Where England's cities are growing: evidence from big building footprint data and explainable AI

Abstract

Urban development is shaped by demographic and socio-economic factors, while simultaneously influencing these dynamics. Understanding these complex relationships is essential for informed urban planning, yet previous research has struggled with fine-scale analysis over large areas due to data and methodological limitations. This study overcomes these challenges by leveraging high-resolution building footprint data and eXplainable AI (XAI). Focusing on England between 2017 and 2023, we first quantify and map the extent of new urban development and further model it as a function of population density, ethnic composition, and the Index of Multiple Deprivation (IMD) using machine-learning algorithms. We then interpret the best-performing model with SHAP values and reveal a substantial nonlinear correlation between these demographic and socio-economic factors and new urban development. This analytical framework offers a novel, scalable, interpretable approach to fine-grained urban analysis, and, for the first time, provides a nationwide quantitative assessment of how population density, ethnic composition, and deprivation jointly shape urban development in England, thereby supporting evidence-based and equitable planning and policymaking.

Publication
Xinyi Yuan
Xinyi Yuan
PhD Researcher
Mingshu Wang
Mingshu Wang
Reader in Geospatial Data Science