Ust-GNN

A unified spatial–topological graph neural network framework for urban analytics demonstrated through a case study on urban health prediction

Bibliographic Data

ID21478739
AuthorsMinwei Zhao (0000-0002-6380-5426, University College London), Sanja Šćepanović (0000-0002-1534-8128, University of Oxford), Stephen Law (0000-0003-3184-572X, University College London, corresponding author), Ivica Obadić (Munich Center for Machine Learning), Cai Wu (0000-0002-5578-5525), Chih‐Cheng Wu (0000-0002-9690-6573), Daniele Quercia (0000-0001-9461-5804, Politecnico di Torino)
Year2026
Volume129
Pages102466
Publication date2026-10-01
Open AccessYes
TypeARTICLE
VenueComputers Environment and Urban Systems (JOURNAL)
Journal identifiersISSN: 0198-9715 • E-ISSN: 1873-7587
PublisherElsevier BV (PUBLISHER)
DOI10.1016/j.compenvurbsys.2026.102466
OpenAlexW4416117526
LanguageEN
References cited107

Understanding how social, demographic, environmental, and spatial factors jointly shape urban outcomes is essential for sustainable urban development and evidence-based policy. Traditional statistical approaches often struggle to capture complex non-linear relationships, while many machine learning methods overlook the joint roles of spatial autocorrelation and network topology in urban systems. Recent advances in GeoAI have addressed these challenges only partially, often treating spatial effects, graph structure, evaluation, and interpretability separately. We present UST-GNN , a unified spatial–topological graph neural network framework that integrates neighbourhood connectivity, heterogeneous urban features, and positional/locational embeddings into a single representation. Using the MedSAT dataset, which contains over 150 environmental and socio-demographic variables and six prescription outcomes across 4835 neighbourhoods in Greater London, UST-GNN outperforms strong statistical, geographically enhanced, and graph Machine Learning baselines, improving out-of-sample R 2 by 8.4–13.2% under strict spatial cross-validation. We further introduce a lightweight principal-component module to interpret learned node embeddings geographically and relate them to policy-relevant covariates. The resulting analyses recover established patterns, offer new perspectives on debated associations, and reveal novel predictors warranting further causal investigation. Together, these findings demonstrate the value of graph-based spatial machine learning for urban health analytics, environmental inequality assessment, and evidence-based urban policy. Beyond predictive gains, UST-GNN provides a unified GeoAI analytical pipeline that can be embedded into urban digital twin workflows for scenario testing, monitoring, and data-informed decision-making for healthier, more sustainable cities

Artificial neural network · Graph · Medical prescription · Public health · Warrant · White paper · Data-Driven Disease Surveillance · Health, Environment, Cognitive Aging · Urban Green Space and Health

Tools

Open DOIOpen Access