FloGAN: Scenario-Based Urban Mobility Flow Generation via Conditional GANs and Dynamic Region Decoupling

2025-07-16

AI Summary

Existing travel flow generation models either over-rely on historical trajectories while neglecting the dynamic evolution of land use and population density, or adopt static mechanistic assumptions that hinder prediction in future scenarios lacking historical data. To address this, we propose a conditional generative adversarial network (cGAN) framework tailored for future urban settings. Our approach innovatively incorporates a dynamic regional disentanglement mechanism and land-use prototype encoding, integrated with an adaptive regional partitioning strategy to explicitly model multi-dimensional dynamic features—including region size, functional type, and spatiotemporal heterogeneity. The method requires neither extensive calibration data nor complex behavioral assumptions, and supports rapid origin-destination (OD) flow generation at user-specified spatial granularities. Experiments on Singaporean mobile signaling data demonstrate consistent and significant improvements over state-of-the-art generative models across multiple spatial resolutions, offering an efficient and robust generative solution for future transportation demand forecasting.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Planning, Routing, and Scheduling: Planning with Language Models
• Natural Language Processing: Generation

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

The mobility patterns of people in cities evolve alongside changes in land use and population. This makes it crucial for urban planners to simulate and analyze human mobility patterns for purposes such as transportation optimization and sustainable urban development. Existing generative models borrowed from machine learning rely heavily on historical trajectories and often overlook evolving factors like changes in population density and land use. Mechanistic approaches incorporate population density and facility distribution but assume static scenarios, limiting their utility for future projections where historical data for calibration is unavailable. This study introduces a novel, data-driven approach for generating origin-destination mobility flows tailored to simulated urban scenarios. Our method leverages adaptive factors such as dynamic region sizes and land use archetypes, and it utilizes conditional generative adversarial networks (cGANs) to blend historical data with these adaptive parameters. The approach facilitates rapid mobility flow generation with adjustable spatial granularity based on regions of interest, without requiring extensive calibration data or complex behavior modeling. The promising performance of our approach is demonstrated by its application to mobile phone data from Singapore, and by its comparison with existing methods.

Problem

• Generates urban mobility flows for simulated scenarios
• Incorporates dynamic factors like land use changes
• Reduces reliance on historical calibration data

Innovation

• Uses conditional GANs for mobility flow generation
• Incorporates dynamic region sizes and land use
• Adjusts spatial granularity without complex modeling