Satellites Reveal Mobility: A Commuting Origin-destination Flow Generator for Global Cities

TL;DR

This work tackles the challenge of obtaining commuting origin-destination flows by leveraging global public data. It introduces GlODGen, which combines region-level semantic features extracted from satellite imagery via Vision-Language Geo-Foundation Models with population data to represent urban regions, and then uses a graph denoising diffusion approach (WEDAN) to generate OD flows. Across 4 continents and 6 cities, GlODGen demonstrates that publicly available data can achieve near-parity with traditional, hard-to-obtain inputs and exhibits strong cross-continental transferability. The approach enables scalable, global OD-flow generation and is released as an open-source tool to support sustainable urban development research and planning.

Abstract

Commuting Origin-destination~(OD) flows, capturing daily population mobility of citizens, are vital for sustainable development across cities around the world. However, it is challenging to obtain the data due to the high cost of travel surveys and privacy concerns. Surprisingly, we find that satellite imagery, publicly available across the globe, contains rich urban semantic signals to support high-quality OD flow generation, with over 98\% expressiveness of traditional multisource hard-to-collect urban sociodemographic, economics, land use, and point of interest data. This inspires us to design a novel data generator, GlODGen, which can generate OD flow data for any cities of interest around the world. Specifically, GlODGen first leverages Vision-Language Geo-Foundation Models to extract urban semantic signals related to human mobility from satellite imagery. These features are then combined with population data to form region-level representations, which are used to generate OD flows via graph diffusion models. Extensive experiments on 4 continents and 6 representative cities show that GlODGen has great generalizability across diverse urban environments on different continents and can generate OD flow data for global cities highly consistent with real-world mobility data. We implement GlODGen as an automated tool, seamlessly integrating data acquisition and curation, urban semantic feature extraction, and OD flow generation together. It has been released at https://github.com/tsinghua-fib-lab/generate-od-pubtools.

Figures (8)

• Figure 1: An illustration of replacing the traditional hard-to-collect urban data by easily accessible global public data (e.g., satellite imagery and population data) in OD flow generation.
• Figure 2: Cases of satellite imagery for urban regions.
• Figure 3: The framework and data pipeline of GlODGen.
• Figure 4: Correlation analysis between generated OD flows and the flows extracted from diverse mobility-related data sources for typical urban areas around the world.
• Figure 5: Visualization of the generated and data-oriented OD flows in Beijing and Shanghai. The generated OD flows show high consistency with the data-oriented data in both cities, demonstrating the effectiveness of GlODGen in capturing real-world mobility patterns.

Theorems & Definitions (3)

• Definition 1
• Definition 2
• Definition 3