Commute Networks as a Signature of Urban Socioeconomic
Performance: Evaluating Mobility Structures with Deep Learning
Models

J 2025

Commute Networks as a Signature of Urban Socioeconomic Performance: Evaluating Mobility Structures with Deep Learning Models

KHULBE, Devashish; Aliaksandr BELY a Stanislav SOBOLEVSKIJ

Základní údaje

Originální název

Commute Networks as a Signature of Urban Socioeconomic Performance: Evaluating Mobility Structures with Deep Learning Models

Autoři

KHULBE, Devashish; Aliaksandr BELY a Stanislav SOBOLEVSKIJ

Vydání

Smart Cities, MDPI, 2025, 2624-6511

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

10100 1.1 Mathematics

Stát vydavatele

Švýcarsko

Utajení

není předmětem státního či obchodního tajemství

Odkazy

URL, URL

Impakt faktor

Impact factor: 5.500 v roce 2024

Označené pro přenos do RIV

Ano

Kód RIV

RIV/00216224:14310/25:00141726

Organizační jednotka

Přírodovědecká fakulta

Klíčová slova anglicky

Graph Neural Networks; socioeconomic modeling; urban mobility

Štítky

14311010, rivok

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 13. 1. 2026 13:59, Mgr. Marie Novosadová Šípková, DiS.

Anotace

V originále

Urban socioeconomic modeling has predominantly concentrated on extensive location and neighborhood-based features, relying on the localized population footprint. However, networks in urban systems are common, and many urban modeling methods do not account for network-based effects. Additionally, network-based research has explored a multitude of data from urban landscapes. However, achieving a comprehensive understanding of urban mobility proves challenging without exhaustive datasets. In this study, we propose using commute information records from the census as a reliable and comprehensive source to construct mobility networks across cities. Leveraging deep learning architectures, we employ these commute networks across U.S. metro areas for socioeconomic modeling. We show that mobility network structures provide significant predictive performance without considering any node features. Consequently, we use mobility networks to present a supervised learning framework to model a city’s socioeconomic indicator directly, combining Graph Neural Network and Vanilla Neural Network models to learn all parameters in a single learning pipeline. In experiments in 12 major U.S. cities, the proposed model achieves considerable explanatory performance and is able to outperform previous conventional machine learning models based on extensive regional-level features. Providing researchers with methods to incorporate network effects in urban modeling, this work also informs stakeholders of wider network-based effects in urban policymaking and planning.

Návaznosti

MUNI/J/0008/2021, interní kód MU

Název: Digital City

Investor: Masarykova univerzita, Digital City, MASH JUNIOR - MUNI Award In Science and Humanities JUNIOR

Citovat

KHULBE, Devashish; Aliaksandr BELY a Stanislav SOBOLEVSKIJ. Commute Networks as a Signature of Urban Socioeconomic Performance: Evaluating Mobility Structures with Deep Learning Models. Smart Cities. MDPI, 2025, roč. 8, č. 4, s. 1-22. ISSN 2624-6511. Dostupné z: https://doi.org/10.3390/smartcities8040125.

@article{2511259,
   author = {Khulbe, Devashish and Bely, Aliaksandr and Sobolevskij, Stanislav},
   article_number = {4},
   doi = {https://doi.org/10.3390/smartcities8040125},
   keywords = {Graph Neural Networks; socioeconomic modeling; urban mobility},
   language = {eng},
   issn = {2624-6511},
   journal = {Smart Cities},
   title = {Commute Networks as a Signature of Urban Socioeconomic Performance: Evaluating Mobility Structures with Deep Learning Models},
   url = {https://doi.org/10.5281/zenodo.11494208},
   volume = {8},
   year = {2025}
}

TY  - JOUR
ID  - 2511259
AU  - Khulbe, Devashish - Bely, Aliaksandr - Sobolevskij, Stanislav
PY  - 2025
TI  - Commute Networks as a Signature of Urban Socioeconomic Performance: Evaluating Mobility Structures with Deep Learning Models
JF  - Smart Cities
VL  - 8
IS  - 4
SP  - 1-22
EP  - 1-22
PB  - MDPI
SN  - 26246511
KW  - Graph Neural Networks
KW  - socioeconomic modeling
KW  - urban mobility
UR  - https://doi.org/10.5281/zenodo.11494208
N2  - Urban socioeconomic modeling has predominantly concentrated on extensive location and neighborhood-based features, relying on the localized population footprint. However, networks in urban systems are common, and many urban modeling methods do not account for network-based effects. Additionally, network-based research has explored a multitude of data from urban landscapes. However, achieving a comprehensive understanding of urban mobility proves challenging without exhaustive datasets. In this study, we propose using commute information records from the census as a reliable and comprehensive source to construct mobility networks across cities. Leveraging deep learning architectures, we employ these commute networks across U.S. metro areas for socioeconomic modeling. We show that mobility network structures provide significant predictive performance without considering any node features. Consequently, we use mobility networks to present a supervised learning framework to model a city’s socioeconomic indicator directly, combining Graph Neural Network and Vanilla Neural Network models to learn all parameters in a single learning pipeline. In experiments in 12 major U.S. cities, the proposed model achieves considerable explanatory performance and is able to outperform previous conventional machine learning models based on extensive regional-level features. Providing researchers with methods to incorporate network effects in urban modeling, this work also informs stakeholders of wider network-based effects in urban policymaking and planning.
ER  -

KHULBE, Devashish; Aliaksandr BELY a Stanislav SOBOLEVSKIJ. Commute Networks as a Signature of Urban Socioeconomic Performance: Evaluating Mobility Structures with Deep Learning Models. \textit{Smart Cities}. MDPI, 2025, roč.~8, č.~4, s.~1-22. ISSN~2624-6511. Dostupné z: https://doi.org/10.3390/smartcities8040125.

Přehled o publikaci