Air quality prediction using machine learning algorithms

• Main Author: Chang, Branson
• Other Authors: Josephine Chong Leng Leng
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2024
• Subjects: Computer and Information Science
• Online Access: https://hdl.handle.net/10356/181105
• Institution: Nanyang Technological University

The advancement in technology has significantly enhanced the development and improvement of various machine learning algorithms. These sophisticated algorithms have empowered environmentalists and government organizations to extract valuable insights about air pollutants. By analyzing historical data, they can accurately forecast future trends, identify pollution sources, and develop effective strategies for air quality management and public health protection. The goal of this project is to identify which air quality pollutants most significantly impact the Air Quality Index (AQI). This will be achieved by comparing AQI parameters used by various countries and using statistical methods and data analytics techniques to analyze the effects of different pollutants on the AQI. Various machine learning algorithms will be compared to determine which is the most effective in predicting AQI based on pollutant concentration. The best machine learning algorithm will be deployed into a web application using Flask. The web application will allow users to predict the AQI by inputting the pollutant concentrations. Users will be able to enter values for various pollutants, such as PM2.5, PM10, NO2, SO2, CO, and O3. The application will then use the machine learning model to calculate and display the AQI, providing real-time predictions and insights into air quality based on the input data. This functionality will help users assess air quality conditions and make informed decisions about their activities and health.