While the subsurface, to date, lacks clear ordering principles and design rules, there is an increasing need to more systematically plan infrastructures in the buried shallow subsurface space. This project will explore how existing (often implicit) rule sets can be integrated in a design algorithm that supports further automated and more systematic design of cables and pipes in urban undergrounds.

This project aimed to support the detection of risky excavation operations based on historical datasets of damages in the Netherlands. Jiarong Li developed, using XGBoost, a data-driven model that predicted the likelihood of damage occurring in an excavation polygon. The Dutch agency Kadaster uses such polygons to exchange data on utility locations between network owners and excavator operators.

The machine learning model had a satisfactory performance with an AUC-ROC score of 0.821 and a balanced accuracy of 0.743.

To scale up city district heating construction projects, processes need to be developed and reliable. Currently teams largely rely on experience and improvisation, making them skilled in troubleshooting, but less efficient in planning and anticipating disruptions. This thesis has explored anticipation and containment through the lens of HRO