A Hybrid Decision-Tree and ANN Learning Model for Air Contamination Forecasting

Development of urban intelligent cities introduces a severe rise in environmental pollution, ranging from air and water pollution to noise pollution. Explicitly, the upsurge in deforestation, industrialization, production, and automobile activities presents increased air pollution. To recommend a suitable preventive method, a proper forecasting model is required. Presently, (ML) machine learning methods aid intelligent data evaluation and are employed in many domains. This study examines the forecasting of air contamination employing distinct ML methods. A hybrid decision-tree and (ANN) artificial neural network model is recommended for proper gauging. The analyses reports reveal that the suggested model outclasses other classical algorithms in terms of accuracy. Precisely, the presented model realized 99% and 99.88% accuracy and precision, with 99% and 99.88% sensitivity and specificity.