Prediction of AQI for Urban Metropolis Using MLSTM-GRU Model

Air pollution is caused by the existence of detrimental substances in atmosphere, which poses serious risks to both the environment and human health. Particulate matter, nitrogen oxide, sulphur dioxide, ozone, and volatile organic compounds are just a few of the contaminants in the air that have an adverse effect on air quality, climate change and various health problems. This study seeks to predict Air Quality Index (AQI) of Kolkata, a rising metropolis with substantial air pollution issues. In order to accomplish this, air quality data of various stations of Kolkata were collected and preprocessed accordingly. The preprocessed dataset was then used to train the prediction model. A Modified LSTM-GRU (MLSTM-GRU) model is proposed in this work and the experimental results demonstrated that the MLSTM-GRU model outperformed the other deep learning models by achieving superior result in terms of Mean Squared Error (MSE), Root Mean Squared Error (RMSE) and R-Squared ( \(\text {R}^2\) ) values. The findings of this study have significant consequences for methods used to regulate air quality.