Uncertainty Quantification of Sparse Travel Demand Prediction with Spatial-Temporal Graph Neural Networks
This addresses uncertainty quantification for sparse travel demand prediction in transportation, which is an incremental improvement over existing spatial-temporal deep learning models.
The paper tackled the problem of uncertainty and sparsity in fine-grained Origin-Destination travel demand prediction by designing a Spatial-Temporal Zero-Inflated Negative Binomial Graph Neural Network (STZINB-GNN), which demonstrated superiority over benchmark models with high accuracy, tight confidence intervals, and interpretable parameters on two real-world datasets.
Origin-Destination (O-D) travel demand prediction is a fundamental challenge in transportation. Recently, spatial-temporal deep learning models demonstrate the tremendous potential to enhance prediction accuracy. However, few studies tackled the uncertainty and sparsity issues in fine-grained O-D matrices. This presents a serious problem, because a vast number of zeros deviate from the Gaussian assumption underlying the deterministic deep learning models. To address this issue, we design a Spatial-Temporal Zero-Inflated Negative Binomial Graph Neural Network (STZINB-GNN) to quantify the uncertainty of the sparse travel demand. It analyzes spatial and temporal correlations using diffusion and temporal convolution networks, which are then fused to parameterize the probabilistic distributions of travel demand. The STZINB-GNN is examined using two real-world datasets with various spatial and temporal resolutions. The results demonstrate the superiority of STZINB-GNN over benchmark models, especially under high spatial-temporal resolutions, because of its high accuracy, tight confidence intervals, and interpretable parameters. The sparsity parameter of the STZINB-GNN has physical interpretation for various transportation applications.