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

Abstract

UST-GNN brings neighbourhood connections, urban attributes, and spatial embeddings together in a graph learning framework. A study of medical prescription patterns across Greater London demonstrates its predictive value and shows how learned representations can be related to environmental and socioeconomic conditions.

Cai Wu

Assistant Professor

I study computational urban morphology, GeoAI, and data-driven urban design, developing reproducible methods for understanding cities across scales.