ST-CopulaGNN : A Multi-View Spatio-Temporal Graph Neural Network for Traffic Forecasting

Modern cities heavily rely on complex transportation, making accurate traffic speed prediction crucial for traffic management authorities. Classical methods, including statistical techniques and traditional machine learning techniques, fail to capture complex relationships, while deep learning approaches may have weaknesses such as error accumulation, difficulty in handling long sequences, and overlooking spatial correlations. Graph neural networks (GNNs) have shown promise in extracting spatial features from non-Euclidean graph structures, but they usually initialize the adjacency matrix based on distance and may fail to detect hidden statistical correlations. The choice of correlation measure can have a significant impact on the resulting adjacency matrix and the effectiveness of graph-based models. This paper proposes a novel approach for accurately forecasting traffic patterns by utilizing a multi-view spatio-temporal graph neural network that captures data from both realistic and statistical domains. Unlike traditional correlation measures such as Pearson correlation, copula models are utilized to extract hidden statistical correlations and construct multivariate distribution functions to obtain the correlation relationship among traffic nodes. A two-step approach is adopted, which involves selecting and testing different types of bivariate copulas to identify the ones that best fit the traffic data, and utilizing these copulas to create multi-weight adjacency matrices. The second step involves utilizing a graph convolutional network to extract spatial information and capturing temporal trends using dilated causal convolutions. The proposed ST-CopulaGNN model outperforms other models in spatio-temporal traffic forecasting that solely rely on distance-based adjacency matrices, such as DCRNN and Graph WaveNet. It also achieves the lowest MAE for 30 and 60 minutes ahead and the lowest MAPE for 15 minutes ahead on the PEMS-BAY dataset. The model incorporates copulas, and the study explores copula function selection and the impact of using paired time-series with a time lag. The findings suggest that using copula-based adjacency matrix configurations, particularly those including Clayton and Gumbel copulas, can enhance traffic forecasting accuracy.