A holistic approach for understanding the status of water quality and causes of its deterioration in a drought-prone agricultural area of Southeastern India

• Published in: Environmental science and pollution research international 2023-11, Vol.30 (55), p.116765-116780
• Main Authors: Pathakamuri, Prabhakara Chowdary, Villuri, Vasanta Govind Kumar, Pasupuleti, Srinivas, Banerjee, Ashes, Venkatesh, Akella Satya
• Format: Article
• Language: English
• Subjects: Aquatic Pollution; Artificial neural networks; Atmospheric Protection/Air Quality Control/Air Pollution; Contamination; Data collection; Deep learning; Drinking water; Drought; Earth and Environmental Science; Ecotoxicology; Entropy (Information theory); Environment; Environmental Chemistry; Environmental Health; GIS Applied to Soil-Agricultural Health for Environmental Sustainability; Groundwater; Groundwater irrigation; Groundwater pollution; Groundwater quality; Learning algorithms; Machine learning; Mathematical models; Neural networks; Parameters; Physicochemical properties; Quality assessment; Turbidity; Waste Water Technology; Water analysis; Water Management; Water Pollution Control; Water quality; Water sampling
• ISSN: 1614-7499; 0944-1344; 1614-7499
• DOI: 10.1007/s11356-022-22906-z

This study investigates the groundwater quality in the Kadiri Basin, Ananthapuramu district of Andhra Pradesh, India. Groundwater samples from 77 locations were collected and tested for the concentration of various physicochemical parameters. The collected data were assimilated in the form of a groundwater quality index to estimate groundwater quality (drinking and irrigation) using an information entropy-based weight determination approach (EWQI). The water quality maps obtained from the study area suggest a definite trend in groundwater contamination of the study area. Furthermore, the influence of different physicochemical parameters on groundwater quality was determined using machine learning techniques. Learning and prediction accuracies of four different techniques, namely artificial neural network (ANN), deep learning (DL), random forest (RF), and gradient boosting machine (GBM), were investigated. The performance of the ANN model (MEA = 11.23, RSME = 21.22, MAPE = 7.48, and R 2  = 0.91) was found to be highly effective for the present dataset. The ANN model was then used to understand the relative influence of physicochemical parameters on groundwater quality. It was observed that the deterioration in groundwater quality in the study area was primarily due to the excess concentration of turbidity and iron values. The relatively higher concentration of sulfate and nitrate had caused a significant impact on the groundwater quality. The study has wider implications for modeling in similar drought-prone agricultural areas elsewhere for assessing the groundwater quality.