Hydrogeochemical characterization of the groundwater of Lahore region using supervised machine learning technique

The cationic and anionic composition in groundwater can be better understood by identifying the type of hydrogeochemical processes influencing groundwater chemistry. This research deals with the characterization of groundwater samples by considering the likely role of hydrogeochemical processes and the factors responsible for the weathering process. The study applies statistical methods and supervised machine learning algorithm (i.e., logistic regression model) on the large data set of 1300 water samples from the Lahore district of Punjab, Pakistan. All the water samples were collected by the local authorities from a deep unconfined aquifer (> 350 ft in depth) for the years of 2005 to 2016. The characterization of groundwater quality parameters includes pH, total dissolved solids (TDS), electrical conductivity (EC), total hardness (TH), calcium (Ca²⁺), magnesium (Mg²⁺), sodium (Na⁺), potassium (K⁺), chloride (Cl^-), bicarbonate (HCO₃^-), nitrate (NO₃^-), and sulfate (SO₄^2-). The results show the sequence of the major ion in the following order: Na⁺  > Ca²⁺  > Mg⁺  > K⁺ and HCO₃^2-  > SO₄^2-  > Cl^-  > NO₃^-. The ionic ratios and Gibb's plot revealed that the prominent hydrogeochemical facies of aquifer water is Ca-HCO₃, Ca-Na-HCO₃, and mixed Ca-Mg-Cl type rock-weathering process, especially carbonate and silicate weathering, as significant process controlling water chemistry. The statistical evaluation of the prepared regression model determined its prediction accuracy as 92.2%, which means the model is highly efficient and satisfies the analysis. The outcomes of this study favor the utilization of such methods for other areas with large data sets.