Assessment of groundwater quality: a fusion of geochemical and geophysical information via Bayesian neural networks

Abstract

Deplorable quality of groundwater arising from saltwater intrusion, natural leaching and anthropogenic activities is one of the major concerns for the society. Assessment of groundwater quality is, therefore, a primary objective of scientific research. Here, we propose an artificial neural network-based method set in a Bayesian neural network (BNN) framework and employ it to assess groundwater quality. The approach is based on analyzing 36 water samples and inverting up to 85 Schlumberger vertical electrical sounding data. We constructed a priori model by suitably parameterizing geochemical and geophysical data collected from the western part of India. The posterior model (post-inversion) was estimated using the BNN learning procedure and global hybrid Monte Carlo/Markov Chain Monte Carlo optimization scheme. By suitable parameterization of geochemical and geophysical parameters, we simulated 1,500 training samples, out of which 50 % samples were used for training and remaining 50 % were used for validation and testing. We show that the trained model is able to classify validation and test samples with 85 % and 80 % accuracy respectively. Based on cross-correlation analysis and Gibb's diagram of geochemical attributes, the groundwater qualities of the study area were classified into following three categories: "Very good", "Good", and "Unsuitable". The BNN model-based results suggest that groundwater quality falls mostly in the range of "Good" to "Very good" except for some places near the Arabian Sea. The new modeling results powered by uncertainty and statistical analyses would provide useful constrain, which could be utilized in monitoring and assessment of the groundwater quality.

Application of the Artificial Neural Network and Neuro‐fuzzy System for Assessment of Groundwater Quality

“…Other studies have reported similar results describing water quality indices developed based on ANNs and ANFIS [2,30,31]. The ability of the ANN and ANFIS models to simulate the concentration values of EC and TDS at the Langat Basin were excellent ( Table 3 and Figs.…”

Analysis of Electrical Resistivity Data in Resolving the Saline and Fresh Water Aquifers in West Coast Maharashtra

“…The pH value in the study area ranges from 5.81 to 6.98. The pH concentration indicates that the groundwater is relatively acidic in Kondura (pH value 5.81), Mochemar (pH value 5.92), Kelus (pH value 5.98), Humarmala (pH value 6.34) and Nerur (pH value 6.36) than the rest of the places (Maiti et al, 2012). The geochemical analysis of groundwater samples further corroborates with the findings of resistivity studies and emphasizes the extent of saline water intrusion into the mainland.…”

“…The western part (VES stations 1 and 29) is encroached by saline water presumably due to the vicinity of Arabian Sea. Geochemical analysis of groundwater in the study area (Maiti et al, 2012) reported that the electrical conductivity (EC) ranged between 70 and 4,450 µS/cm (mean =421.47 ìS/cm). The EC values recorded at VES points 2, 5, 26 and 29 falls beyond the acceptable level for drinking prescribed by World Health Organization (WHO, 1984), and were attributed due to the intrusion of saline water from Arabian Sea.…”

“…A total of 36 water samples in this study area were collected and the groundwater quality was assessed using Bayesian neural network (BNN) algorithm (Maiti et al, 2012). The BNN model-based results suggest that groundwater quality falls mostly in the range of "Good" to "Very good" except for some places in the vicinity of the Arabian Sea.…”

Water quality concern in the Amaravathi River Basin of Karur district: a view at heavy metal concentration and their interrelationships using geostatistical and multivariate analysis

“…According to Langenegger (1990) classification, the majority of the samples fall under saline category (1500-10,000 μS/cm). TDS is regarded as one of the key factors which decide the use of groundwater for any purpose (Maiti et al, 2013). The TDS value of surface water (November 2011) and groundwater found during November 2012 and 2013 exceeds the acceptable limit of 500 mg/L.…”