A Single-Factor Prediction Method for Air Quality Pollution Based on Neural Network

In recent years, with rapid societal development, the issue of air pollution has become increasingly significant, especially with PM2.5 particles posing a serious threat to human health. This study introduces a novel air quality prediction model based on neural networks-AR-LSTM, which incorporates advanced artificial intelligence technologies such as Residual Networks (ResNet), Graph Convolutional Networks (GCN), attention mechanisms, and Long Short-Term Memory networks (LSTM). This model effectively captures the spatiotemporal dependencies of air pollutant concentrations, thereby predicting the PM2.5 levels for the next 24 hours. By analyzing the air quality data from Shenyang, the AR-LSTM model demonstrated superior predictive accuracy and robustness compared to traditional machine learning models and other deep learning models. The results of this study not only verify the effectiveness of the model but also provide a scientific basis for air quality management and policy-making in the field of environmental science