GeoFlow: Geo-Aware Modeling of Inter-Area Relationships in Origin-Destination Flow Prediction and Generation
2026-07-06 • Machine Learning
Machine Learning
AI summaryⓘ
The authors developed GeoFlow, a new method to better predict and simulate how people move between different areas in a city. Unlike older methods, GeoFlow includes geographic details like locations and distances to understand movement over long distances and across multiple regions. It uses special layers in its model to combine local area information with overall city layout, making predictions more accurate and realistic. Tests show GeoFlow works better than previous methods at both predicting flows and generating diverse movement patterns.
Origin-Destination FlowUrban MobilityGraph AttentionGeospatial AttributesGeodesic DistanceFlow MatchingAxial-Global AttentionGenerative Models
Authors
Zherui Huang, Guanjie Zheng, Hao Xue, Linghe Kong
Abstract
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.