Applied Research on AQI Prediction Based on BP Neural Network Modeling

Abstract

In recent years, air environment quality has become a hot issue of concern for people all over the world, and the prediction of air quality is of great significance for air pollution prevention and control. There is mainly a nonlinear relationship between air quality data and influencing factors, and BP neural network has a strong nonlinear mapping ability, which can fit the more complex nonlinear mapping relationship. Based on this, this paper utilizes BP neural networks to establish an air quality index AQI prediction model to predict the AQI in Nanjing, with an average relative error of about 1% and a prediction accuracy of 99%. The establishment of this model can provide reliable reference and decision-making basis for government departments and citizens.