Air Quality Prediction Model Based on BP Neural Network and LSTM

This article uses monthly observation data from national level ground meteorological observation stations in Beijing from 2014 to 2022, and uses LSTM model and ARIMA time series model to predict the data of air quality index factor indicators. A BP neural network model is used to construct a prediction model for Beijing's air quality index. By comparing the predicted data of Air Quality Index (AQI) with the actual data, the accuracy of the model's predicted AQI in Beijing is over 95%, indicating a relatively accurate prediction accuracy. It can be used for predicting the air quality index in Beijing. Provide technical support for air quality and environmental governance in Beijing.