Abstract
Air pollution monitoring and modeling are the most important focus of climate and environment decision-making organizations. The development of new methods for air quality prediction is one of the best strategies for understanding weather contamination. In this research, different air quality parameters were forecasted, including Carbon Monoxide (CO), Nitrogen Monoxide (NO), Nitrogen Dioxide (NO(2)), Ozone (O(3)), Sulphur Dioxide (SO(2)), Fine Particles Matter (PM(2.5)), Coarse Particles Matter (PM(10)), and Ammonia (NH(3)). Hourly datasets were collected for air quality monitoring stations near Delhi, India, from November 25, 2020 to January 24, 2023. In this context, five intelligent models were developed, including Long Short-Term Memory (LSTM), Bidirectional Long-Short Term Memory (Bi-LSTM), Gated Recurrent Unit (GRU), Multilayer Perceptron (MLP), and Extreme Gradient Boosting (XGBoost). The modelling results revealed that Bi-LSTM model had the best predictability performance for forecasting CO with (R(2) = 0.979), NO with (R(2) = 0.961), NO(2) with (R(2) = 0.956), SO(2) with (R(2) = 0.955), PM(10) with (R(2) = 0.9751) and NH(3) with (R(2) = 0.971). Meanwhile, GRU and LSTM models performed better in forecasting O(3) and PM(2.5) with (R(2) = 0.9624) and (R(2) = 0.973), respectively. The current research provides illuminating visuals highlighting the potential of deep learning to comprehend air quality modeling, enabling improved environmental decisions.