پیش‌بینی سطح آب زیرزمینی دشت بستان‌آباد با استفاده از ترکیب نظارت شده مدل‌های هوش‌ مصنوعی

نوع مقاله: مقاله پژوهشی

نویسندگان

1 دانشگاه تبریز،دانشکده علوم طبیعی

2 دانشگاه تبریز

چکیده

آبخوان دشت بستان‌آباد واقع در استان آذربایجان‌شرقی تأمین‌کننده اصلی نیازهای آبی منطقه می‌باشد. با توجه به برخی محدودیت‌های مدل‌های عددی مثل وقت‌گیر و پر‌هزینه بودن و نیاز به داده‌های زیاد، در این تحقیق از مدل‌های هوش مصنوعی شامل شبکه‌های عصبی پیشرو (FNN)، شبکه‌های عصبی برگشتی ‌(RNN) و برنامه‌نویسی بیان ژن (GEP) جهت بررسی تغییرات سطح آب زیرزمینی دشت استفاده شده است. دسته‌بندی پیزومترها به دلیل نا‌همگنی آبخوان، قبل از مدل‌سازی صورت پذیرفت. پارامترهای بارش، تبخیر، دبی خروجی رودخانه اوجان‌ و سطح آب‌زیرزمینی در یک زمان قبل به ‌عنوان ورودی مدل‌ها مورد استفاده قرار گرفت. با وجود نتایج قابل‌قبول هر سه مدل بر اساس متوسط RMSE هر دسته در مراحل آموزش و آزمایش، جهت استفاده از کارایی هر سه مدل و دستیابی به نتیجه بهتر، از روش ترکیبی مدل‌های هوش مصنوعی با استفاده از یک شبکه‌عصبی مصنوعی به ‌عنوان ترکیب‌کننده غیرخطی استفاده گردید. نتایج نشانگر کاهش متوسط خطای هر دسته در مدل هوش‌مصنوعی‌مرکب نسبت به مدل‌های منفرد به مقدار میانگین 17% در مقادیر RMSE می‌باشد. با استفاده از نتایج مدل هوش مصنوعی مرکب، تأثیر کاهش 30 و 50 درصدی تخلیه از چاه‌های بهره‌برداری بر روی سطح آب زیرزمینی مورد بررسی قرار گرفت. نتایج نشانگر بالا رفتن قابل‌توجه سطح آب در همه پیزومتر‌ها به جز پیزومتر آغچه کهل می باشد. این موضوع نشان دهنده تأثیر بالای مقادیر پمپاژ نسبت به تغییرات آب و هوایی در تغییرات سطح آب زیرزمینی منطقه مطالعاتی می باشد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Prediction of ground water level of Bostan Abad using combining artificial intelligence models

چکیده [English]

Bostan Abad aquifer located in the East Azerbayjan Province is the main supplier of the region's water needs. Using a numerical model has some limitations such as high complexity, costly, time consuming and a lot of data demanding. For this reason, in the present study the artificial intelligence models including feed forward neural networks (FNN), recurrent neural networks (RNN) and gene expression programming (GEP) were used for prediction of groundwater level changes. Classification of parameters was carried out before modeling, due to their heterogeneity of the aquifer. Precipitation, evaporation, discharge of Ojan River and groundwater level at a time before (t0-1), were used as input parameters in the models. Despite the acceptable results of all three models, based on the average RMSE of each cluster in the training and testing steps, combining the artificial intelligence models using a non-linear neural network as a combiner was adopted to achieve better results than three individual models. The results show decreasing of the average error with a value of 17% in the RMSE for each category in the Supervised Intelligent Committee Machine (SICM) compared to each individual model The SICM was adopted to evaluate the effect of reducing 30 and 50% of the extraction well discharges on groundwater level.The results indicated that the increasing water level in most of piezometers are remarkable. This reflects the high impact of pumping in the amount of groundwater fluctuation is relatively higher than climate change in the study area.

کلیدواژه‌ها [English]

  • Artificial Neural Network
  • Bostan Abad Plain
  • Gene expression programming
  • Supervised intelligent committee machine
  • Water Table

Ahmadi F, Radmanesh F, Mirabbasi Najafabadi R (2014) Comparison of genetic programming and support vector machine methods in prediction of daily stream flow (Case study: Barandoezchay River). Journal of Water and Soil (Agricultural Scinces and Technology) 1(6):1162-1171 (In Persian)

ASCE Task Committee on Aplication of Artificial Neural Networks in Hydrology (2000). Artificial neural network in hydrology, partI and II. Journal of Hydraulic Engineering 5:2 115-137

Ataie-Ashtiani B, Ketabchi H, Rajabi MM (2014) Optimal management of freshwater lens in a small island using surrogate models and evolutionary algorithms. Journal of Hydrologic Engineering ASCE 19(2):339-354

Borelli A, De Falco I, Della C A, Nicodemi M, Trautteur G (2006) Performance of genetic programming to extract the trend in noisy data series. Physica A: Statistical Mechanics and its Applications 370(1):104-108

Chen CH, Lin Z SH (2006) A committee machine with empirical formulas for permeability prediction.Computer and Geoscience. 32(4):485–49

Chiang YM, Chang LCh, Chang FJ (2004) Comparison of static-feedforward and dynamic-feedback neural networks for rainfall–runoff  modeling. Journal of Hydrology 290(3-4):297-311

Coppola E, Szidarovszky F, Poulton M, Charles E (2003) Artificial neural network approach for predicting transient water level in a multilayered groundwater system under variable state, pumping, and climate conditions. Journal of Hydrologic Engineering 8(6):348-360

Coulibaly P, Anclil F, Aravena R, Brnard B (2001) Artificial neural network modeling of water table depth fluctuations. Water Resources Research 37(4):885-896

Daliakopoulos NI, Coulibaly P, Tsanis IK (2005) Groundwater level forecasting using artificial neural networks. Journal of Hydrology 309(1-4):229-240

Ferreira C (2001) Gene expression programming: A new adaptive algorithm for solving problems. Complex System 13(2):87–129

Fijani E, Nadiri A, Moghaddam A A, Tsai F T C, Dixon B (2013) Optimization of DRASTIC method by supervised committee machine artificial intelligence to assess groundwater vulnerability for Maragheh–Bonab plain aquifer, Iran. Journal of Hydrology 503:89-100

Yekom Consulting Engineering Company (2012) groundwater studies of Bostan Abad aquifer. Ministry of Energy- Regional Water Company of East Azarbaijan 1-6 (In Persian)

Haykin S (1999) Neural networks: A comprehensive foundation. 2nd ed, Prentice-Hall, Englewood Cliffs, 842p

Imani M, You RJ, Kuo ChY (2014) Forecasting Caspian sea level changes using satellite altimetry data (June 1992–December 2013) based on evolutionary supportvector regression algorithms and gene expression programming. Journal of Global and Planetary Change 121:53-63

Jahedan N (2008) Hydrogeology study of Bostan Abad plain and presentation management solutions using mathematical models. Master's Thesis, Tabriz University (In Persian)

Karimpouli S, Fathian Pour N, Roohi J (2010) 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 73:227-232

Ketabchi H, Ataie-Ashtiani B (2015) Review: Coastal groundwater optimization- advances, challenges, and practical solutions. Hydrogeology Journal 23:1129-1154

Kumar ARS, Sudheer KP, Jain SK, Agarwal PK, (2005) Rainfall-runoff modeling using artificial neural networks: Comparison of network types. Hydrological Processes 19(6):1277–1291

Liong SY, Gautam TR, Khu ST, Babovic V, Keijzer M, Muttil N (2002) Genetic programming: A new paradigm in rainfall runoff modeling. Journal of the American Water Resources Association 38 (3):705–718

Lippman, R (1987) An introduction to computing with neural nets. IEEE ASSP Mag 4:4-22

Lopes HS, Weinert WR (2004) EGIPSYS: An enhanced gene expression programming approach for symbolic regression problems. International Journal of Applied Mathematics and Computer Science 14(3):375-384

Mehdipour FE, BozorgHaddad O, Marino MA (2013) Prediction and simulation of monthly groundwater levels by genetic programming. Journal of Hydro-environment Research 7(4):253-260

Mitchell M (1996) An introduction to genetic algorithms. MIT Press, 158p

Moghaddam AA, Nourani V, Nadiri A (2009) Prediction of temporal and spatial of groundwater level in Tabriz metro area using neural kriging models. Journal of Iran-Water Resources Research 5(1):14-24(In Persian)

Nadiri A (2015) Application of artificial intelligence methods in geosciences and hydrology. OMICS Group International, 126p

Nadiri A, Gharekhani M, Khatibi R, Sadeghfam S, Asghari Moghaddam A (2017) Groundwater vulnerability indices conditioned by supervised intelligence committee machine (SICM). Journal Science of the Total Environment 574:691-706

Nadiri A, Moghaddam AA, Tsai FTC, Fijani E (2013b) Hydrogeochemical analysis for Tasuj plain aquifer, Iran. Journal of Earth System Science 122(4):1091-1105

Nadiri AA, Fijani E, Tsai FTC, Moghaddam AA (2013a) Supervised committee machine with artificial intelligence for prediction of fluoride concentration. Journal of Hydroinformatics 15(4):1474-1490

Naftaly U, Intrator N, Horn D (1997) Optimal ensemble averaging of neural networks. Comput in Neural Systems 8:283–296

Nayak P, Rao YRS, Sudheer (2006) Ground water level forecasting in a shallow aquifer using artificial neural network approach. Water Resources Management 20:77-90

Nourani V (2009) Using artificial neural networks (ANNs) for sediment load forecasting of Talkherood river mouth. Journal of Urban and Environmental Engineering 3(1):1-6

Nourani V, Mogaddam AA, Nadir i A O (2008) An ANN-based model for spatiotemporal groundwater level forecasting. Journal of Hydrological Processes 22:5054-5066

Sharkey AJC (1996) On combining artificial neural nets. Connection Science 8:299–314

Shiri J, Kisi O, Yoon H, Lee KK (2013) Predicting groundwater level fluctuations with meteorological effect implications—A comparative study among soft computing techniques. Journal of Computers and Geosciences 56:32-44

Sulaiman M, Shafie A, Karim O, Basri H (2011) Improved water level forecasting performance by using optimal steepness coefficients in an artificial neural network. Water Resources Management 25(10):2525–2541

Tayfur G, Nadiri AA, Moghaddam AA (2014) Supervised intelligent committee machine method for hydraulic conductivity estimation. Water Resources Management 28:1173-1184

Yang CC, Prasher SO, Lacroix R, Sreekanth S, Patni NK, Masse L (1997) Artificial neural network model for subsurface drained farmland. Journal of Structural Engineering 123:285-292

Yoon H, Jun SC, Hyun Y, Bae GO, Lee KK (2011) A comparative study of artificial neural networks and support vector machines for predicting groundwater levels in a coastal aquifer. Journal of Hydrology 396:128–138