Technology Category
Planning, Routing, and Scheduling: Optimization of Spatio-temporal SystemsMachine Learning: Multimodal LearningComputer Vision: Multi-modal Vision
MCST-Mamba: Multivariate Mamba-Based Model for Traffic Prediction
🤖 AI Summary
Traffic forecasting faces challenges including dynamic road conditions, heterogeneous external disturbances, and strong couplings among multivariate traffic signals (e.g., speed, flow, occupancy), rendering existing methods inadequate for jointly modeling cross-channel spatiotemporal dependencies. To address this, we propose the first Mamba-based architecture tailored for multivariate traffic forecasting. Our method decouples spatiotemporal modeling from adaptive embedding, employing a dual-branch Mamba structure: one branch captures temporal evolution of time series, while the other encodes spatial correlations among sensors. Additionally, we introduce a channel-aware adaptive embedding mechanism to explicitly model dynamic inter-variable dependencies. Evaluated on multiple real-world datasets, our model achieves state-of-the-art performance in multi-step joint forecasting—outperforming mainstream baselines with significantly fewer parameters—demonstrating superior efficiency, expressive power, and scalability.
Technology Category
Application Category
📝 Abstract
Accurate traffic prediction plays a vital role in intelligent transportation systems by enabling efficient routing, congestion mitigation, and proactive traffic control. However, forecasting is challenging due to the combined effects of dynamic road conditions, varying traffic patterns across different locations, and external influences such as weather and accidents. Traffic data often consists of several interrelated measurements - such as speed, flow and occupancy - yet many deep-learning approaches either predict only one of these variables or require a separate model for each. This limits their ability to capture joint patterns across channels. To address this, we introduce the Multi-Channel Spatio-Temporal (MCST) Mamba model, a forecasting framework built on the Mamba selective state-space architecture that natively handles multivariate inputs and simultaneously models all traffic features. The proposed MCST-Mamba model integrates adaptive spatio-temporal embeddings and separates the modeling of temporal sequences and spatial sensor interactions into two dedicated Mamba blocks, improving representation learning. Unlike prior methods that evaluate on a single channel, we assess MCST-Mamba across all traffic features at once, aligning more closely with how congestion arises in practice. Our results show that MCST-Mamba achieves strong predictive performance with a lower parameter count compared to baseline models.
Problem
Research questions and friction points this paper is trying to address.
Predicting multiple interrelated traffic variables simultaneously
Handling dynamic road conditions and external influences
Capturing joint spatio-temporal patterns in traffic data
Innovation
Methods, ideas, or system contributions that make the work stand out.
Multivariate Mamba model for traffic prediction
Adaptive spatio-temporal embeddings integration
Dedicated Mamba blocks for spatio-temporal modeling
🔎 Similar Papers
No similar papers found.
