Environmental questions, made tangible.

At Metabolism of Cities, I co-developed and co-authored D4.4, the Urban Circularity Assessment Method, as one of four named authors. We combined material-flow accounts for two reference years with bottom-up building-stock accounting and 18 indicators. The method specified Sankey and dashboard outputs for facilitated application in Apeldoorn, Bodø, Mikkeli, Porto and Seville.

Scope and limitsThe method estimates urban flows and stocks from available evidence; it does not audit every tonne moving through a city. Published example figures retain their original authorship.

At Metabolic, I co-authored D2.2, CENTRINNO Cartography Alpha Version, as one of six named authors. I helped shape a method connecting geographic context, community mapping and material flows. The alpha demonstrator paired a three-page public-site mock-up using Amsterdam as its example with KUMU maps, showing how the approach could support nine pilot cities.

Scope and limitsThis is a co-authored method and alpha demonstrator, not evidence of nine fully delivered pilot websites. “Urban ecosystem” refers to resources, infrastructure and social relationships, not a biodiversity survey.

I built a Python pipeline aligning Landsat temperature and vegetation data, VoxCity urban-form measures, Urbanity street networks and Global Streetscapes image semantics, with EUBUCCO building footprints. I trained exploratory XGBoost models and used SHAP to inspect associations. A later audit identified problems in the temperature target and spatial folds; I am rebuilding those stages before publishing performance claims.

Scope and limitsModel validation is being rebuilt after my own re-audit found problems in the temperature target and in how the spatial cross-validation folds were separated. Until that work is finished, no model score, explanation or cooling scenario here is a validated claim.