Generating Synthetic Mobility Networks with Generative Adversarial Networks

TL;DR

This paper introduces MoGAN, a GAN-based model that generates realistic synthetic urban mobility networks, outperforming traditional models and useful for data augmentation and simulation purposes.

Contribution

The paper presents MoGAN, a novel GAN-based approach for generating realistic mobility networks, improving over classical models in realism and applicability.

Findings

MoGAN outperforms Gravity and Radiation models in realism.

MoGAN effectively generates synthetic mobility networks for various datasets.

The model is useful for data augmentation and simulation tasks.

Abstract

The increasingly crucial role of human displacements in complex societal phenomena, such as traffic congestion, segregation, and the diffusion of epidemics, is attracting the interest of scientists from several disciplines. In this article, we address mobility network generation, i.e., generating a city's entire mobility network, a weighted directed graph in which nodes are geographic locations and weighted edges represent people's movements between those locations, thus describing the entire mobility set flows within a city. Our solution is MoGAN, a model based on Generative Adversarial Networks (GANs) to generate realistic mobility networks. We conduct extensive experiments on public datasets of bike and taxi rides to show that MoGAN outperforms the classical Gravity and Radiation models regarding the realism of the generated networks. Our model can be used for data augmentation and performing simulations and what-if analysis.