06-2026 | UST-GNN for urban health analytics
Our UST-GNN paper became available online in Computers, Environment and Urban Systems on 24 June 2026, ahead of its October 2026 issue.
UST-GNN combines spatial context and neighborhood connectivity within a graph neural network. A case study in Greater London examines how these relationships contribute to urban health prediction, with spatial cross-validation used to evaluate performance beyond the neighborhoods used for training.
Read the publication details and publisher’s version.
Cai Wu
Assistant Professor
I study computational urban morphology, GeoAI, and data-driven urban design, developing reproducible methods for understanding cities across scales.