A geospatial and explainable-AI approach to metabolic clustering in Belgian cities was presented at the AGU Fall Meeting. The presentation explores interpretable spatial clusters of urban metabolic indicators and their relationships with urban form, infrastructure and energy use.

The contribution is developed through Spatial clustering, machine learning, explainable AI, and geospatial analysis. The geographical or conceptual scope is Belgium. It was presented at AGU Fall Meeting during 2024.

The contribution reflects the Lab’s interdisciplinary approach, combining quantitative and qualitative evidence to translate urban-metabolism research into planning, design, governance or policy.