06-2026 | Interpretable graph learning for commuting flows
Our paper Theory-informed and interpretable graph learning for urban commuting flows became available online in Sustainable Cities and Society on 13 June 2026.
The paper introduces PIG-GNN, which brings geographic principles into graph learning for commuting-flow prediction. Using commuting data from England, the study examines how predictive accuracy and interpretable patterns of spatial interaction can be addressed together.
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.