GravityGNN: A Novel Graph Neural Network for Modelling Home-to-Work Spatial Flows in England
Abstract
This conference paper develops a graph neural network approach to modelling commuting flows in England. It brings spatial interaction modelling and graph learning together to examine connections between residential and employment locations.
Type
Publication
19th International Conference on Computational Urban Planning and Urban Management (CUPUM 2025)
Paper at CUPUM 2025, held in London on 23–27 June 2025. The proceedings link below leads to the conference collection.
Cai Wu
Assistant Professor
I study computational urban morphology, GeoAI, and data-driven urban design, developing reproducible methods for understanding cities across scales.