Ambient Air Quality Classification by Grey Wolf Optimizer Based Support Vector Machine.

Area of Science:

• Environmental Science
• Public Health
• Data Science

Background:

• Escalating population and industrial development raise public health concerns, particularly regarding air quality.
• Increased vehicle emissions and industrial activities contribute to elevated pollutant concentrations.
• Existing indices for pollutant concentrations necessitate refinement for comprehensive air quality assessment.

Purpose of the Study:

• To develop a mathematical framework for a Cumulative Index (CI) integrating key air pollutants.
• To propose a supervised learning classifier for air quality assessment.
• To evaluate the classifier's performance using real-world air quality data.

Main Methods:

• Formulation of a Cumulative Index (CI) based on SO2, NO2, PM2.5, and PM10 concentrations.
• Implementation of a Support Vector Machine (SVM) algorithm for air quality classification.
• Validation of the SVM classifier using empirical data from Kolkata, Delhi, and Bhopal.

Main Results:

• The developed Cumulative Index (CI) provides a consolidated measure of air quality.
• The SVM classifier demonstrated high efficacy in distinguishing between good and harmful air quality.
• The model's performance was validated across diverse urban environments.

Conclusions:

• The proposed mathematical framework and SVM classifier offer a robust method for air quality monitoring.
• This approach can significantly contribute to public health strategies by providing clear air quality indicators.
• The CI and SVM model show promise for widespread application in environmental health management.