Enhancing Air Quality Monitoring with Machine Learning: Case Study in Delhi and Gurugram

The Air Quality Index (AQI) is a measure employed to evaluate the impact of air contamination on person's well-being within a short timeframe. It aims to inform the community about the detrimental physical conditions and consequences of local air contamination. The quantities of atmosphere contamination in Indian metropolitan areas (especially Delhi and NCR) have markedly risen, prompting various approaches to devise a mathematical formula for calculating the AQI. However, with the advancements in machine learning (ML), researchers have used ML techniques to establish a correlation between vulnerability to air contamination and negative health consequences among the population. This study uses different models to forecast AQI for the Delhi and Gurugram regions. The experimental research is conducted using traditional ML approaches such as Linear Regression and random Forest, and advanced ML techniques such as Deep Neural Networks (DNNs), Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM), and Liquid Neural Networks (LNNs). The research examines current developments in time series forecasting techniques, going beyond accepted methods. Comparative analysis, which assesses each technique's performance under various circumstances, is at the core of this study. Considerations include robustness to various data properties, interpretability, and computational efficiency. The results help practitioners choose the best method for a definite set of time series data.