Hybrid Machine Learning Models for Fine-grained Air Quality Forecasting

Abstract

Air pollution has become a major environmental issue that is causing many deaths each year and putting the environment and human health at serious risk. It causes the greenhouse effect, contributes to global warming, and increases the risk of lung cancer and other diseases that affect the respiratory system, including allergies. Setting and upholding strict air quality standards is essential to effectively combating air pollution. The air quality index (AQI) is a measurement used to determine the amount of pollutants in the atmosphere. By utilizing the capabilities of machine learning algorithms, precise forecasting of the fine-grained AQI is made feasible. To predict the AQI, a number of algorithms have been used, including logistic regression, decision tree regression, KNN, SVR, and linear regression. This project's main goal is to create models with machine learning algorithms and determine which model is best for AQI prediction.