A Fuzzy Inference System for enhanced groundwater quality assessment and index determination

Groundwater is a vital resource for human consumption, particularly in rural areas with limited access to treated water. Assessing groundwater quality is crucial for economic development and human well-being. The conventional Water Quality Index models used for this purpose have limitations related to data volatility and judgment uncertainties. To overcome these limitations, our study introduces a novel approach that employs a Fuzzy Inference System to determine the Water Quality Index. The dataset used in our research includes multiple parameters such as pH, EC, TDS, Ca, Mg, Na, K, HCO3, Cl, SO4, TH, DWQI, and other physio-chemical and chemical parameters. Our approach utilizes linguistic variables, fuzzy rules, and the hyperbolic tangent set function to handle imprecise and uncertain water quality data. By employing Fuzzy C-Means clustering, we group similar water samples based on quality parameters and map membership values to linguistic terms representing water quality categories. Suitable defuzzification methods are then applied to convert fuzzy outputs into precise results. This proposed approach provides a comprehensive framework for accurate water quality assessment, enabling informed decision-making and more reliable and precise evaluations of groundwater quality for human consumption. Our approach enhances groundwater safety and supports the effective management of this vital natural resource.