Optimized machine learning model for air quality index prediction in major cities in India

Area of Science:

• Environmental Science
• Computer Science
• Data Science

Background:

• Urban air pollution, driven by industrialization and vehicle emissions, drastically elevates the Air Quality Index (AQI) in major cities.
• Accurate AQI analysis is crucial for implementing effective government measures to mitigate air pollution.
• Existing methods for AQI prediction require enhancement to meet the demands of rapidly urbanizing areas.

Purpose of the Study:

• To develop and validate an optimized artificial intelligence model for precise Air Quality Index (AQI) prediction in major Indian cities.
• To enhance the accuracy of air pollution forecasting by integrating advanced machine learning techniques.
• To provide a reliable tool for policymakers to address urban air quality challenges.

Main Methods:

• An optimized machine learning model combining Grey Wolf Optimization (GWO) with the Decision Tree (DT) algorithm was developed.
• The model was trained and tested using air quality data from Kaggle for major Indian cities including Delhi, Hyderabad, Kolkata, Bangalore, Visakhapatnam, and Chennai.
• Performance was evaluated using metrics such as R-Square, Root Mean Square Error (RMSE), Mean Squared Error (MSE), Mean Absolute Error (MAE), and accuracy, and compared against k-nearest Neighbors, Random Forest, and Support Vector Regressor models.

Main Results:

• The proposed GWO-DT model demonstrated superior prediction performance compared to traditional machine learning algorithms.
• Achieved high accuracy rates: 88.98% for New Delhi, 91.49% for Bangalore, 94.48% for Kolkata, 97.66% for Hyderabad, 95.22% for Chennai, and 97.68% for Visakhapatnam.
• The model's effectiveness in predicting AQI across diverse major cities was experimentally verified.

Conclusions:

• The optimized GWO-DT model offers a significant advancement in artificial intelligence-driven air quality prediction.
• This approach provides a more accurate and reliable method for forecasting AQI, aiding in pollution control strategies.
• The study highlights the potential of hybrid AI models in addressing critical environmental issues like urban air pollution.