Air Quality Prediction Model Based on Spatio-temporal Graph Convolution Neural Networks

With the rapidly development of economy and technology, the problem of air pollution is becoming more and more serious. A large number of studies show that air pollution not only causes huge economic losses, but also seriously endangers human life and health. Therefore, the control and prevention of air pollution has become very important, and air quality prediction is an important part of the control and prevention. In the era of big data, prediction models based on deep learning show superior performance in the field of air quality prediction. In this paper, the prediction model based on Spatio-Temporal Graph Convolutional Neural Networks(STGCN) is used to predict the air quality. The prediction results show that the Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) of the Spatio-Temporal Graph Convolutional Neural Networks(STGCN) model are better than the traditional algorithm models such as RNN,LSTM,LSVR,GRU and ARIMA.