Machine Learning (ML) is rapidly transforming the field of air quality management by enabling more accurate, scalable, and efficient analysis of environmental data. This talk will provide an introduction to the fundamental concepts of ML and demonstrate how these techniques are being applied to tackle key challenges in air quality research. The session will cover a range of applications, including data fusion for integrating measurements from ground monitors, satellites, and low-cost sensors; forecasting models for short- and long-term air pollution prediction; and computer vision for image based pollutant estimation. In addition, the talk will explore the use of ML tools to study air pollution perception, offering insights into how public awareness and behavioral responses can complement traditional monitoring approaches. Through real-world examples and case studies, the session will highlight the potential of AI/ML methods to support evidence-based decision-making and improve strategies for air quality assessment and management. Participants will gain both conceptual understanding and practical perspectives on how modern AI tools are shaping the future of environmental science.