Data Driven Air Quality Analysis and Predictions: A Machine Learning Approach

Air is one of the natural elements of the world. Due to the growth of civilization and industries the air around us has become more polluted. So, predicting the air quality has become a necessary step. By predicting the air quality beforehand, we can take the necessary steps to make the place and the people aware. Machine learning algorithms can help to detect air quality using air pollutants elements. Many research has been done in this field so there are datasets that are available which we can use to predict the air quality. Accurate air quality forecasts can enable timely interventions and raise public awareness. In this study, we utilize machine learning algorithms to predict air quality based on air pollutant PM2.5 from 2016 to 2023. We employed five machine learning models: K-Nearest Neighbors (KNN) Classifier, Random Forest, Gaussian Naïve Bayes, Support Vector Machine (SVM), and Logistic Regression. Our findings indicate that KNN classifier performed the best among the models. This provides valuable insights into the effectiveness of different machine learning approaches for air quality prediction.