Timely and accurate traffic prediction is crucial
for public safety and rational allocation of resources such as
roads. However, it still remains an open challenge for timely
accurate traffic forecasting, due to the highly nonlinear temporal
correlation and dynamical spatial dependence of traffic data. In
order to fully capture the temporal and spatial dependences, we
propose a dual-channel spatio-temporal wavelet transform graph
neural network (DSTwave) for traffic forecasting. Specifically, the
wavelet transform neural network is used to obtain the low- and
high-frequency parts from the original traffic sequence signals,
and in order to accurately capture the spatio-temporal dependence
of the low- and high-frequency components in the longand
short-term patterns, the dual-channel ST-GCN with trendseasonal
feature decomposition is carefully designed. In addition,
Dynamic-adaptive adjacency matrix is introduced, which can
flexibly adapt to changing data. A large number of experiments
on two real datasets show that the proposed model has high
prediction accuracy.