Prediction of particulate matter concentration profile in an opencast copper mine in India using an artificial neural network model

Abstract

Springer Science+Business Media Dordrecht Particulate matter (PM) is a major pollutant in and around opencast mine areas. The problem of degradation of air quality due to opencast mine is more severe than those in underground mine. Prediction of dust concentration must be known to implement control strategies and techniques to control air quality degradation in the workplace environment. Limited studies have reported the dispersion profile and travel time of PM between the benches inside the mine. In this paper, PM concentration has been measured and modeled in Malanjkhand Copper Project (MCP), which is one of the deepest opencast copper mines in India. Meteorological parameters (wind speed, temperature, relative humidity) and PM concentration in seven size ranges (i.e., PM 0.23–0.3 , PM 0.3–0.4 , PM 0.4–0.5 , PM 0.5–0.65 , PM 0.65–0.8 , PM 0.8–1 , and PM 1–1.6 ) have been measured for 8 days. The results of the field study provide an understanding of the dispersion of the PM generated due to mining activities. This research work presents an approach to assess the exposure of enhanced level of PM concentration on mine workers and its variation with depth. The correlations study shows that concentration of PM during its travel from source to surface is associated with depth. Empirical equations are developed to represent relationships between concentrations of PM and depth. Artificial neural network (ANN) model showing the relationship between PM concentration and meteorological parameters has been developed. The performance of the ANN model is evaluated in terms of the correlation coefficient between the real and the forecasted data. The results show strong agreement between the experimental data and the modeled output. The findings of this work are important in understanding fine PM variation inside the mine at the workplace and the associated exposure of mine workers.