Complex Urban Systems

This research studies how hidden urban dynamics can be reconstructed from heterogeneous and incomplete evidence. The aim is not simply to predict a city-scale outcome, but to build models whose assumptions, uncertainty, and limits remain interpretable.

• Probabilistic inference for urban processes that cannot be observed directly.
• Integration of mobility, demographic, transport, and infrastructure data.
• Large-scale models that preserve interpretable mechanisms and uncertainty.
• AI methods that support urban reasoning without erasing evidence boundaries.

The work treats every dataset as a partial view of the city. Models are designed around what each source can support, where sources disagree, and which conclusions should remain uncertain.