Implementing Machine Learning Algorithms to Predict Particulate Matter (PM2.5): A Case Study in the Paso del Norte Region

Abstract

This work focuses on the prediction of an air pollutant called particulate matter (PM (Formula presented.)) across the Paso Del Norte region. Outdoor air pollution causes millions of premature deaths every year, mostly due to anthropogenic fine PM (Formula presented.). In addition, the prediction of ground-level PM (Formula presented.) is challenging, as it behaves randomly over time and does not follow the interannual variability. To maintain a healthy environment, it is essential to predict the PM (Formula presented.) value with great accuracy. We used different supervised machine learning algorithms based on regression and classification to accurately predict the daily PM (Formula presented.) values. In this study, several meteorological and atmospheric variables were retrieved from the Texas Commission of Environmental Quality’s monitoring stations corresponding to 2014–2019. These variables were analyzed by six different machine learning algorithms with various evaluation metrics. The results demonstrate that ML models effectively detect the effect of other variables on PM (Formula presented.) and can predict the data accurately, identifying potentially risky territory. With an accuracy of 92%, random forest performs the best out of all machine learning models.