Predictive modelling of post-monsoon groundwater quality in Telangana using machine learning techniques

¹ Krasnoyarsk State Agrarian University 660049, Krasnoyarsk, Russia
² Reshetnev Siberian State of Science and Technology, Krasnoyarsk, Russia
³ Siberian Federal University, Krasnoyarsk, Russia
⁴ Bauman Moscow State Technical University, Artificial Intelligence Technology Scientific and Education Center, Moscow, Russia
⁵ SPE «Radiosvyaz» JSC, ERP department, 19 Dekabristov Str., Krasnoyarsk, 660021, Russia

^* Corresponding author: vasi4244@gmail.com

Abstract

Groundwater quality is vital for public health, agriculture, and industry, especially in regions like Telangana, India. This study analyses and predicts post-monsoon 2020 groundwater quality using data from the Telangana State Groundwater Department. We employed Linear Regression and Random Forest Regression to predict key parameters: pH and Total Dissolved Solids (TDS). Exploratory data analysis revealed significant correlations, such as between TDS and Electrical Conductivity (E.C). The Linear Regression model for TDS performed exceptionally well, with an R² of 0.985, while the Random Forest model also showed strong results. However, both models exhibited moderate accuracy in predicting pH. The study demonstrates the effectiveness of machine learning models in predicting groundwater quality, offering valuable tools for groundwater management. These findings can aid policymakers and environmental managers in making informed decisions to safeguard water resources.