Prediction of air quality index using machine learning

• Main Author: Cheah Jia'an
• Other Authors: Wong Kin Shun, Terence
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2024
• Subjects: Engineering; Machine learning
• Online Access: https://hdl.handle.net/10356/176459
• Institution: Nanyang Technological University

This project aimed to develop a machine-learning model for forecasting the Air Quality Index in Hong Kong with the use of historical and real time pollutant data. Through careful evaluation of the five machine learning models, this study aimed to identify the most effective model to predict air quality index. Ultimately, Linear Regression emerged as the top runner up as it demonstrated strongest predictive capabilities for forecasting of the next day’s Air Quality Index, showcasing its great potential in addressing air pollution challenges. It is important to note that Gaussian Naïve Bayes and Support Vector Regression were excluded due to their requirement for the target variable(y) to be a 1D array, a limitation of the libraries available in Jupyter Notebook. By rigorously evaluating key metrics such as Mean Square Error, Root Mean Squared Error and Coefficient of Determination, this project highlights the urgent need to tackle air pollution challenges.