一种用于交通预测的自适应时空图神经网络

raffic forecasting is of great significance in urban management and traffic planning. However, in the task of trafficprediction, the modeling of complex dynamic spatio-temporal dependence is still a great challenge. For the problem thatthe neural network can't capture the long-term traffic information in the spatial dimension, the new neural network structureproposed in the past can't capture the complex traffic data in the spatial dimension. Through adaptive graph convolutionalnetwork, the specific state of nodes is automatically captured and the interdependence between different nodes is automaticallyinferred to extract the complete spatial features of traffic data. Then, the time characteristics of traffic data are capturedby the time memory module in the spatio-temporal short-term memory network, and the short, medium and long-term timedependence is simulated.