GeoFlow通过地理信息增强区域表示，提升跨区域流量预测与生成效果。
GeoFlow: Geo-Aware Modeling of Inter-Area Relationships in Origin-Destination Flow Prediction and Generation
- 融合相对位置、多跳距离等地理特征，增强区域表征
- 使用几何-内在融合编码器，准确捕捉长程依赖关系
- 适合城市规划与交通分析，提升生成样本真实度
起止点（OD）流量建模支撑城市规划与出行分析，但现有图模型常忽略关键地理属性，难以建模远距离及多区域依赖。本文提出GeoFlow框架：(i) 通过相对位置、k跳距离和测地线距离等地理特征增强区域表征；(ii) 设计几何-内在融合编码器，结合图注意力捕捉区域内部信号与坐标感知编码器建模全局结构；(iii) 采用轴向-全局注意力解码器，捕获OD间的竞争性依赖。针对流量生成，与流匹配模型结合，生成更真实多样出行样本。实验表明，GeoFlow在预测精度上表现更优，同时显著提升生成样本的保真度与多样性。消融与分析验证各模块有效性。代码已开源：https://github.com/ZheruiHuang/GeoFlow。
原文摘要 · Abstract (English)
Origin-destination (OD) flow modeling underpins urban planning and mobility analysis, but prevailing graph-based methods often neglect salient geographic attributes, limiting their ability to model long-range and multi-area dependencies. In this paper, we introduce GeoFlow, a novel framework that (i) augments area representations with geospatial attributes, including relative positions, k-hop and geodesic distances, (ii) employs a specialized geometric-intrinsic fusion encoder design that combines graph attention for intrinsic area signals with coordinate-aware encoders for global structure, and (iii) adopts an axial-global attention decoder to capture OD-specific competitive dependencies. For OD flow generation, GeoFlow is paired with flow matching models to produce more authentic and diverse mobility samples. Empirically, GeoFlow achieves superior performance in predictive accuracy, while substantially improving generative fidelity and diversity. Ablation and analytical studies confirm the contribution of each component. Code is available at https://github.com/ZheruiHuang/GeoFlow.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。