Experimentation
and Statistical Prediction of Dust Emission in Iron Ore Mines using Supervised Machine
Learning (Regression) Modelling
Pal Rajib, Vardhan Harsha, Amrites Senapati and Sahas Swamy V.
Disaster Advances; Vol. 18(5); 57-70;
doi: https://doi.org/10.25303/185da57070; (2025)
Abstract
In India, the mine area and the processing plant of materials such as iron ore and
coal will cause dust emissions. The fugitive dust emission creates a hazardous working
environment for the workers. Dust emissions will cause pulmonary-related diseases
to the workers and also to the people living in nearby areas of the mine. Environmental
effects such as air pollution occur due to the dispersion of particulate matter
over the permissible limit in the processing area. This study evaluates dust emission
levels and air quality control measures in an iron ore mine (A), Karnataka, India.
Fugitive and workplace dust sampling was conducted following DGMS and MoEF and CC
guidelines, with a specific focus on PM10 and PM2.5 particulate matter. Measurements
revealed that dust concentrations in several mining areas exceeded the permissible
limit of 1200 μg/m³ as per the National Ambient Air Quality Standards (NAAQS, 2009).
To analyze and predict these concentrations, supervised machine learning (regression)
modeling including linear, polynomial (order 2) and polynomial (order 2) models,
was applied. The results indicated that a third-order polynomial regression model
provided the best fit for predicting dust concentrations, demonstrating lower error.
The study emphasizes the necessity of more robust dust suppression measures including
installing a dry fog dust suppression system, to guarantee safe working conditions
and adherence to environmental regulations, even in the face of efforts to reduce
dust exposure.
