of rainfall and the use of artificial neural network. Iran-Watershed Management Science & Engineering. 2011. [In Persian]
33. Shahhossein Dastjerdi S, Shahnoushi N, Darijani A, Davari K. Application of artificial neural network models in simulation of drought severity (A Case of Torshakli Station in Golestan Province). Third National Conference on Integrated Water Resource Management.2012. [In Persian]
34. Gopalakrishnan K. Effect of training algorithms on neural networks aided pavement diagnosis. International Journal of Engineering, Science and Technology. 2010;2(2):83-92.
35. Legates DR, McCabe GJ. Evaluating the use of “goodness‐of‐fit” measures in hydrologic and hydroclimatic model validation. Water resources research. 1999;35(1):233-41.
36. Erfanian M, Bayazi M, Abghari H, Esmali Ouri A. Monthly simulation of streamflow and sediment using the SWAT in Nazlochai and prioritization of critical regions. Journal of Watershed Engineering and Management. 2016;552-562. [In Persian]
37. Ahmadi L. Water allocation in Nazloo plain, Urima, using Weap and Vensim. Thesis for the degree of Master of Science in civil engineering. Semnan University. 2016. [In Persian]
38. Noori R, Farokhnia A, Morid S. Riahi Madvar H. Effect of input variables preprocessing in artificial neural network on monthly flow prediction by PCA and wavelet transformation. Journal of Water and Wastewater. 2009 20(1): 13-22. [In Persian]
39. Rajaee T, Ebrahimi H. Application of wavelet-neural network model for forecasting groundwater level time series with non-stationary and nonlinear characteristics. J. of Water and Soil Conservation. 2016;22(5): 99-115. [In Persian]
40. Nikmanesh MR. Prediction of monthly average discharge using the hybrid model of artificial neural network and wavelet transforms (Case study: KorRiver-Pol-e-Khan Station). J. of Water and Soil Conservation. 2015;22(3): 231-239. [In Persian]
41. Rajaee T, Jafari H. Prediction of water sodium absorption ratio (SAR) using ANN and wavelet conjunction model (case study: Rudbar Station of Sefidrud River). 2016;26(2-2):189-205. [In Persian]