Spatial Prediction of Fluoride Concentration Using Artificial Neural Networks and Geostatic Models

Document Type : Research Paper

Authors

Abstract

In the last decades, researchers had high consideration on the presence of chemical anomalies in water, soil and air which threat human health. Anomalies in fluoride concentration values exceeding standard limit (>1.5 mg/l) in drinking water have high importance, because of direct influence on physiology of human body. Fluoride concentration values of water resources in Bazargan and poldasht plains exceed standard limit (WHO). The aim of this research is spatial prediction of fluoride concentration in these plains. For this purpose Artificial Neural Networks (ANNs) model was utilized as a nonlinear model. For spatial prediction of fluoride concentration in the study area, different structures of these models were tested and the best structure (FNN-BFG) was determined. Spatial modeling was carried out by this structure and using fluoride ion concentration, correlated ions values and position of each sample, for which the determination coefficients of training and test steps were equal to 0.9625 and 0.9019 respectively. Then, results of the model were compared to those of the geostatistical methods of kriging and cokriging and the determination coefficients for test steps were 0.7285 and 0.8556, respectively. The best results of the three developed models were related to ANNs models. 

Keywords

Main Subjects

References

اصغریمقدم الف، جمیری ر و محمدی ع، 1384. مطالعۀ مشخصات هیدروژئولوژیکی بازالت­های منطقۀ ماکو جهت بهرهبرداری بهینه از آب­های زیرزمینی با استفاده از روش­های ژئوفیزیکی و GIS، طرح تحقیقاتی. دانشگاه تبریز، گروه زمینشناسی.
اصغریمقدم الف، جمیری ر و محمدی ع، 1386. منشاء غلظت بالای فلوئورید در آب­های زیرزمینی گدازه­های بازالتی دشت­های بازرگان-پلدشت و تأثیر نامطلوب آن بر سلامتی اهالی منطقه، مجله محیط شناسی، شمارۀ 41، ص. 25-32.
اصغریمقدم الف، فیجانی الف، 1387. مطالعات هیدروژئولوژی و هیدروشیمیایی آبخوان­های بازالتی و کارستی منطقه ماکو در ارتباط با سازندهای زمین شناسی منطقه، فصلنامه علمی-پژوهشی علوم زمین، سال هفدهم، شماره 67. ص. 2-13.
اصغریمقدم الف، فیجانی، الف و ندیری ع، a1387. تأثیر بازالتهای منطقه ماکو در غلظت فلوئورید منابع آب زیرزمینی طرح تحقیقاتی. دانشگاه تبریز، گروه زمینشناسی.
اصغریمقدم الف، نورانی و و ندیری ع، b1387. مدل­سازی بارش دشت تبریز با استفاده از شبکه­های عصبی مصنوعی. مجله دانش کشاورزی، جلد 18، شمارۀ 1. ص. 1-15.
بی­نام، امور مطالعات منابع آب سازمان آب منطقه­ای استان آذربایجان غربی 1372. گزارش شناسائی منابع آب کارست و سازند سخت حوضۀ آبریز ارس، وزارت نیرو، 161 ص.
حسنی‌پاک ع الف، 1377. زمین‌آمار. انتشارات تهران. 314 ص.
فیجانی الف، 1386. بررسی هیدروژئولوژی و هیدروژئوشیمی آبخوان­های بازالتی – آبرفتی دشت­های بازرگان و پلدشت. پایاننامه کارشناسی ارشد آبشناسی، دانشکده علوم طبیعی، دانشگاه تبریز. 141 ص.
ندیری ع، 1386، پیش‌بینی سطح آب­های زیرزمینی توسط مدل ANNs در محدودة متروی شهر تبریز. پایاننامه کارشناسی ارشد آبشناسی، دانشکده علوم طبیعی، دانشگاه تبریز. 178ص.
AlmasriMN and Kaluarachchi JJ, 2005. Modular neural networks to predict the nitrate distribution in ground water using the on-ground nitrogen loading and recharge data. Environmental Modeling & Software 20: 851-871.
ASCE American Society of Civil Engineering Task Committee on geostatistical techniques in geohydrology, 1990. Review of geostatistics in geohydrology. 1:Basic concepts; 2:applications. ASCE J Hydraulic Engin 116(5): 612-658.
ASCE Task Committee on Application of Artificial Neural Networks in Hydrology, 2000. Artificial neural network in hydrology, part I and II. J Hydraulic Engin 5(2): 115-137.
Asghari Moghaddam A and Fijani E, 2008. Distribution of fluoride in groundwater of Maku area, northwest of Iran. Environmental Geology 56(2): 281-287.
Asghari Moghaddam A and Fijani E, 2009. Hydrogeologic framework of the Maku area basalts, north western Iran. Hydrogeology Journal 17: 949-959.
Carrilla- Rivera JJ, Cardona A and Edmunds WM, 2002. Use of abstraction regime and knowledge of hydrogeological conditions to control high-fluoride concentration in abstracted groundwater: San Luis Potosi Basin, Mexico. J Hydrology 261: 24-47.
 
Choi S, Yun Z, Hong S and Ahn K, 2001. The effect of co-existing ions and surface characteristics of nanomemberences. Desalination 133: 53-64.
Daliakopoulos NI, Coulibaly P and Tsanis IK, 2005. Ground water level forecasting using artificial neural networks. J Hydrol 309: 229-240.
Desbarats AJ, Logan CE, Hiton MJ and Sharpe DR, 2002. On the kriging of water table elevations using collateral information from a digital elevation model. J Hydrol 255: 25-38.
Gambolati G and Volpi G, 1979. A conceptual deterministic analysis of the kriging technique in hydrology. Water Resour Res 15(3): 625-629.
Guo Q, Wang Y, Ma T and Ma R, 2007. Geochemical processes controlling the elevated fluoride concentration in groundwaters of the TaiyuanBasin, Northern China. J of Geochemical Exploration 93: 1-12.
Hammer K, 2006. Hydrochemistry and sources of fluoride in Silurian-Ordovician aquifer system, Estonia. M.S. thesis, University of Tartu, Institute of Geology 50 pp.
Isaaks EH and Srivastava RM, 1989. Applied Geostatistics, OxfordUniversity Press.
Jacks G, Bhattacharya P, Chaudhary V and Singh KP, 2005. Controls on the genesis of high-fluoride groundwaters in India. Applied Geochemistry 20: 221-228.
Kim K and Jeong YG, 2005. Factors influencing natural occurrence of fluoride-rich ground waters: a case study in the southeastern part of the KoreanPeninsula. Chemosphere 58: 1399-1408.
Lallahem S, Mania J, Hani A and Najjar Y, 2005. On the use of neural networks to evaluate ground water levels in fractured media. J Hydrol 307: 92-111.
MyersDE, 1991. Pseudocross-variograms, Positive definiteness and cokriging. Mathematical Geology 23: 805-816.
Nourani V, Asghari Moghaddam A and Nadiri AA, 2008a. An ANN-based model for spatiotemporal groundwater level forecasting. Hydrological Processes 22 (26): 5054-5066.
Nourani V, Asghari Moghaddam A and Nadiri AA, 2008b. Forecasting spatiotemporal water levels of Tabriz aquifer. Trends in Applied Sciences Research 3: 319-329.
Pan GC, Gaard D, Moss K and Heiner T, 1993. A Comparison between cokriging and ordinary kriging, case study with a polymetalic deposit. Mathematical Geology 25: 337-398.
Satagopan J and Rajagopalan B, 1994. Comparing spatial estimation techniques for precipitation analysis. Stochastic and Statistical Methods in Hydrology and Environmental Engineering, 3: 317-330. Kluwer Academic Publishers.
Saxena VK and Ahmed S, 2001. Dissolution of fluoride in groundwater: a water-rock interaction study. Environmental Geology 40: 1084-1087.
Shaji T and Kitaura H, 2006. Statistical and geostatistical analysis of rainfall in central Japan. Computers Geosciences 32: 1007-1024.
Water and Soil Science
Volume 19, Issue 2
May 2009
Pages 129-145

Files

Share

How to cite

Statistics