大规模城市交通延迟预测：一种系统方法，结合多分辨率特征工程与深度学习
Scalable Transit Delay Prediction at City Scale: A Systematic Approach with Multi-Resolution Feature Engineering and Deep Learning
AI总结：
本文提出了一种城市级交通延迟预测方法，结合多分辨率特征工程和深度学习，通过自适应PCA降维和混合聚类技术，实现高效、可扩展的预测系统，适用于实时大规模部署。
摘要：
城市公交运输部门需要可靠的、覆盖整个网络的延迟预测，以向乘客提供准确的到达信息，并支持实时运营控制。准确的预测有助于乘客规划行程、减少等待时间，并允许运营人员调整发车间隔、调度额外车辆和管理中断。尽管实时数据如GTFS-实时（GTFS-RT）现在已广泛可用，但大多数现有延迟预测系统只能处理少数路线，依赖手工特征，并且很少提供如何设计可扩展、可重用架构的指导。我们提出了一种城市级预测流水线，结合多分辨率特征工程、降维和深度学习。该框架通过探索23种聚合组合在H3单元、路线、路段和时间模式上生成1,683个时空特征，并使用自适应PCA将其压缩为83个组件，同时保留95%的方差。为了避免密集城区落入单一H3区域导致的“巨团问题”，我们引入了一种混合H3+拓扑聚类方法，产生12个平衡的路线集群（变异系数0.608），并实现了高效的分布式训练。我们比较了五种模型架构在蒙特利尔市STM网络六个月内公交运营数据上的表现。一个具有集群意识的全局LSTM在准确性和效率之间取得了最佳平衡，优于Transformer模型，性能提升18至52%，同时参数数量减少275倍。我们还报告了多级评估，包括基本路段、路段和行程级别，并通过走步验证和延迟分析，证明所提出的流水线适用于实时、城市级部署，并可重用于其他网络，只需有限的调整。
英文摘要：
Urban bus transit agencies need reliable, network-wide delay predictions to provide accurate arrival information to passengers and support real-time operational control. Accurate predictions help passengers plan their trips, reduce waiting time, and allow operations staff to adjust headways, dispatch extra vehicles, and manage disruptions. Although real-time feeds such as GTFS-Realtime (GTFS-RT) are now widely available, most existing delay prediction systems handle only a few routes, depend on hand-crafted features, and offer little guidance on how to design a scalable, reusable architecture. We present a city-scale prediction pipeline that combines multi-resolution feature engineering, dimensionality reduction, and deep learning. The framework generates 1,683 spatiotemporal features by exploring 23 aggregation combinations over H3 cells, routes, segments, and temporal patterns, and compresses them into 83 components using Adaptive PCA while preserving 95% of the variance. To avoid the "giant cluster" problem that occurs when dense urban areas fall into a single H3 region, we introduce a hybrid H3+topology clustering method that yields 12 balanced route clusters (coefficient of variation 0.608) and enables efficient distributed training. We compare five model architectures on six months of bus operations from the Société de transport de Montréal (STM) network in Montréal. A global LSTM with cluster-aware features achieves the best trade-off between accuracy and efficiency, outperforming transformer models by 18 to 52% while using 275 times fewer parameters. We also report multi-level evaluation at the elementary segment, segment, and trip level with walk-forward validation and latency analysis, showing that the proposed pipeline is suitable for real-time, city-scale deployment and can be reused for other networks with limited adaptation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
