Machine learning models for estimating criteria pollutants and health risk-based air quality indices over eastern coast coal mine complex belts
Pradeep Kumar, Arti Choudhary, P. K. Joshi, Ram Pravesh Kumar, R. Bhatla
Abstract
Estimating criteria pollutants is crucial due to their continuous increase and impact on respiratory health. To mitigate the impact of air pollution on human health, it is essential to understand the concentration of air pollutants at specific locations. This study aims to evaluate the variation, estimate the levels of criteria pollutants, and assess their potential health risks in the vicinity of a coal mine complex and a thermal power plant situated in an eastern coastal state of India. The pre-existing hot spot regions—Talcher (T) and Brajrajnagar (B)—which host many coal-fired power plants and clusters of coal-mining blocks in the coastal state of Odisha, are considered. Talcher consistently shows higher levels of particulate matter (PM 10 ), nitrogen dioxide (NO 2 ), and sulfur dioxide (SO 2 ), reflecting a greater industrial impact. Brajrajnagar, while also impacted, exhibits comparatively lower pollutant concentrations. The observed seasonal trends highlight the necessity for targeted mitigation strategies to address pollution levels and associated health risks in these regions. Novel machine learning (ML) models, including independent component regression (ICR), ElasticNet (ENET), and boosted tree (BT), are applied to estimate criteria pollutants. Statistical analyses highlight BT as the superior model, outperforming ENET and ICR in pollutant estimation, particularly in Talcher. Taylor plots and statistical evaluations further validate the BT model’s robustness in air pollutant estimation. Additionally, the study assesses the associated health risks posed to nearby populations of Talcher and Brajrajnagar. The analysis highlights significant spatial disparities in pollution levels, with Talcher consistently recording higher concentrations of PM 10 , NO 2 , and SO 2 and poorer air quality index (AQI) than Brajrajnagar. Talcher also shows greater health risks, with pollutant exposure linked up to 6% higher risks for PM 10 , 5% for NO 2 , and up to 3% for SO 2 . The health risk-based air quality index (HAQI) reveals an underestimation of health risks by the current AQI, emphasizing the need for improved metrics to address the impacts of multi-pollutant exposure.