توسعۀ مدل DRASTIC با استفاده از هوش مصنوعی در پتانسیل آلودگی آبخوان مناطق نیمه ‏خشک

نوع مقاله : پژوهشی

نویسندگان

1 دانش‏آموختۀ کارشناسی ارشد مهندسی عمران آب و سازه‏های هیدرولیکی و عضو باشگاه پژوهشگران جوان و نخبگان، واحد مشهد، دانشگاه آزاد اسلامی، مشهد، ایران

2 دانش ‏آموختۀ کارشناسی ارشد، گروه مهندسی نقشه‏ برداری، دانشکدۀ مهندسی نقشه‏ برداری و اطلاعات مکانی، دانشگاه تهران، تهران، ایران

3 دانش ‏آموختۀ کارشناسی ارشد، گروه مهندسی عمران، دانشگاه صنعتی خواجه نصیرالدین طوسی، تهران، ایران

4 دانشیار گروه مهندسی عمران، دانشگاه بیرجند، بیرجند، ایران

چکیده

به دلیل رشد اقتصادی سریع و بهره‏ برداری بیش از حد از آب ‏های زیرزمینی، مسئلۀ آلودگی نیترات در آب‏ های زیرزمینی بسیار جدی شده ‏است. هدف اصلی این مطالعه، توسعۀ مدل DRASTIC برای شناسایی آسیب ‏پذیری آب‏های زیرزمینی در برابر آلودگی نیترات است. بنابراین، مدل استاندارد DRASTIC با در نظر گرفتن عامل کاربری اراضی (مدل DRASTIC-LU) ‏برای به نمایش گذاشتن آسیب ‏پذیری آب‏های زیرزمینی ارائه شد. نوآوری تحقیق حاضر، توسعۀ مدل‏ های DRASTIC و DRASTIC-LU توسط ماشین بردار پشتیبان (SVM) ‏به منظور جلوگیری از خطای روش‏های همپوشانی و شاخص است. برای پیاده‏ سازی و اعتبارسنجی مدل‏ها، 21 نمونه چاه مشاهداتی در آبخوان دشت بیرجند جمع‏ آوری شدند. مقادیر RMSE مربوط به مدل‏های DRASTIC، DRASTIC-LU، DRASTIC+SVM و DRASTIC-LU+SVM به‌ترتیب 821/0، 743/0، 612/0 و 490/0 ‌شد که نشان داد مدل‏های ترکیبی با استفاده از SVM همبستگی بهتری را بین مقدار آسیب ‏پذیری و آلودگی نیترات نشان می‏ دهد. همچنین، مشخص شد که مدل DRASTIC-LU+SVM برای ارزیابی آسیب ‏پذیری آب‏ های زیرزمینی در برابر نیترات دقت بیشتری دارد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Development of DRASTIC model using artificial intelligence on the potential of aquifer contamination in semi-arid regions

نویسندگان [English]

  • Mobin Eftekhari 1
  • Seyed Ahmad Eslaminezhad 2
  • Ali Haji Elyasi 3
  • Mohammad Akbari 4
1 Master of Science (MSc), Civil Engineering, Water and Hydraulic Structures, Young Researchers and Elite Club, Mashhad Branch, Islamic Azad University, Mashhad, Iran
2 MSc.Faculty of Surveying and Geomatics Engineering, University of Tehran, Tehran, Iran
3 Department of Civil Engineering, K. N. Toosi University of Technology, Tehran,Iran
4 Assist. Prof. at Dept. of Civil Engineering, University of Birjand, Birjand, Iran
چکیده [English]

Due to rapid economic growth and over-exploitation of groundwater, nitrate contamination in groundwater has become very serious. The main purpose of this study is to develop a DRASTIC model to identify the vulnerability of groundwater to nitrate contamination. Therefore, the standard DRASTIC model was presented considering the land use factor (DRASTIC-LU model) to demonstrate the vulnerability of groundwater. The novelty of the present study is the development of DRASTIC and DRASTIC-LU models by support vector machine (SVM) to prevent the error of overlap and index methods. For implementation and validation of the models, 21 samples of observation wells were collected in Birjand plain aquifer. RMSE values for DRASTIC, DRASTIC-LU, DRASTIC+SVM, and DRASTIC-LU+SVM models were calculated to be 0.821, 0.743, 0.612, and 0.490, respectively, which was found that the hybrid models using SVM shows a better correlation between the amount of vulnerability and nitrate contamination. It was also found that the DRASTIC-LU+SVM model has a higher accuracy for assessing the vulnerability of groundwater to nitrate.

کلیدواژه‌ها [English]

  • Vulnerability
  • DRASTIC model
  • Nitrate contamination
  • Support vector machine
[1]. Arabgol R, Sartaj M, Asghari K. Predicting nitrate concentration and its spatial distribution in groundwater resources using support vector machines (SVMs) model. Environmental Modeling & Assessment. 2016; 21(1):71-82.
[2]. Thapa R, Gupta S, Guin S, Kaur H. Sensitivity analysis and mapping the potential groundwater vulnerability zones in Birbhum district, India: a comparative approach between vulnerability models. Water Science. 2018; 32(1):44-66.
[3]. Li X, Ye S, Wang L, Zhang J. Tracing groundwater recharge sources beneath a reservoir on a mountain-front plain using hydrochemistry and stable isotopes. Water Science and Technology: Water Supply. 2017; 17(5):1447-57.
[4]. Machiwal D, Jha MK, Singh VP, Mohan C. Assessment and mapping of groundwater vulnerability to pollution: Current status and challenges. Earth-Science Reviews. 2018; 185:901-27.
[5]. Sarkar M, Pal SC. Application of DRASTIC and Modified DRASTIC Models for Modeling Groundwater Vulnerability of Malda District in West Bengal. Journal of the Indian Society of Remote Sensing. 2021; 4:1-9.
[6]. Khosravi K, Sartaj M, Tsai FT, Singh VP, Kazakis N, Melesse AM, Prakash I, Bui DT, Pham BT. A comparison study of DRASTIC methods with various objective methods for groundwater vulnerability assessment. Science of the total environment. 2018; 642:1032-49.
[7]. Pacheco FA, Pires LM, Santos RM, Fernandes LS. Factor weighting in DRASTIC modeling. Science of the Total Environment. 2015; 505:474-86.
[8]. Sajedi-Hosseini F, Malekian A, Choubin B, Rahmati O, Cipullo S, Coulon F, Pradhan B. A novel machine learning-based approach for the risk assessment of nitrate groundwater contamination. Science of the total environment. 2018; 644:954-62.
[9]. Caprario J, Rech AS, Finotti AR. Vulnerability assessment and potential contamination of unconfined aquifers. Water Supply. 2019; 19(4):1008-16.
[10]. Rajput H, Goyal R, Brighu U. Modification and optimization of DRASTIC model for groundwater vulnerability and contamination risk assessment for Bhiwadi region of Rajasthan, India. Environmental Earth Sciences. 2020; 79(6):1-5.
[11]. Hu X, Ma C, Qi H, Guo X. Groundwater vulnerability assessment using the GALDIT model and the improved DRASTIC model: a case in Weibei Plain, China. Environmental Science and Pollution Research. 2018; 25(32):32524-39.
[12]. Arezoomand omidi langrudi M, Khashei Siuki A, Javadi S, Hashemi SR. Groundwater Vulnerability Assessment by the use of Drastic-New Modified model (Case study: Kuchesfehan-Astane plain). Iranian Journal of Irrigation and Drainage. 2015; 9(1),75-62. [Persian]
[13]. Oroji B, Solgi I. Vulnerability Assessment of Asadabad (Hamadan) Plain Groundwater by GIS. Environmental Sciences, 14(1). 2016; 91-104. [Persian].
[14]. Zafane D, Gharbi F, Douaoui A.A. New Model (DRASTIC-LU) for Evaluating Groundwater Vulnerability in Alluvial Aquifer of Upper Cheliff (Algeria). Recent Advances in Environmental Science from the Euro-Mediterranean and Surrounding Regions. 2018; 1(1),615-617.
[15]. Shakoor A, Khan Z.M, Farid H.U, Sultan M, Ahmad I, Ahmad N, Ali M.U. Delineation of regional groundwater vulnerability using DRASTIC model for agricultural application in Pakistan. Arabian Journal of Geosciences. 2020; 13(4), 1-12.
[16]. Isazadeh M, Biazar SM, Ashrafzadeh A. Support vector machines and feed-forward neural networks for spatial modeling of groundwater qualitative parameters. Environmental Earth Sciences. 2017; 76(17):1-4.
[17]. Tehrany MS, Pradhan B, Jebur MN. Flood susceptibility analysis and its verification using a novel ensemble support vector machine and frequency ratio method. Stochastic environmental research and risk assessment. 2015; 29(4):1149-65.14-
[18]. Chen W, Peng J, Hong H, Shahabi H, Pradhan B, Liu J, Zhu AX, Pei X, Duan Z. Landslide susceptibility modelling using GIS-based machine learning techniques for Chongren County, Jiangxi Province, China. Science of the total environment. 2018; 626:1121-35.
[19]. Deng W, Yao R, Zhao H, Yang X, Li G. A novel intelligent diagnosis method using optimal LS-SVM with improved PSO algorithm. Soft Computing. 2019; 23(7):2445-62.
[20]. Jia Z, Bian J, Wang Y, Wan H, Sun X, Li Q. Assessment and validation of groundwater vulnerability to nitrate in porous aquifers based on a DRASTIC method modified by projection pursuit dynamic clustering model. Journal of contaminant hydrology. 2019; 226:103522.
[21]. Deng W, Xu J, Song Y, Zhao H. An effective improved co-evolution ant colony optimisation algorithm with multi-strategies and its application. International Journal of Bio-Inspired Computation. 2020; 16(3):158-70.
[22]. ghanbari N, Rangzan K, Kabolizade M, Moradi P. Improve the results of the DRASTIC model using artificial intelligence methods to assess groundwater vulnerability in Ramhormoz alluvial aquifer plain. Journal of Water and Soil Conservation. 2017; 24(2), 45-65.
[23]. Nadiri A, Naderi K, Asghari Moghaddam A, Habibi M. Spatiotemporal Predicting of Groundwater Level Using Artificial Intelligence Models and Geostatistics Model (Case study: Duzduzan plain). Geography and Planning. 2017; 20(58), 281-301.
[24]. Salehnia N, Salehnia N, Ansari H, Kolsoumi S, Bannayan M. Climate data clustering effects on arid and semi-arid rainfed wheat yield: a comparison of artificial intelligence and K-means approaches. International journal of biometeorology. 2019; 63(7):861-72.
[25]. Raghavendra N, Deka PC. Support vector machine applications in the field of hydrology: a review. Applied soft computing. 2014; 19: 372-86.
[26]. Malik A, Kumar A, Singh RP. Application of heuristic approaches for prediction of hydrological drought using multi-scalar streamflow drought index. Water Resources Management. 2019; 33(11):3985-4006.
[27]. Pradhan B. A comparative study on the predictive ability of the decision tree, support vector machine and neuro-fuzzy models in landslide susceptibility mapping using GIS. Computers & Geosciences. 2013; 51:350-65.
[28]. Naghibi SA, Ahmadi K, Daneshi A. Application of support vector machine, random forest, and genetic algorithm optimized random forest models in groundwater potential mapping. Water Resources Management. 2017; 31(9):2761-75.
[29]. Meyer D, Wien FT. Support vector machines. The Interface to libsvm in package e1071. 2015; 5;28.
[30]. Aller L, Bennett T, Lehr JH, Petty RJ, Hackett G. DRASTIC: A Standardized System for Evaluating Ground Water Pollution Potential Using Hydrogeologic Settings. Kerr Environmental Research Laboratory, U.S. Environmental Protection Agency Report (EPA). 1987; 600/2.87, 1-641.
[31]. Kumar A, Pramod Krishna A. Groundwater vulnerability and contamination risk assessment using GIS-based modified DRASTIC-LU model in hard rock aquifer system in India. Geocarto International. 2020; 35(11):1149-78.
[32]. Venkatesan G, Pitchaikani S, Saravanan S. Assessment of groundwater vulnerability using GIS and DRASTIC for upper Palar River basin, Tamil Nadu. Journal of the Geological Society of India. 2019; 94(4):387-94.
[33]. Ahirwar S, Shukla JP. Assessment of groundwater vulnerability in upper Betwa river watershed using GIS based DRASTIC model. Journal of the Geological Society of India. 2018; 91(3):334-40.
[34]. Zghibi A, Merzougui A, Chenini I, Ergaieg K, Zouhri L, Tarhouni J. Groundwater vulnerability analysis of Tunisian coastal aquifer: an application of DRASTIC index method in GIS environment. Groundwater for Sustainable Development. 2016; 2:169-81.
[35]. Joshi P, Gupta PK. Assessing groundwater resource vulnerability by coupling GIS-based DRASTIC and solute transport model in Ajmer District, Rajasthan. Journal of the Geological Society of India. 2018; 92(1):101-6.
[36]. Baghapour MA, Nobandegani AF, Talebbeydokhti N, Bagherzadeh S, Nadiri AA, Gharekhani M and Chitsazan N. Optimization of DRASTIC method by artificial neural network, nitrate vulnerability index, and composite DRASTIC models to assess groundwater vulnerability for unconfined aquifer of Shiraz Plain, Iran. Journal of Environmental Health Science and Engineering. 2016; 14(1), pp.1-16.
[37]. Eftekhari M, Akbari M. Development of DRASTIC Method Considering Land Use to Analyze the Potential of Aquifer Pollution in Semi-Arid Regions. Environment and Water Engineering. 2020; 6(4):345-59. [Persian].
[38]. Eftekhari M, Eslaminezhad S, Haji Elyasi A, Akbari M. Geostatistical Evaluation with Drinking Groundwater Quality Index (DGWQI) in Birjand Plain Aquifer. Environment and Water Engineering, 2021; 7(2), 268-279. [Persian].
[39]. Choubin B, Mosavi A, Alamdarloo EH, Hosseini FS, Shamshirband S, Dashtekian K, Ghamisi P. Earth fissure hazard prediction using machine learning models. Environmental research. 2019; 179:108770.
[40]. Rahimzadeh kivi M, Hamzeh S, Kardan Moghadam H. Identification of Vulnerability Potential of Groundwater Quality in Birjand Plain using DRASTIC Model and its calibration using AHP. Physical Geography Research Quarterly. 2015; 47(3), 481-498. [Persian].
[41]. Davijani MH, Anvar AN, Banihabib ME. Locating water desalination facilities for municipal drinking water based on qualitative and quantitative characteristics of groundwater in Iran’s desert regions. Water resources management. 2014; 28(10):3341-53.
[42]. Mosazadeh H, Rezaei A, and Emami H. Investigation of temporal and spatial distribution of groundwater nitrate contamination in Birjand plain and aquifer. National Conference on Water Resources Management Strategies and Environmental Challenges. Sari University of Agricultural Sciences and Natural Resources. 2018. [Persian].