STContext: A Multifaceted Dataset for Developing Context-aware Spatio-temporal Crowd Mobility Prediction Models

2025-01-07

AI Summary

Existing spatiotemporal crowd flow prediction (STCFP) studies suffer from incomplete contextual feature coverage and inconsistent modeling paradigms, leading to poor model comparability and limited robustness. To address these issues, this work introduces STContext—the first comprehensive, multi-scenario benchmark dataset for STCFP—featuring five prediction tasks, nine diverse geographic regions, and ten heterogeneous contextual features (e.g., weather, AQI, POIs, road networks). We propose the first standardized workflow for contextual feature fusion: feature transformation → dependency modeling → representation fusion → training strategy—and establish a principled contextual modeling paradigm with empirically grounded guidelines for STCFP. Leveraging graph neural networks and multi-source data alignment techniques, we systematically evaluate multiple fusion strategies, distill key practical principles, and demonstrate significant improvements in prediction accuracy, robustness, and interpretability across diverse settings.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Feature Construction/Reformulation
• Humans and AI: Crowd Sourcing and Human Computation

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services

Abstract

In smart cities, context-aware spatio-temporal crowd flow prediction (STCFP) models leverage contextual features (e.g., weather) to identify unusual crowd mobility patterns and enhance prediction accuracy. However, the best practice for incorporating contextual features remains unclear due to inconsistent usage of contextual features in different papers. Developing a multifaceted dataset with rich types of contextual features and STCFP scenarios is crucial for establishing a principled context modeling paradigm. Existing open crowd flow datasets lack an adequate range of contextual features, which poses an urgent requirement to build a multifaceted dataset to fill these research gaps. To this end, we create STContext, a multifaceted dataset for developing context-aware STCFP models. Specifically, STContext provides nine spatio-temporal datasets across five STCFP scenarios and includes ten contextual features, including weather, air quality index, holidays, points of interest, road networks, etc. Besides, we propose a unified workflow for incorporating contextual features into deep STCFP methods, with steps including feature transformation, dependency modeling, representation fusion, and training strategies. Through extensive experiments, we have obtained several useful guidelines for effective context modeling and insights for future research. The STContext is open-sourced at https://github.com/Liyue-Chen/STContext.

Problem

• STCFP Model Optimization
• External Conditions Inconsistency
• Data Set Limitations

Innovation

• STContext dataset
• context-aware STCFP model
• deep learning integration