Assessment of Heavy Metal Contamination and Its Impact on Water Quality and Aquatic Life in Mine Surface Plant Areas

Abstract

The Copper mining industry accounts for the country’s largest export earning and creates several jobs. Despite this the mines have been known to be the major contributor to the environmental pollution. It has been observed that in one province of the country, there is high presence of iron and other heavy metals in the surrounding areas. Unfortunately these heavy metals find themselves in water bodies and consequently affect the aquatic life. This study was conducted to develop suitable machine learning prediction models that estimate the impact of mine pollutants on fish production in the Kalumbila area of North-Western Province. The Machine Learning techniques employed include Multiple Linear Regression (MLR), Artificial Neural Networks (ANN), Random Forest (RF) and K-Nearest Neighbors (KNN). These models were evaluated and, in terms of Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) with the values of 0.25 (25%) and 0.22 (22%) indicating that Random Forest appear to be the best-performing models in terms of prediction accuracy compared to other models. In addition, the RF model also achieved the highest R2 score of 0.94, indicating its ability to explain a greater proportion of the variance in the dependent variable compared to the other models. This means that RF provides a strong prediction accuracy than other models in terms of determining heavy metal contamination in impact on Water Quality and Aquatic Life in Mine Surface Plant Areas. Therefore this study shows the potential of Machine Learning models to assist decision makers in understanding the pollution levels in water bodies.