تعهد نامه

نوع مقاله : مقالات پژوهشی

نویسندگان

1 دانشجوی کارشناسی ارشد مدریت منابع آب، گروه مهندسی عمران ، واحد اهواز، دانشگاه آزاد اسلامی، اهواز، ایران.

2 استادیار، گروه علوم و مهندسی آب، واحد اهواز، دانشگاه آزاد اسلامی، اهواز، ایران.

چکیده

زمینه و هدف: به‌دلیل پیچیدگی­های موجود در سیستم­های آب زیرزمینی و همچنین محدودیت­های موجود، مدل­سازی آب­های زیرزمینی به آسانی میسر نمی­باشد، اما مدل شبکه عصبی مصنوعی، دارای توانایی بالایی در مدل­سازی سیستم­های پیچیده و غیرخطی هستند و از طرفی روش­های زمین آماری هم در مدل­سازی آب زیرزمینی دارای دقت مناسبی می­باشند.
مواد و روش‌ها: هدف از پژوهش حاضر، شبیه‌سازی پارامترهای کیفی آب زیرزمینی (SAR، TDS و EC) دشت دزفول اندیمشک با استفاده از مدل‌های ANN-PSO و زمین آمار می‌باشد. بدین‌منظور از اطلاعات 61 حلقه چاه مشاهده­ای موجود در دشت دزفول- اندیمشک استفاده شد. ورودی‌های مدل شبکه عصبی شامل پارامترهای کیفی SO42-، pH، HCO32-، Na+، Mg2+، Ca2+، TDS، SAR و EC در نظر گرفته شد.
یافته­ ها: بر اساس نتایج حاصل از شبیه­سازی با مدل شبکه عصبی مصنوعی، بالاترین دقت مدل ANN-PSO در شبیه­سازی به­ترتیب مربوط به پارامترهای EC، SAR و TDS و بر اساس نتایج حاصل از درون­یابی با روش زمین‌آمار، بالاترین دقت مدل کریجینگ در شبیه­سازی به­ترتیب مربوط به پارامترهای EC، TDS و SAR بود. نتایج کلی حاصل از شبیه­سازی پارامترهای کیفی آب زیرزمینی نشان داد که مدل ANN-PSO دقت بیشتری در شبیه­سازی پارامترهای کیفی آب زیرزمینی دشت درفول اندیمشک نسبت به مدل کریجینگ دارد؛ به­طوری­که مقدار R2 برای شبیه­سازی پارامترهای SAR، TDS و EC با استفاده از مدل ANN-PSO در مرحله آزمون به‌ترتیب 92/0، 918/0 و 955/0 و با استفاده از مدل کریجینگ 902/0، 915/0 و 931/0 برآورد شد.
نتیجه‌گیری: نتایج این پژوهش نشان داد، تلفیق مدل­های شبکه عصبی مصنوعی با الگوریتم­های بهینه­سازی، به‌عنوان ابزاری مفید برای شبیه­سازی پارامترهای کیفی آب زیرزمینی کاربرد دارند.

کلیدواژه‌ها

عنوان مقاله [English]

Comparison of Artificial Neural Network and Kriging models in predicting groundwater quality parameters (SAR, TDS and EC) of Dezful Andimeshk plain

نویسندگان [English]

  • Fariborz Bahrami 1
  • Aslan Egdernezhad 2

1 M.Sc. Student, Department of Civil Engineering, Ahvaz Branch, Islamic Azad University, Ahvaz, Iran.

2 Assistant Professor, Department of Water Sciences and Engineering, Ahvaz Branch, Islamic Azad University, Ahvaz, Iran.

چکیده [English]

Background and Purpose: Due to the complexities in the nature of ground water systems, it sounds like a demanding job to model either the time or the location of ground water. However, artificial neural networks have a high capability to model both complicated and non-linear models. Besides, Geostatistic Methods are, to a good extent, accurate in modelling ground water.
Material and Methods: The aim of this study is to simulate groundwater quality parameters (SAR, TDS and EC) of Dezful Andimeshk plain using ANN-PSO and geostatistical models. For this purpose, information from 61 observation wells in Dezful-Andimeshk plain has been used. Neural network model inputs including qualitative parameters SO42- ، pH ، HCO32-، Na+، Mg2+، Ca2+، TDS، SAR and EC were considered.
Results: The results of simulation with intelligent model showed that the highest accuracy of ANN-PSO model in simulation is related to EC, SAR and TDS parameters, respectively. The results of interpolation by geostatistical method showed that the highest accuracy of Kriging model in simulation is related to EC, TDS and SAR parameters, respectively. The general results obtained from the simulation of groundwater quality parameters showed that the ANN-PSO model is more accurate in simulating the groundwater quality parameters of the plain in Andimeshk than the Kriging model. So that the value of R2 for simulating SAR, TDS and EC parameters using ANN-PSO model in the test phase is 0.92, 0.918 and 0.955 respectively and using kriging model is 0.902. 0.915 and 0.931 were estimated.
Conclusion: The results of this study also showed that the combination of intelligent models with optimization algorithms is used as a useful tool to simulate groundwater quality parameters.

کلیدواژه‌ها [English]

  • Groundwater
  • Quality Parameters
  • Geostatistics
  • Modeling
1.Sarani N. Soltani J, Sarani S A, Moasheri SA. Comparison of Artificial Neural Network and Multivariate Linear Regression Model to Predict Sodium adsorption ratio (SAR), the Case of Sistan River, Iran. International Journal of Biological, Ecological and Environmental Sciences (IJBEESB2012). 2012 [In Persian].
2.Samin M, Soltani J, Zeraatcar Z, Moasheri SA, Sarani N. Spatial Estimation of Groundwater QualityParameters Based on Water Salinity Data using Kriging and Cokriging Methods. International Conference on Transport, Environment and Civil Engineering (ICTECE'), Kuala lumpur. 2012; August 25-26, Malaysia, pp. 75-79.
3.Moasheri SA, Mohamad RO, Beyranvand Z, Poornoori Z. Estimating the spatial quality parameters of Kashan plain with integration method of Geostatistics - Artificial Neural Network Optimized by Genetic-Algorithm. International Journal of Agriculture and Crop Sciences. 2013; 5 (20): 2434-2442.
4.Govindaraju RS,  Rao AR E. Artificial neural networks in hydrology. Journal of Springer Science and Business Media. 2013; 36: 1-60.
5.Menhaj MB. Basics of artificial neural networks. Amirkabir University of Technology Publications, Tehran, 2001 [In Persian].
6.Vali Samani J, Yari RA. Examining temporal and spatial changes of groundwater salinity using kriging method. The 7th Iranian Hydraulic Conference. Tehran University of Water and Power Industry, Tehran. 2008. [In Persian].
7.Rahmani Gh R. Simulation of Aghili Plain Groundwater Resources Using Artificial Neural Networks and Its Comparison with the Results of the Finite Difference Mathematical Model. [Msc Thesis]. University of shahid chamran, Ahvaz, Iran. 2011; 150 pp [In Persian].
8.Isa Zadeh M, Arab Zadeh R, Darbandi S. Evaluating the performance of geostatistics and artificial neural network methods in estimating the qualitative parameters of the aquifer (case study: Garveh Plain - Dehgolan). Journal of water and soil sciences (agricultural sciences and techniques and natural resources). 2016; 20 (78): 197-201.
9.Sebghati M, Gholami V. Groundwater salinity simulation by combining the capabilities of artificial neural network and GIS on the southern shores of the Caspian Sea. Journal of Irrigation Science and Engineering. 2019; 42(4): 181-194 [In Persian].
10.Dos Santos V.F, Calda G.V, Borges C.R, Franklin Lapa M.C. Use of geographic information system (GIS) in the characterization of the Cunha Canal, Rio de Janeiro, Brazil: effects of the urbanization on water quality. Environmental Earth Sciences. 2015; 73 (3): 1345-1356.
11.Anonymous. Semi-detailed hydrogeological studies of Dezful Andimeshk plain. Ahwaz Water Engineering Company, 2011 [In Persian].
12.Hasani Pak A. Geostatistics (University of Tehran). 1998; 330 pp [In Persian].
13.Musavi-Jahromi SH, Golabi M. Application of artificial neural networks in the river water quality modeling: Karoon river, Journal of Applied Sciences. 2008; 8 (12):2324-2328.
14.Banejad H, Kamali M, Amirmoradi K, Olyaie F. 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). Journal Health & Environ. 2013; 6(3): 277-294.
15.Ahaninjan K, Egdernezhad A. Modeling Qualitative Parameters of SAR, EC, and TDS in Groundwater using Optimized Artificial Neural Network Model (Case Study: Behbahan Plain). Journal of Environment and Water Engineering. 2020; 6(2), 161-172 [In Persian].
16.Jamshidi Avanaki M, Ebrahimi K. Comparison of artificial neural networks and geostatistical approach in predicting groundwater level (Case study: Mashhad plain aquifer). Second Conference on Environmental Management and Planning, University of Tehran, Tehran, 2013 [In Persian].
17.Rajaee T, Pouraslan F. Temporal and spatial forecast of Davarzan plain groundwater level. Hydrogeomorphology. 2015; 1 (4): 1-19 [In Persian].
18.Habibi M, Nadiri A, Asghari Moghadam A, Naderi K. Combination of artificial intelligence and geostatistical methods for temporal and spatial prediction of groundwater level in Hadishahr plain. Iranian Journal of Watershed Management Science and Engineering. 2016; 23 (10): 27-32 [In Persian].
19.Isazadeh M, Arabzadeh R, Darbandi S. Evaluation of the performance of geostatistical methods and artificial neural network in estimating the aquatic qualitative parameters (Case study: Qorveh-Dehgolan plain). Journal of Soil and Water Sciences (Agricultural Science and Technology and Natural Resources). 2016; 20 (78): 197-201 [In Persian].
20.Nourani V, Goli Ejlali R, Alami MT. Spatiotemporal Groundwater Level Forecasting in Coastal Aquifers by Hybrid Artificial Neural Network-Geostatistics Model: A Case Study. Environmental Engineering Science. 2011; 28(3): 217-228.
21.Ebadi Y, Javdan J. Rezaee Moghaddam MH. Assessing the accuracy of artificial neural networks and geostatistics in intervening groundwater level level Case study: Shabestar-Sufian plain. Geographical Information Quarterly. 2018; 28 (110): 133-145 [In Persian].
22.Ghaffari Razin MR, Voosoghi B, Mohammadzadeh A. Efficiency of artificial neural networks in map of total electron content over Iran. Acta Geodaetica et Geophysica. 2015; 1-15.
23.Behzad A, Hamzeh F. Investigation of the effect of geological formations on water quality, West Dehdasht aquifer. Geography Research Quarterly. 2011; 3 (11): 93-112 [In Persian].