🤖 AI Summary
To address the challenges of complex patterns and poor interpretability in forecasting nonstationary spatiotemporal traffic data, this paper proposes a VMD-GCN hybrid framework. First, Variational Mode Decomposition (VMD) adaptively disentangles the raw traffic series into intrinsic mode components, with the number of modes dynamically optimized via reconstruction loss. Subsequently, a mode-aware graph convolutional network (GCN) is designed to jointly model spatiotemporal features for each component and enable end-to-end prediction. This work establishes the first integrated modeling paradigm combining VMD and GCN, and—uniquely—reveals the distinct contributions of individual modes to short-term versus long-term forecasting as well as bandwidth-constrained inference. Evaluated on the LargeST benchmark, the method surpasses state-of-the-art approaches on both short- and long-horizon traffic flow prediction tasks, while significantly enhancing model robustness and physical interpretability.
📝 Abstract
This paper focuses on spatiotemporal (ST) traffic prediction using graph neural networks. Given that ST data consists of non-stationary and complex time events, interpreting and predicting such trends is comparatively complicated. Representation of ST data in modes helps us to infer behavior and assess the impact of noise on prediction applications. We propose a framework that decomposes ST data into modes using the variational mode decomposition (VMD) method, which is then fed into the neural network for forecasting future states. This hybrid approach is known as a variational mode graph convolutional network (VMGCN). Instead of exhaustively searching for the number of modes, they are determined using the reconstruction loss from the real-time application data. We also study the significance of each mode and the impact of bandwidth constraints on different horizon predictions in traffic flow data. We evaluate the performance of our proposed network on the LargeST dataset for both short and long-term predictions. Our framework yields better results compared to state-of-the-art methods.