Multi-site air quality prediction based on graph convolutional neural network-bi-directional LSTM model

To address the current problem of single-site prediction and inadequate extraction of spatial features for PM2.5 hourly concentration prediction, a graphical convolutional neural network (GCN) is proposed to obtain the spatial correlation between PM2.5 monitoring stations in Beijing by considering the features of time series in time and space, and assign weights according to the distance between stations to abstract into an undirected topological map. The missing data sequences are complemented by using a long and short-term memory network to extract temporal features on the time-series dataset, which are normalized and then fused with the components extracted by the GCN to make predictions. The experimental results show that GCN-BiLSTM has higher prediction accuracy and better results than single RNN, LSTM, and BiLSTM algorithms.