A seasonal autoregressive technique for forecasting PM2.5 trend in Delhi

Abstract

Delhi's air pollution is a severe and persistent environmental problem that frequently reaches dangerous levels. Alarmingly high particulate matter (PM2.5) levels are commonly observed in Delhi, particularly during winter. The World Health Organization (WHO) has set acceptable guidelines for PM2.5 concentrations at 10 µg/m³ for an annual average and 25 µg/m³ for a 24-hour average. However, PM2.5 concentrations in Delhi's air often significantly exceed these limits. PM2.5 pollution has a profound impact on both the environment and public health worldwide. It is a major contributor to respiratory and cardiovascular diseases, lung cancer, breathing problems, and strokes. Additionally, it harms the environment by causing acid rain, damaging vegetation, and reducing visibility. Accurate forecasting of PM2.5 concentrations is therefore essential for implementing health precautions, protecting public health, and providing decision-making guidelines to minimize exposure to its harmful effects. The seasonal autoregressive integrated moving average (SARIMA) model is a robust, adaptable, and precise method for predicting time-series data with seasonal and non-seasonal components. It is particularly useful for real-time forecasting, especially in scenarios where seasonality plays a significant role. SARIMA effectively utilizes past data to predict future PM2.5 trends. The proposed model provides valuable insights for forecasting PM2.5 concentrations in Delhi. Air quality index (AQI) data from 2015 to 2022 was used to train the model, which was developed using the SARIMA technique to predict trends for the next five years with 95% accuracy. This predictive capability enables informed decision-making to promote a sustainable environment and safeguard public well-being. By accurately forecasting PM2.5 concentrations, the model supports proactive policy decisions and helps protect residents from the adverse effects of air pollution.