Estimation of nitrate concentration in groundwater of Kadava river basin-Nashik district, Maharashtra, India by using artificial neural network model

被引：46

作者：

Wagh V.M. ^{[1
]}

Panaskar D.B. ^{[1
]}

Muley A.A. ^{[2
]}

机构：

[1] School of Earth Sciences, Swami Ramanand Teerth Marathwada University, Nanded, Maharashtra

[2] School of Mathematical Sciences, Swami Ramanand Teerth Marathwada University, Nanded, Maharashtra

来源：

Modeling Earth Systems and Environment | 2017年 / 3卷 / 1期

关键词：

ANN; Groundwater quality; Nashik; Nitrate;

D O I：

10.1007/s40808-017-0290-3

中图分类号：

学科分类号：

摘要：

Monitoring of groundwater quality is an important tool to facilitating adequate information about water management in respective areas. Nitrate concentration in aquifer systems is crucial problem in intensive agricultural regions of Indian subcontinent. Nitrate is one of the qualitative parameter of groundwater and its enrichment leads to human health implications, hence it entails precise periodic extent. In the present study, artificial neural network (ANN) model with back propagation algorithm was implemented to predict groundwater quality and its suitability of Kadava River basin in Nashik district. The groundwater qualitative data were collected from 40 dug/bore wells in pre and post monsoon season of 2011. In this context, significant correlated parameters viz., EC, TDS, TH, Ca, Mg, Na, Cl, CO3, HCO3 and SO4 for pre monsoon; EC, TDS, TH, Mg, Na, Cl, F, CO3, HCO3 and SO4 were considered in post monsoon season. In case of the study area, among 40 groundwater samples, 52.50% and 65% showed higher concentration than the permissible limit (45 mg/L) of Bureau of Indian standards of nitrate in pre and post monsoon season. As a result, the optimal network architectures obtained through R software as 10-8-1 and 10-6-1 for training and 10-6-1 and 10-6-1 are used in testing pre and post monsoon season data set respectively. The simulated outputs track the measured and predicted NO3 values with coefficient of determination (R2), residual mean square error (RMSE) and mean absolute relative error (MARE) for training and testing data. Accordingly, it is promising to manage groundwater resources in an easier manner with proposed ANN model. © 2017, Springer International Publishing Switzerland.

引用

共 28 条

[1]

Agarwal R., Nitrate contamination in ground water samples of Gangapur city town (Sawai Madhopur District) Rajasthan, J Chem Biol Phys Sci, 2, 1, pp. 511-513, (2012)

[2]

APHA, Standard methods for the examination of water and wastewater, (2005)

[3]

Assaf H., Saadeh M., Geostatistical assessment of groundwater nitrate contamination with reflection on DRASTIC vulnerability assessment: the case of the Upper Litani Basin, Lebanon, Water Resour Manage, 23, pp. 775-796, (2009)

[4]

Indian standards specification for drinking water, BIS, 10500, (2012)

[5]

Burkardt M.R., Kolpin D.W., Hydrogeologic and landuse factors associated with the herbicide and nitrate occurrence in near surface aquifers, J Envviron Qual, 22, pp. 646-656, (1993)

[6]

Central Groundwater Board (CGWB), (2014)

[7]

Chang F.J., Tsai W.P., Chen H.K., Yam R.S.W., Herricks E.E., A self organizing radial basis network for estimating riverine fish diversity, J Hydrol, 476, pp. 280-289, (2013)

[8]

Chen J., Wu H., Qian H., Gao Y., Assessing nitrate and fluoride contaminants in drinking water and their health risk of rural residents living in a semiarid region of northwest china, Exposure Health (London), (2016)

[9]

Comly H.H., Cyanosis in infants caused by nitrates in well water, J Am Med Assoc, 257, pp. 2788-2792, (1987)

[10]

Ehteshami M., Farahani N.D., Tavassoli S., Simulation of nitrate contamination in groundwater using artificial neural networks, Model Earth Syst Environ, 2, 1, pp. 1-10, (2016)

← 1 2 3 →