URBAN AMBIENT AIR QUALITY INDEX CLASSIFICATION USING MULTI-POLLUTANT SENSOR READINGS

Abstract

Urban air pollution has emerged as a critical environmental and public health
challenge, especially in rapidly growing cities. Continuous monitoring and accurate
assessment of air quality are essential for mitigating its adverse effects. This project
presents a machine learning-based approach for the classification of the Urban
Ambient Air Quality Index (AQI) using data obtained from multi-pollutant
environmental sensors.
The proposed system analyzes key atmospheric pollutants, including particulate
matter (PM2.5 and PM10), carbon monoxide (CO), nitrogen dioxide (NO₂), sulfur
dioxide (SO₂), and ozone (O₃). These pollutant concentrations are collected through
sensor networks and used as input features for model development. Prior to model
training, the dataset undergoes preprocessing steps such as missing value treatment,
normalization, and feature optimization to enhance accuracy and reliability.
Various classification algorithms, such as Decision Trees, Random Forest, Support
Vector Machines, and Neural Networks, can be employed to categorize air quality
into standard AQI levels (e.g., Good, Moderate, Poor, etc.). The system aims to
provide real-time and accurate predictions of air quality, enabling authorities and
individuals to take informed decisions for health protection and environmental
management.
Overall, this work contributes to the development of intelligent air quality monitoring
systems by leveraging machine learning techniques, thereby supporting sustainable
urban living and pollution control strategies.