BIGCity: A Universal Spatiotemporal Model for Unified Trajectory and Traffic State Data Analysis
Xie Yu, Jingyuan Wang, Yifan Yang, Qian Huang, Ke Qu
TL;DR
BIGCity presents a true multi-task, multi-data modality spatiotemporal foundation model by unifying trajectories and traffic states through ST-units and a spatiotemporal tokenizer. A task-oriented prompt framework (VMTP) guides a tunable LLM backbone (LoRA-enhanced GPT-2) to perform diverse tasks without task-specific fine-tuning, trained via Masked Reconstruction and Prompt Tuning. Across three real-city datasets, BIGCity achieves state-of-the-art performance on 8 tasks and demonstrates robust cross-city generalization and scalability. This framework enables joint analysis of micro- and macro-mobility patterns with broad applicability to smart-city analytics and navigation services.
Abstract
Typical dynamic ST data includes trajectory data (representing individual-level mobility) and traffic state data (representing population-level mobility). Traditional studies often treat trajectory and traffic state data as distinct, independent modalities, each tailored to specific tasks within a single modality. However, real-world applications, such as navigation apps, require joint analysis of trajectory and traffic state data. Treating these data types as two separate domains can lead to suboptimal model performance. Although recent advances in ST data pre-training and ST foundation models aim to develop universal models for ST data analysis, most existing models are "multi-task, solo-data modality" (MTSM), meaning they can handle multiple tasks within either trajectory data or traffic state data, but not both simultaneously. To address this gap, this paper introduces BIGCity, the first multi-task, multi-data modality (MTMD) model for ST data analysis. The model targets two key challenges in designing an MTMD ST model: (1) unifying the representations of different ST data modalities, and (2) unifying heterogeneous ST analysis tasks. To overcome the first challenge, BIGCity introduces a novel ST-unit that represents both trajectories and traffic states in a unified format. Additionally, for the second challenge, BIGCity adopts a tunable large model with ST task-oriented prompt, enabling it to perform a range of heterogeneous tasks without the need for fine-tuning. Extensive experiments on real-world datasets demonstrate that BIGCity achieves state-of-the-art performance across 8 tasks, outperforming 18 baselines. To the best of our knowledge, BIGCity is the first model capable of handling both trajectories and traffic states for diverse heterogeneous tasks. Our code are available at https://github.com/bigscity/BIGCity