“…Therefore, the operation of ITS is heavily dependent on precise traffic prediction, the core of which is modeling spatial-temporal dynamics of traffic features. Recent years have witnessed a widespread application of graph convolutional network (GCN) for extracting spatial correlations, where the distribution of traffic sensors is modeled as a series of nodes and edges in a graph ( Bao et al, 2023 ; Kong et al, 2022 ; Chen et al, 2022 ; Huang et al, 2022 ). In addition, recurrent neural network (RNN) and its variants, also known as long short-term memory (LSTM) and gated recurrent unit (GRU) have been extensively applied to model temporal dependency due to their outstanding performance in processing time series ( Zhao et al, 2023 ; Ma et al, 2023 ; Afrin & Yodo, 2022 ; Ma, Dai & Zhou, 2022 ).…”