تخمین پارامترهای هیدرودینامیکی آبخوان محبوس با استفاده از مدل فازی سوگنو

نوع مقاله : پژوهشی

نویسندگان

1 دانشجوی کارشناسی ارشد، دانشکدۀ علوم طبیعی، دانشگاه تبریز

2 دانشیار گروه علوم زمین، دانشکدۀ علوم طبیعی، دانشگاه تبریز

3 دکتری هیدروژئولوژی، بخش علوم زمین شیراز، دانشگاه شیراز

4 استادیار گروه مهندسی عمران، دانشکده فنی مهندسی، دانشگاه مراغه

5 دانشجوی کارشناسی، دانشکدۀ فنی مهندسی، دانشگاه آزاد اسلامی تبریز

چکیده

شناخت دقیق پارامترهای هیدروژئولوژیکی مانند قابلیت انتقال، هدایت هیدرولیکی و ضریب ذخیره یا آبدهی ویژه از جمله پارامترهای مهم برای پیش‏بینی شرایط آبخوان هستند که عموماً تعیین آنها برای نقاط مختلف آبخوان با هزینه‏های فراوانی انجام می‏‌شود. در سال‏های اخیر، از مدل‏های هوش مصنوعی به عنوان جایگزین روش‏های انطباق منحنی تیپ برای تعیین پارامترهای هیدرودینامیکی آبخوان‏ها استفاده شده است. بنابراین، در مطالعۀ حاضر نیز برای تعیین پارامترهای هیدرو‏دینامیکی آبخوان محبوس از منطق فازی سوگنو استفاده شد. ابتدا دقت، قابلیت اطمینان و توانایی تعمیم این مدل فازی از طریق آزمایش آن با داده‏های افت- زمان واقعی تأیید شد. سپس، نتایج به‌دست‌آمده از این مدل با نتایج به‌دست‌آمده از روش‏ گرافیکی تایس و شبکۀ عصبی مصنوعی مقایسه شد. مقایسۀ RRMSE مدل شبکۀ عصبی مصنوعی و مدل فازی به منظور تخمین قابلیت انتقال آبخوان و ضریب ذخیره در مرحلۀ آزمایش نشان داد مدل فازی، خطا را به‌ترتیب 21/9 و 66/11 درصد نسبت به شبکۀ عصبی کاهش می‏دهد. بنابراین، نتایج به‌دست‌آمده از روش گرافیکی تایس، شبکۀ عصبی مصنوعی و مدل منطق فازی در مرحلۀ صحت‏سنجی نشان می‌دهند مدل فازی سوگنو در کنار دو روش یادشده توانایی تعیین پارامترهای آبخوان تحت فشار را دارد. این کارایی نسبی بیشتر منطق فازی سوگنو را می‌توان در توانایی ذاتی آن در کار با داده‏ها و پارامترهای دارای عدم قطعیت نسبت به روش گرافیکی تایس و شبکۀ عصبی مصنوعی دانست.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Determination the Hydrodynamic Parameters of Confined Aquifer Using Sugeno Fuzzy Logic

نویسندگان [English]

  • Hamed Mahmoudi Hajilari 1
  • Ata Allah Nadiri 2
  • Tahereh Azari 3
  • Sina Sadeghfam 4
  • Hadi Mahmoudi Hajilari 5
1 MSc. Student, Department of Earth Sciences, University of Tabriz, Tabriz, Iran
2 Associated Professor, Department of Earth Sciences, University of Tabriz, Tabriz
3 Ph.D in Hydrogeology, Department of Earth Sciences, University of Shiraz, Tabriz
4 Assistant Professor, Department of Civil Engineering and Environment, University of Maragheh
5 BSc., Faculty of Engineering, Islamic Azad University of Tabriz, Tabriz
چکیده [English]

The accurate recognition of hydrogeological parameters such as transmissivity, hydraulic conductivity and storage coefficient or specific yield are the most important parameters for predicting the aquifer conditions that are determined at different points of aquifer with great cost. In recent years, artificial intelligence models have been used as alternatives method to adaptive graphical methods to determine the hydrodynamic parameters of aquifers. Therefore, in this study the Sugeno fuzzy logic was used to determine the hydrodynamic parameters of the confined aquifer. First, the accuracy, reliability and generalization ability of the fuzzy model is verified by time-drawdown field data. Then, the results of this model were compared with the results of obtained from the Theis graphical method and artificial neural network. Comparison of the RRMSE of the Sugeno fuzzy model and the artificial neural network for determining the transmissivity and storage coefficient in testing step show that the fuzzy model reduces the error relative to the neural network 9.21% and 11.66%, respectively. Therefore, the results of the Theis graphical method, artificial neural network and fuzzy logic model in the verification step indicates that the Sugeno fuzzy model is able to determine the parameters of confined aquifer. The sugene fuzzy logic model is due to its high ability to contrast with uncertainty data that has more accurate results to the Theis graphical method and artificial neural network.

کلیدواژه‌ها [English]

  • Artificial Neural Network
  • Theis type curve
  • Principal Component Analysis (PCA)
  • Sugeno fuzzy logic
  • Confined aquifer
[1]. Theis C V. The relationship between the lowering of the piezometric surface and the rate and duration of discharge of a well using ground-water storage.Trans Am Geophys Union. 1935; (16): 519–524.
[2]. Chow V T. On the determination of transmissibility and storage coefficnts from pumping test data. Trans. Amer. Geophysical Union. 1952; 33: 397-404.
 [3]. Cooper H H, Jacob C E. A generalized graphical method for evaluating formation constants and summarizing well field history. Trans. Amer. Geophysical union. 1946; 27: 526-534.
[4]. Neuman S P. Analysis of pumping test data from anisotropic unconfined aquifers considering delayed gravity response. water resources research. 1975; 11: 329-342.
 [5]. Hazen A. Some physical properties of sands and gravels. Massachusetts state board of health 24th Annual Report. 1892;539-556.
 [6]. Shepherd R G. Correlations of permeability and grain size. Ground Water.1989; 27: 633-638.
 [7]. Alyamani M, Sen Z. Determination of hydraulic conductivity from complete grain size distribution curves. Ground Water. 1993; 31: 551-555.
[8]. Samani N, Gohari-Moghadam M, Safavi A A. A simple neural network model for the determination of aquifer parameters. J Hydrol. 2007; 340(1–2):1–11.
[9]. Lin G F, Chen G R. An improved neural network approach to the determination of aquifer parameters. J Hydrol. 2006;316(1–4): 281–289.
[10]. Lin H T, Ke K Y, Chen Ch H, Wu Sh Ch, Tan Y Ch. Estimating anisotropic aquifer parameters by artificial neural networks. Hydrol Process. 2010 ;(24): 3237–3250.
[11]. Delnaz A, Rakhshandehroo GH, Nikoo M. Assessment of GRNN model in comparison to ANN and RBF models for estimating confined aquifer parameters. Hydrogeology. Summer 2017, Page 102-117 [ Persian].
[12]. Schaap M G, Leij F J. Using neural networks to predict soil water retention and soil hydraulic conductivity. Soil Tillage Res. 1998;47:37– 42.
[13]. Merdun H, Inar O C, Meral R, Apan M. Comparison of artificial neural network and regression pedotransfer functions for prediction of soil water retention and saturated hydraulic conductivity. Soil Tillage Res. 2006; 90:108–116.
[14]. Nayak P C, Rao Y R S, Sudheer K P. Groundwater level forecasting in a shallow aquifer using artificial neural network approach. Water Resour Manag. 2006;20(1):77–90.
[15]. Tayfur G, Moramarco T, Singh V P. Predicting and forecasting flow discharge at sites receiving significant Lateral inflow. Hydrol Process. 2007; 21(14):1848–1859.
[16]. Mohanty S, Jha M K, Kumar A, Sudheer K P. Artificial neural network modeling for groundwater level forecasting in a River Island of Eastern India. Water Resour Manag. 2010;24(9):1845–1865.
[17]. Motaghian H R, Mohammadi J. Spatial estimation of saturated hydraulic conductivity from terrain attributes using regression. kriging and artificial neural networks. Pedosphere. 2011; 21(2):170–177.
[18]. Shirmohammadi B, Vafakhah M, Moosavi V Moghaddamnia, A. Application of several data-drive techniques for predicting groundwater level.Water Resour Manag. 2013; 27(2):419–432.
[19]. Nadiri AA, Gharekhani M, Khatibi R, Sadeghfam S, Asghari Moghaddam A. Groundwater vulnerability indices conditioned by Supervised Intelligence Committee Machine (SICM). Science of The Total Environment. 2017;574: 691-70.
[20]. Tayfur G, Nadiri, AA, Asghari Moghaddam A. Supervised Intelligent Committee Machine Method for Hydraulic Conductivity Estimation. Water Resour Manage. 2014; 28:1173–1184.
[21]. Ross J, Ozbek M, Pinder G F. Hydraulic conductivity estimation via fuzzy. Math Geol. 2007;39(8):765–780.
 
[22]. Olatunji S O, Selamat A, Abdulraheem A. Modeling the permeability of carbonate reservoir using type-2 fuzzy logic systems. Comput Ind. 2011; 62:147–163.
[23]. Colin, F, Guillaume S, Tisseyre B. Small catchment agricultural management using decision variables defined at catchment scale and a fuzzy rule-based system: a Mediterranean vineyard case study. Water Resour Manag.2011;25(11):2649–2668.
[24]. Bárdossy A, Disse M. Fuzzy rule-based models for infiltration. Water Resour Res.1993; 29(2):373–382.
[25]. Tutmez B, Hatipoglu Z. Spatial estimation model of porosity. Comput Geosci. 2007; 33:465–475.
[26]. Chu H J, Chang L C. Application of optimal control and fuzzy theory for dynamic groundwater remediation design. Water Resour Manag. 2009;23(4):647–660.
[27]. Helmy T, Fatai A, Faisal K. Hybrid computational models for the characterization of oil and gas reservoirs. Expert Syst Appl. 2010;37(7):5353–5363.
[28]. Anifowose F, Abdulraheem A. Fuzzy logic-driven and SVM-driven hybrid computational intelligence models applied to oil and gas reservoir characterization. J Nat Gas Sci Eng. 2011; 3(3):505–517.
[29]. Tayfur G.Soft computing in water resources engineering.WIT Press, Southampton. 2012.
[30]. Morankar D V, Raju K S,Kumar D N. Integrated sustainable irrigation planning with multiobjective fuzzy optimization approach. Water Resour Manag. 2013;27(11):3981–4004.
[31]. Nadiri A A, Gharekhani M, Khatibi R,
Sadeghfam S and Asghari Moghaddam A. Groundwater vulnerability indices conditioned by Supervised Intelligence Committee Machine (SICM). Science of The Total Environment. 2017; 574: 691-706.
[32].Lin G F,Chen G R. Determination of aquifer parameters using radial basis function network approach. J Chinese Inst Engrs. 2005; 28(2):241-249.
[33].Azari T, Samani N, and Mansoori E. An artificial neural network model for the determination of leaky confined aquifer parameters. an accurate alternative to type curve matching methods. Iranian Journal of Science & Technology. 2015;39(A4): 463-472.
[34]. Zadeh LA. Fuzzy sets.Information and Control. 1965; 8 (3): 338–353.
[35]. Nadiri AA, Fijani E, Tsai FT-C, Asghari Moghaddam A. Supervised committee machine with artificial intelligence for prediction of fluoride concentration. Journal of Hydroinformatics. 2013;15: 1474–1490
[36]. Maier H R, Jain A, Dandy G C, Sudheer K P. Methods used for the development of neural networks for the prediction of water resource variables in river systems. current status and future directions. Environ Model Softw. 2010; 25(8): 891-909.
[37]. Wu W, Dandy G C, Maier H R. Protocol for developing ANN models and its application to the assessment of the quality of the ANN model development process in drinking water quality modeling.Environ Modell Softw. 2014 ;(54):108–127.
[38]. Todd D K, Mays LW. Groundwater Hydrology. New York: Wiley. 2005.