Surface water quality assessment by Random Forest

Abstract The energetic nature of these important water resources makes them the most vulnerable to contamination from additional waste multiple sources. Water quality monitoring is critical environmental management, and successful provides direction confirms effectiveness management. Models based on artificial intelligence are fundamental for anticipating appropriate moderation measures surface quality. In any case, it remains a challenge requires requirement improve display accuracy. Faster cheaper control required due real-world impact low With this inspiration, research examines an array machine-learning calculations estimate proposed approach uses Random Forest modeling also useful predicting in Kulik geographic region West Bengal, India. It good tool assessing ensuring safe use drinking water. Various parameters (iron, fluoride, total coliform, fecal pH, dissolved solids, magnesium, alkalinity, chloride, hardness, nitrate, calcium, Escherichia coli) were measured seasonally (winter, summer, rain) over 10 years (2010–2019). estimated study solids (TDS), iron.