تخمین هدایت هیدرولیکی و ارزیابی عدم قطعیت بین مدل‌ها و داده‌های ورودی توسط متوسط‌گیری بیزین از مدل‌های هوش مصنوعی

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشکده عمران-دانشگاه تبریز

2 گروه آب دانشکده عمران، دانشگاه تبریز

3 گروه عمران دانشگاه سراسری مراغه

4 دانشیار، دانشکده علوم زمین، دانشگاه تبریز، تبریز، ایران

چکیده

تخمین هدایت هیدرولیکی از مهمترین بخش های مطالعات هیدروژئولوژی بوده که در مدیریت آب های زیرزمینی حائز اهمیت است. اما به علت محدودیت‌های عملی، زمانی و یا هزینه ای، اندازه گیری مستقیم آن با دشواری همراه است. لذا استفاده از مدل‌های هوش مصنوعی با صرف هزینه کم و کارایی بالا می‌توانند جایگزین مناسبی برای این منظور باشند. از آنجا که داده های ورودی )شامل مقاومت عرضی، ضخامت آبخوان، هدایت الکتریکی و فاصله اقلیدسی( و تکنیک های آموزشی متفاوت در این نوع مدل‌ها به عنوان مهمترین عوامل ایجادعدم قطعیت هستند، لذا تاثیر منابع مختلف عدم قطعیت در خروجی باید درنظرگرفته شود. در این تحقیق روش میانگین‌گیری مدل بیزین (BMA )توسعه داده شده که شامل ترکیب مدل های شبکه عصبی مصنوعی، منطق فازی و نروفازی در تخمین هدایت هیدرولیکی و ارزیابی عدم قطعیت است. در مدل BMA ،وزن مدل ها توسط معیار اطلاعات بیزین (BIC ) تعیین شده و واریانس درون مدل ناشی از عدم قطعیت داده ورودی و واریانس بین مدل ها ناشی از عدم قطعیت مربوط به ذات مدل های هوش مصنوعی محاسبه می شود. در این مطالعه روش توسعه داده شده برای تخمین هدایت هیدرولیکی در آبخوان دشت ارومیه اعمال شده است. نتایج نشان می دهد اگرچه مقدار ضریب تعیین BMA نسبت به ضریب تعیین بهترین مدل، بالاتر نبوده ولی خروجی BMA حاصل اختصاص وزنهایی است که عدم قطعیت بین مدل ها و داده های ورودی را در نظر می گیرد. همچنین تاثیر تغییرات سطح آب زیرزمینی از زمان آزمون پمپاژ تا سال 1394بر مقادیر هدایت هیدرولیکی بررسی شده و نتایج تفاوت بسیار کمی در تغییرات هدایت هیدرولیکی نشان می دهد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Hydraulic conductivity and uncertainty analysis of between-models and input data by using Bayesian model averaging of artificial intelligence model

نویسندگان [English]

  • yousef hassanzadeh 1
  • Marjan Moazamnia 2
  • Sina Sadeghfam 3
  • Ata Allah Nadiri 4
2 Faculty of Civil Engineering/ University of Tabriz
3 Assistant Professor, Faculty of Engineering/ University of Maragheh
4 Associate Professor, Faculty of Earth Sciences/ University of Tabriz
چکیده [English]

The estimation of hydraulic conductivity is one of the most important part of hydrogeological studies which is important in groundwater management. But due to practical, time or cost constraints, direct measurement is difficult. Hence, the using artificial intelligence models with low cost and high performance can be an appropriate alternative for this purpose. Since input data and different training techniques in these models are the most important source of uncertainty, the effect of various sources of uncertainty in output should be considered. In this research a Bayesian Model Averaging (BMA) are developed which includes the model combination of artificial neural network, fuzzy logic and neuro-fuzzy to estimate hydraulic conductivity and uncertainty analysis. In the BMA model, the weight of the models is determined by the Bayesian information criterion (BIC), and the within-model variance, steam from the uncertainty of input data and the between-model variance steam from uncertainty associated with the nature of the artificial intelligence model are calculated. In this study, the developed method has been applied to estimate the hydraulic conductivity in the Urmia aquifer. The results show that although the determination coefficient of BMA is not higher than the determination coefficient of the best model, the output of the BMA is the result of assigning weights that take into account the uncertainty between the models and the input data. Also, the effect of groundwater level variation on estimated hydraulic conductivity from pumpage test up to 2015 was evaluated and the result indicated an insignificant changes in hydraulic conductivity.

کلیدواژه‌ها [English]

  • Bayesian Model Averaging
  • Hydraulic Conductivity
  • Artificial Neural Network
  • Fuzzy Logic
  • neuro-fuzzy
[1]  C.V. Theis, The relation between the lowering of the piezometric surface and the rate and duration of discharge of a well using ground‐water storage, Eos, Transactions American Geophysical Union, 16(2) (1935) 519-524.
[2]  V.T. Chow, On the determination of transmissibility and storage coefficients from pumping test data, Eos, Transactions American Geophysical Union, 33(3) (1952) 397-404.
[3]  H. Cooper Jr, C.E. Jacob, A generalized graphical method for evaluating formation constants and summarizing well‐field history, Eos, Transactions American Geophysical Union, 27(4) (1946) 526-534.
[4]  J. Ross, M. Ozbek, G.F. Pinder, Hydraulic conductivity estimation via fuzzy analysis of grain size data, Mathematical geology, 39(8) (2007) 765-780.
[5]  J. Sun, Z. Zhao, Y. Zhang, Determination of three dimensional hydraulic conductivities using a combined analytical/neural network model, Tunnelling and Underground Space Technology, 26(2) (2011) 310-319.
[6]  Y. Yao, C. Zheng, J. Liu, G. Cao, H. Xiao, H. Li, W. Li, Conceptual and numerical models for groundwater flow in an arid inland river basin, Hydrological Processes, 29(6) (2015) 1480-1492.
[7]  H. Norouzi, A.A. Nadiri, A. Asghari Moghaddam, M. Norouzi, Comparing Performans of Fuzzy Logic, Artificial Neural Network and Random Forest Models in Transmissivity Estimation of Malekan Plain Aquifer, Iranian journal of Ecohydrology, 5(3) (2018) 739-751.
[8]  A.A. Nadiri, S. Yousefzadeh, A Comparison of the Performance of Artificial Neural Network, Fuzzy Logic and Adaptive Neuro-Fuzzy Inference Systems Models in the Estimation of Aquifer Hydraulic Conductivity. A Case Study: Maraghe-Bonab Aquifer, Hydrogeomorphology, 3(10) (2017) 21-40.
[9]  J. Behmanesh, E. Rezaie, EVALUATION OF REGRESSION AND NEURO_FUZZY MODELS IN ESTIMATING SATURATED HYDRAULIC CONDUCTIVITY,  (2015).
[10] H. Motaghian, J. Mohammadi, Spatial estimation of saturated hydraulic conductivity from terrain attributes using regression, kriging, and artificial neural networks, Pedosphere, 21(2) (2011) 170-177.
[11] G. Tayfur, A.A. Nadiri, A.A. Moghaddam, Supervised intelligent committee machine method for hydraulic conductivity estimation, Water resources management, 28(4) (2014) 1173-1184.
[12] S. Tamari, J. Wösten, J. Ruiz‐Suárez, Testing an artificial neural network for predicting soil hydraulic conductivity, Soil Science Society of America Journal, 60(6) (1996) 1732-1741.
[13]  H. Merdun, Ö. Çınar, R. Meral, M. Apan, Comparison of artificial neural network and regression pedotransfer functions for prediction of soil water retention and saturated hydraulic conductivity, Soil and Tillage Research, 90(1-2) (2006) 108-116.
[14] J.-S. Lim, Reservoir properties determination using fuzzy logic and neural networks from well data in offshore Korea, Journal of Petroleum Science and Engineering, 49(3-4) (2005) 182-192.
[15]  S. Karimpouli, N. Fathianpour, J. Roohi, A new approach to improve neural networks' algorithm in permeability prediction of petroleum reservoirs using supervised committee machine neural network (SCMNN), Journal of Petroleum Science and Engineering, 73(3-4) (2010) 227-232.
[16]  A. Kadkhodaie‐Ilkhchi, A. Amini, A fuzzy logic approach to estimating hydraulic flow units from well log data: A case study from the Ahwaz oilfield, South Iran, Journal of Petroleum Geology, 32(1) (2009) 67-78.
[17]  C.-H. Chen, Z.-S. Lin, A committee machine with empirical formulas for permeability prediction, Computers & Geosciences, 32(4) (2006) 485-496.
[18]  R. Tibshirani, A comparison of some error estimates for neural network models, Neural Computation, 8(1) (1996) 152-163.
[19] R. Dybowski, Assigning confidence intervals to neural network predictions, in:  Neural Computing Applications Forum (NCAF) Conference, 1997.
[20]  R. Marcé, M. Comerma, J.C. García, J. Armengol, A neuro‐fuzzy modeling tool to estimate fluvial nutrient loads in watersheds under time‐varying human impact, Limnology and Oceanography: Methods, 2(11) (2004) 342-355.
[21] F.T.C. Tsai, X. Li, Inverse groundwater modeling for hydraulic conductivity estimation using Bayesian model averaging and variance window, Water Resources Research, 44(9) (2008).
[22] A.A. Nadiri, N. Chitsazan, F.T.-C. Tsai, A.A. Moghaddam, Bayesian artificial intelligence model averaging for hydraulic conductivity estimation, Journal of Hydrologic Engineering, 19(3) (2014) 520-532.
[23] J.A. Hoeting, D. Madigan, A.E. Raftery, C.T. Volinsky, Bayesian model averaging: a tutorial, Statistical science, (1999) 382-401.
[24] Raftery, A. E., Madigan, D., & Hoeting, J. A. (1997). Bayesian model averaging for linear regression models. Journal of the American Statistical Association, 92(437), 179-191.
[25]  R. Kass, A. Raftery, Bayes Factors, in Journal of the American Statistical Association,  (1995).
[26] D. Draper, Assessment and propagation of model uncertainty, Journal of the Royal Statistical Society: Series B (Methodological), 57(1) (1995) 45-70.
[27] K. Hornik, M. Stinchcombe, H. White, Multilayer feedforward networks are universal approximators, Neural networks, 2(5) (1989) 359-366.
[28] S. Haykin, Neural networks: a comprehensive foundation, Prentice-Hall, Inc., 2007.
[29] R. Khatibi, M.A. Ghorbani, F.A. Pourhosseini, Stream flow predictions using nature-inspired firefly algorithms and a multiple model strategy–directions of innovation towards next generation practices, Advanced Engineering Informatics, 34 (2017) 80-89.
[30] T. Takagi, M. Sugeno, Fuzzy identification of systems and its applications to modeling and control, IEEE transactions on systems, man, and cybernetics, (1) (1985) 116-132.
[31] L.A. Zadeh, Fuzzy sets, in:  Fuzzy sets, fuzzy logic, and fuzzy systems: selected papers by Lotfi A Zadeh, World Scientific, 1996, pp. 394-432
[32] J.C. Bezdek, Objective function clustering, in:  Pattern recognition with fuzzy objective function algorithms, Springer, 1981, pp. 43-93.
[33] S.L. Chiu, Fuzzy model identification based on cluster estimation, Journal of Intelligent & fuzzy systems, 2(3) (1994) 267-278
[34] M.-S. Chen, S.-W. Wang, Fuzzy clustering analysis for optimizing fuzzy membership functions, Fuzzy sets and systems, 103(2) (1999) 239-254.
[35] A.A. Nadiri, E. Fijani, F.T.-C. Tsai, A. Asghari Moghaddam, Supervised committee machine with artificial intelligence for prediction of fluoride concentration, Journal of Hydroinformatics, 15(4) (2013) 1474-1490.
[36] S. Heddam, A. Bermad, N. Dechemi, ANFIS-based modelling for coagulant dosage in drinking water treatment plant: a case study, Environmental monitoring and assessment, 184(4) (2012) 1953-1971.
[37] A.S. Kechris, Analytic Well-founded Relations, in: Classical Descriptive Set Theory, Springer, 1995, pp. 239-241.
[38] E.E. Leamer, E.E. Leamer, Specification searches: Ad hoc inference with nonexperimental data, Wiley New York, 1978.
[39] J.O. Berger, Prior information and subjective probability, in:  Statistical Decision Theory and Bayesian Analysis, Springer, 1985, pp. 74-117.
[40] M. Ye, S.P. Neuman, P.D. Meyer, Maximum likelihood Bayesian averaging of spatial variability models in unsaturated fractured tuff, Water Resources Research, 40(5) (2004).
[41] X. Li, F.T.C. Tsai, Bayesian model averaging for groundwater head prediction and uncertainty analysis using multimodel and multimethod, Water resources research, 45(9) (2009).
[42] F.T.C. Tsai, X. Li, Multiple parameterization for hydraulic conductivity identification, Groundwater,46(6)(2008)851-564.
[43]  R. Maillet, The fundamental equations of electrical prospecting, Geophysics, 12(4) (1947) 529-556.
[44]  N. Harb, K. Haddad, S. Farkh, Calculation of transverse resistance to correct aquifer resistivity of groundwater saturated zones: implications for estimating its hydrogeological properties, Lebanese science journal,11(1)(2010) 105-115.
[45] D.T. Purvance, R. Andricevic, On the electrical‐hydraulic conductivity correlation in aquifers, Water Resources Research, 36(10) (2000) 2905-2913.
[46] R. Valcarce, W. Rodríguez, Resolution power of well log geophysics in karst aquifers, Journal of Environmental Hydrology, 12 (2004) 1-7.
[47] R.A. Olea, Normalization, in:  Geostatistics for Engineers and Earth Scientists, Springer, 1999, pp. 31-38.