Investigation on Leveraging Optimal Machine Learning Models for Air Quality Assessment to Promote Environmental Health and Sustainability

Air Quality is of paramount importance since it directly impact on the welfare of individuals, environmental sustainability, along with their general wellness. Poor air quality, characterized by high levels of pollutants, contributes to respiratory diseases, cardiovascular issues, and other health concerns. Additionally, it impacts ecosystems, climate patterns, and visibility. Monitoring and maintaining good air quality are crucial for safeguarding public health, preserving the environment, and fostering sustainable living conditions for present and future generations. Machine learning models are crucial for finding air quality as they offer advanced tools to analyze complex datasets, model intricate relationships, and enhance prediction accuracy with a specific emphasis on Extreme Gradient Boosting (XGBoost) an efficient gradient algorithm renowned for handling complex datasets. Additionally, the research investigates attribute selection methods to identify influential features impacting air quality. The proposed approach ensures the identification of key attributes that significantly contribute to the accuracy of air quality predictions, thereby enhancing the sophistication and focus of the modelling process. The proposed methodology involves obtaining and preparing data from an open-source dataset, followed by meticulous curation, classification, and analysis using machine learning models. The robust capability of XGBoost to capture intricate relationships within air quality data, evidenced by its high accuracy, underscores its reliability as a predictive model for real-world air quality forecasting.