SMOTEDNN: A Novel Model for Air Pollution Forecasting and AQI Classification

Rapid industrialization and urbanization are rapidly deteriorating ambient air quality, especially in the developing nations. Air pollutants impose a high risk on human health degrade environment as well. Earlier studies have used machine learning (ML) statistical modeling to classify forecast pollution. However, these methods suffer from complexity of pollution dataset resulting lack efficient classification forecasting ML-based models improper data pre-processing, class imbalance issues, splitting, hyperparameter tuning. There is gap existing due handling optimization. The present investigation aims bridge gaps aid effective forecasting. Five ML were developed, including one novel model named SMOTEDNN (Synthetic Minority Oversampling Technique with Deep Neural Network) address classification. All five utilized pre-processing rigorous Three developed for step-index based autoregression. showed higher accuracy. Significantly, achieved an accuracy (99.90%) than other current previous studies.