Use of neural networks and spatial interpolation to predict groundwater quality

Abstract

The artificial neural networks share its working analogous with the human brain; and by using these artificial neural models, various complex nonlinear relationships can be modeled which cannot be described easily using mathematical equations. In this study, groundwater quality at a sanitary landfill site used for solid waste disposal was modeled using artificial neural networks. The groundwater quality was assessed for two consecutive years 2016 and 2017 at ten locations near the site, and the data were used for modeling. Total hardness was predicted using neural networks by using three learning algorithms, and the best one was used in the final model for prediction. The interpolation maps were drawn for both the years to understand the total hardness concentrations at unsampled locations using ArcGIS Geostatistical Analyst Extension, and Inverse Distance Weighing method was used. The percentage effect of spatial and temporal changes on total hardness was calculated by doing the sensitivity analysis and thus finding the relative importance of each input parameter on total hardness. Different algorithms were tested to select the best-performing algorithm with optimal neural architecture.

Evaluation of Water Pollution Prevention Planning Based on Urban and Rural Integration Based on BP Neural Network

“…Surface water extraction, change detection and environmental assessment were prerequisites for water resources management [11]. Kalawapudi Komal used artificial neural network to model the groundwater quality of sanitary landfill for solid waste treatment in the research [12]. These studies showed that the application of BPNN had a positive effect, but there were still some problems.…”

Electrospun amine-functionalized silica nanoparticles–cellulose acetate nanofiber membranes for effective removal of hardness and heavy metals (As(v), Cd(ii),Pb(ii)) in drinking water sources

“…8 The dissolution of multivalent ions, such as Ca(II), Mg(II), Sr(II), Fe(II), and Mn(II), and their associated anions such as HCO 3 − , SO 4 2− , Cl − , NO 3 − , etc., from seepage, sedimentary rocks (such as chalk and limestone), and soil run-off causes water hardness. 9 Drinking hard water can lead to health issues such as cardiovascular diseases, dental difficulties, atopic eczema, and Alzheimer's disease, 5,10 as well as kidney diseases when associated with trace amounts of heavy metals and fluorides. 11 Heavy metal poisoning from drinking water is a global concern.…”

Assessment and Prediction of Groundwater using Geospatial and ANN Modeling

“…Few research studies (Yesilnacar et al 2008;Mohanty et al 2010;Sunayana et al 2019) suggest that neural network models could help in predicting the groundwater quality and groundwater level well in advance for understanding the future scenario. Artificial neural network (ANN) models have also been applied to the water quality problems by several researchers (Singh et al 2009;Ay and Kisi 2012;Csábrági et al 2017).…”