Air Quality Monitoring Using Machine Learning Techniques

Abstract

Abstract-Air pollution (AP) is a major global environmental issue, drawing attention from researchers due to its impact on human health. Predicting air quality is crucial to inform people about health risks and protect against the effects of air pollution, particularly in metropolitan cities facing severe environmental challenges. Real-time monitoring of pollution data enables local authorities to analyze traffic conditions and make informed decisions. In this study, we developed a machine learning model to forecast the air quality index of India, which is a standard measure of pollutant levels (e.g., SO2, NO2) over a specific period. Our model is based on historical data from previous years and uses Gradient Descent-boosted multivariable regression to predict the air quality index for an upcoming year. To improve model efficiency, we applied cost estimation to the predictive problem. The proposed model demonstrates high accuracy, achieving 96% on the current available dataset for predicting India's air quality index. Moreover, we utilized XG Boost and Light GBM algorithms to determine the order of preference based on similarity to the ideal solution, further enhancing the model's performance. Our model has the capability to predict the air quality index for an entire county, state, or any bounded region, given historical pollutant concentration data. By implementing parameter-reducing formulations, we outperformed standard regression models, making our approach a valuable tool for air quality prediction and environmental decision-making to protect human health. Keywords—Machine Learning, Air Quality, Air quality prediction, Monitoring System, Intelligent System.