Developing the Optimal Hybrid Neural Network for Predicting the Factor of Air Pollutants

Abstract

Urban air pollution can be reduced via precise air pollutant forecasts.For that, the air quality index (AQI) quantifies air quality.In this manner, accurate and trustworthy air quality index (AQI) estimates are essential for preserving the natural environment and the general population's health. Using the backpropagation (BP) algorithm, this study describes a method for enhancing the performance of neural networks. Using a network optimized with natural swarm intelligence, a novel optimal-hybrid model approachto Nature Swarm Intelligence (NSI), predicting the Air Quality Index (AQI), is possible. This NSI comprises the optimization algorithms Dove Swarm optimization (DSA) and Bat Algorithm (BA), which aim to optimize the weight of the Backpropagation neural network (BPNN) to promote the air quality prediction. The constructed optimal-hybrid modelcaptured the characteristics of the AQI series and produced a more accurate AQI forecast according to exhaustive comparisons using a set of evaluation indicators. Experiments conducted verify the proposed modelis validfor application when attempting to forecast the AQI. This is because it receives a high RMSE, MAPE, Error Absolute total, and Accuracy value from the simulation. This is because the simulation results suggest that the network model could be a good option for actualization, which is why this is the case.