Weng et al., "Beyond Distance: Mobility Neural Embeddings Reveal Visible and Invisible Barriers in Urban Space" (2025)

Guangyuan Weng, Minsuk Kim, Yong-Yeol Ahn, and Esteban Moro, Submitted (2025)
arXiv | Code

@article{weng2025beyond,
    author = {Guangyuan Weng and Minsuk Kim and Yong-Yeol Ahn and Esteban Moro},
    title = {Beyond Distance: Mobility Neural Embeddings Reveal Visible and Invisible Barriers in Urban Space},
    year = {2025},
    eprint = {2506.24061},
    archivePrefix = {arXiv},
    primaryClass = {cs.CY},
}

Human mobility in cities is shaped not only by visible structures such as highways, rivers, and parks but also by invisible barriers rooted in socioeconomic segregation, uneven access to amenities, and administrative divisions. Using neural embedding models on 25.4 million trajectories across 11 major U.S. cities, we reveal a functional distance between places that reflects behavioral rather than physical proximity. Amenity access, administrative borders, and income/racial segregation are the strongest predictors of behavioral barriers, and these invisible divisions concentrate in urban cores and persist across time and scale.