The quantification and prediction of particulate matter (PM) concentrations in the air are essential due to their negative impacts on human health and the environment. This study quantified PM concentrations and associated health effects at four natural gas-based power plants in Bangladesh. The measurement of PM2.5 and PM10 using the respirable dust samplers APS-113NL and APS-113BL, respectively from the year of 2015 to 2021 revealed that the concentration of both types of particles fluctuated over the years. The highest recorded levels of particles were in 2019, with PM2.5 at 126 µg/m3 and PM10 at 283 µg/m3 and the lowest recorded levels of particles were in 2017, with PM2.5 at 76.3 µg/m3 and PM10 at 203.3 µg/m3. In 2021, PM2.5 and PM10 concentrations were 88.5 and 225 µg/m3, respectively, lower than in the past two years. Statistical modeling assessed atmospheric contaminants analyzed time series data, and projected air quality. ARIMA, ETS, and ANN modeling methods have been used to predict the monthly average of PM2.5 and PM10 concentrations. RMSE, MAPE, MASE, and MAE have been utilized for model orders, time series analysis, and forecasting validation. There is a significant variation between the forecasting models and forecasts for average PM2.5 and PM10 concentrations in natural gas-fired power plants from 2022 to 2024. This study also conducted a face-to-face interview with over 100 employees using a structured questionnaire to assess the health effects they are facing due to poor air quality in the power generation complex and found that 2 and 13 % of employees had respiratory and skin issues, respectively. Nonetheless, regular health checks, air filtration, and renewable energy consumption may benefit residents and the environment.