Quantitative modeling of nitrate distribution in the Ardabil Plain aquifer using fuzzy logic

Document Type : Research Paper


1 Assistant professor, geology department, University of Kurdistan

2 Professor, geology department, University of Tabriz

3 Associate professor, geology department, Kharazmi University


The Ardabil plain aquifer, with area about 900 km2, has high concentration amounts of nitrate in some parts. Nowadays, nitrate pollution in groundwater due to the widespread application of fertilizers and increasing of drinking water demand, has encountered consumers with problem. The adverse health effects of high nitrate levels in drinking water have been well documented.
In the last two decades use of fuzzy logic has considered to simulate of environmental process because of complexity in modeling domain and uncertainty in data. Most of these research studies has profited from advantages of fuzzy logic beside other scientific methods.
In previous published academic researches which investigated vulnerability of aquifer by fuzzy logic, it has been concluded that data clustering and determination of bounds between these clusters is a matter of importance and the efficiency of fuzzy logic is higher than traditional methods.
Reviewing the previous records indicates that there is not any literature about modeling of nitrate in Ardabil plain. So in this study distribution of nitrate in Ardabil plain aquifer has been estimated using fuzzy logic modeling and the performance of this method has been compared with kriging.
Material and Methods
The study area is located between latitude 38°00′ and 38°30′ and longitude 48°00′ and 48°40′ and it covers an area of approximately 900 km2. In order to spatial distribution modeling of nitrate concentration in Ardabil plain, a total of 61 wells were sampled for chemical analyses on November, 2011. In this study 75% and 25% of samples were used for calibration and verification, respectively.
Fuzzy logic
Contrary to classic sets, that their members are completely belong to them, in fuzzy sets the members have membership grades between 0 and 1. One of the applications of fuzzy theory is modeling. In order to modeling by fuzzy logic, first input data are shown as fuzzy membership functions, then these membership functions are related to output data via definition of fuzzy rules. Sugeno model is used in process of this kind of modeling which consists of three stages: 1- clustering, 2- identification of rules and 3- parameter estimation.
To determine the optimum number of clusters, the software of FuzME has been applied.   
After the determination of classes, inputs of model were related to the outputs by definition of the if-then fuzzy rules. In the last step, least square errors were minimized to calibrate model.
Kriging is a geostatistics interpolation method which is an efficient linear unbiased estimator. After the examination of normality of data and using normalization for data without normal distribution, the best experimental and theoretical variogram basis isotropic or anisotropic properties of data plotted by GS+ software. As a result the best chosen variogram was exponential with nugget effect of 0.09 and sill about 0.50.
Discussion of Results & Conclusions
In this study longitude and latitude have considered as inputs and nitrate concentrations have kept for output of model. For the reason that the UTM amounts were large numbers, in the beginning the inputs normalized between 0 and 1 then they were classified in six clusters by fuzzy c-mean clustering method. Since the number of rules in this type of modeling is equal to the clusters, therefore the set of inputs was related to the set of outputs via defining six rules and the parameters of model were estimated by the running of the model. The calibrated parameters of input and output membership functions are given in table (1).
Table 1- the optimized parameters of input membership functions and output linear functions




out put
























































To do the verification of model a total of 16 separated samples were used and its results were compared with that of kriging method. For this purpose root mean square error (RMSE), mean absolute error (MAE) and coefficient of determination (R2) were computed which is presented in table (2).
Table 2- Statistical characteristics of used data for verification












Fuzzy logic













According to reported results in table (2), purposed model showed better results than kriging method, so to generate the nitrate distribution map, the verified fuzzy model was run and final result is shown in figure (1).
Figure 1- Spatial distribution map of nitrate in Ardabil plain aquifer
The reliability of spatial distribution maps of pollutant is very important in water resources management. Basically, the geostatistics interpolation methods especially kriging are used to generate spatial distribution data. According to the results, the used fuzzy model was very efficient in estimating of nitrate concentrations in the study area. 
The final output of the model shows that the nitrate concentrations in some parts of north and south –west of the plain is higher than 10 mg which these parts occupied about 17% of aquifer area.
The places with high amounts of nitrate around Ardabil city had full conformity with urban waste water, thus with strong probability nitrate pollution could be related to waste water. Also, high concentrations of nitrate in the north margin of the plain are in conformity with landfill which it can be considered as cause of nitrate pollution at that area likely.


Main Subjects

استواری، ی.، بیگی‌ هرچگانی، ح. و داودیان، ع. ر. 1391. بررسی تغییرات مکانی نیترات در آب زیرزمینی دشت لردگان، مدیریت آب و آبیاری، دورۀ 2، شمارۀ 1، بهار 1391، صص 55- 67.
اصغری‌مقدم، الف. 1389. اصول شناخت آب‌های زیرزمینی، انتشارات دانشگاه تبریز، 349 ص.
جعفری ملک‌آبادی، ع. و همکاران. ۱۳۸۳. بررسی غلظت نیترات در آب‌های زیرزمینی استان اصفهان، علوم و فنون کشاورزی و منابع طبیعی، سال هشتم، شمارۀ سوم صص 69- 82.
جلالی، م. و کلاه‌چی، ز. ۱۳۸۴. غلظت نیترات در آب‌های زیرزمینی منطقة بهار همدان، مجلة علوم خاک و آب، جلد ۱۹، شمارة ۲، صص ۱۹۴ تا ۲۰۲.
حسنی‌پاک، ع. الف. 1377. زمین آمار (ژئواستاتیستیک)، چاپ اول، انتشارات دانشگاه تهران، 314 ص.
خزاعی، الف.، آل‌شیخ، ع. الف.، کریمی، م. و وحیدنیا، م. ح. 1391. مقایسة دو روش مدل‌سازی با استفاده از شبکة عصبی- فازی در پیش‌بینی غلظت آلایندة مونوکسید کربن، محیط‌شناسی، سال سی و هشتم، شمارة 4، صص 29- 44.
دانشور وثوقی، ف. و دین‌پژوه، ی. 1391. بررسی روند تغییرات کیفیت آب زیرزمینی دشت اردبیل با استفاده از روش اسپیرمن، محیط‌شناسی، سال سی و هشتم، شمارة 4، صص 17- 28.
رحیمی بندرآبادی، س. و ثقفیان، ب. 1386. برآورد توزیع مکانی بارندگی با کمک تئوری مجموعه‌های فازی، مجلۀ علمی- پژوهشی تحقیقات منابع آب ایران، سال سوم، شمارۀ 2، صص 26- 38.
لطیف، م. ۱۳۸۱. بررسی آلودگی نیترات و منشأیابی آن در آب‌های زیرزمینی دشت مشهد، پایان‌نامۀ کارشناسی ارشد، دانشکدۀ کشاورزی، دانشگاه صنعتی اصفهان.
محسنی، ا. ۱۳۶۵. بررسی وضع آلودگی آب‌های زیرزمینی به یون نیترات در اثر کاربرد کودهای ازته در شهرستان بابل، پایان‌نامة کارشناسی ارشد، دانشکدة کشاورزی، دانشگاه تربیت مدرس.
محمدیان فضلی، م. و صادقی، غ. ر. ۱۳۸۲. بررسی آلودگی منابع تأمین آب آشامیدنی شهر زنجان طی سال‌های 79- 80، مجلۀ علمی دانشگاه علوم پزشکی و خدمات درمانی زنجان، شمارة ۴۳، صص ۴۹ تا ۵۴.
نیک‌نام، ر.، محمدی، ک. و جوهری‌مجد، و. 1386. ارزیابی آسیب‌پذیری سفرۀ آب زیرزمینی تهران- کرج با روش DRASTIC و منطق فازی، مجلۀ علمی- پژوهشی تحقیقات منابع آب ایران، سال سوم، شمارۀ 2، صص 39- 47.
هاشمی، س. ح.، عظیمی قادیکلایی، م. م.، رعیتی دماوندی، م. و برکتین، س. 1391. کاربرد روش ارزیابی جامع فازی در پهنه‌بندی کیفی آب رودخانه‌ها، محیط‌شناسی، سال سی و هشتم، شمارة ۶۲، صص 103- 110.
یوسفی، ذ. و نائیج، ا. ۱۳۸۶. بررسی و تعیین میزان نیترات منابع آب آشامیدنی روستایی آمل، مجلة دانشگاه علوم پزشکی مازندران، دورة هفدهم، شمارة ۶۱، صص ۱۶۱ تا ۱۶۵.
Almasri, M. N. and Kaluarachchi, J. J. 2005. Multi-criteria decision analysis for the optimal management of nitrate contamination of aquifers. Journal of Environmental Management, 74, 365–381.
Amini, M., Afyuni, M., Fathianpour, N., Khademi, H. and Flühler, H. 2005. Continuous soil pollution mapping using fuzzy logic and spatial interpolation. Geoderma, 124 (3–4), 223–233.
Antonakos, A. K. and Lambrakis, N. J. 2007. Development and testing of three hybrid methods for the assessment of aquifer vulnerability to nitrates, based on the drastic model, an example from NE Korinthia, Greece. Journal of Hydrology, 333, 288– 304.
Chen, X. 2004. Recursive Least-Squares Method with Membership Functions, Proceedings of the Third International Conference on Machine Learning and Cybernetics, Shanghai, pp: 1962-1966.
Dixon, B., Scott, H. D.,Steele, K. F. and Dixon, J. C. 2002. Prediction of aquifer vulnerability to pesticides using fuzzy rule-based models at the regional scale. Physical Geography, 23 (2), 130-153.
Flipo, N., Jeanne'e, N., Poulin, M., Even, S. and Ledoux, E. 2007. Assessment of nitrate pollution in the Grand Morin Aquifers (France): combined use of geostatistics and physically-based modeling. Environmental Pollution, 146 (1), 241–256.
Jacquin, A. p. and Shamseldin, A. Y. 2006. Development of rainfall-runoff models using Takagi-Sugeno Fuzzy Inference System. Journal Homepage: WWW.elsevier.com/locate/jhydrol.
Kim, K. H., Yun, S.T., Choi, B. Y., Chae, G. T., Joo, Y., Kim, K. and Kim, H. S. 2009. Hydrochemical and multivariate statistical interpretations of spatial controls of nitrate concentrations in a shallow alluvial aquifer around oxbow lakes (Osong area, central Korea). Journal of Contaminant Hydrology, 107, 114–127.
Kord, M. and Moghaddam, A. A. 2014. Spatial analysis of Ardabil plain aquifer potable groundwater using fuzzy logic. Journal of King Saud University – Science, 26, 129–140.
Majumder, R. K., Hasnat, M. A., Hossain, Sh., Ikeue, K. and Machida, M. 2008. An exploration of nitrate concentrations in groundwater aquifers of central-west region of Bangladesh. Journal of Hazardous Materials, 159, 536–543.
Matlab user’s Guide. 2001. Fuzzy logic toolbox, Matlab CD-ROM Mathworks, Inc.
Mertens, M. and Huwe, B. 2002. FuN-Balance: a fuzzy balance approach for the calculation of nitrate leaching with incorporation of data imprecision. Geoderma, 109, 269– 287.
Minasny, B. and McBratney, A. B. 2002. FuzME Version 3. Australian Centre for Precision Agriculture, The University of Sydney NSW 2006, Australia. Available at: http://www.usyd.edu.au/su/agric/acpa/fkme/program.html; accessed 17/7/2005.
Nadiri, A., Fijani, E., Asghari-Moghaddam, A., Tsai, F. 2013. Supervised committee machine with artificial intelligence for prediction of fluoride concentration.  Journal of Hydroinformatics ,  15(4),1474-1490.
Nadiri, A., Chitsazan, N., Tsai, F., and Moghaddam, A. 2014. Bayesian Artificial Intelligence Model Averaging for Hydraulic Conductivity Estimation. J. Hydrol. Eng., 19(3), 520–532.
Rajasekaran, S. and Vijayalakshmi Pai, G. A. 2005. Neural networks, fuzzy logic, genetic algorithms synthesis and applications, Prentice-Hall of India, New Delhi, 439.
Shrestha, R. R., Bardossy, A. and Rode, M. 2007. A hybrid deterministic–fuzzy rule based model for catchment scale nitrate dynamics. Journal of Hydrology, 342, 143– 156.
Tayfur, G., Nadiri, A., Moghaddam, A. 2014. Supervised Intelligent Committee Machine Method for Hydraulic Conductivity Estimation. Water Resources Management, 28(4):1173-84.
Tutmez, B. and Hatipoglu, Z. 2010. Comparing two data driven interpolation methods for modeling nitrate distribution in aquifer. Ecological Informatics, 5 , 311–315.
Vitharana, U. W. A., Van Meirvenne, M., Cockx, L. and Bourgeois, J. 2006. Identifying potential management zones in a layered soil using several sources of ancillary information. Soil Use and Management, 22, 405–413.