Description

Predicting the anthropogenic causes of subsidence in the Netherlands and unravel the contributions of deep versus shallow processes.

Problem Context:

The Netherlands is subsiding with rates outpacing sea-level rise, as a result of groundwater management, hydrocarbon extraction, and salt mining. This threatens the viability of the country and has great socio-economic consequences, because subsidence results in damage to the built environment, greenhouse gas emissions, and saline water intrusion. Predicting subsidence rates and unravelling of the contributions of different anthropogenic subsidence processes is essential for stakeholders and policy makers to mitigate subsidence.

Project set-up:

Input datatypes comprises: Earth Observation data (InSAR), water level (Groundwatertools), geological structural model (GeoTOP), gas reservoir production data (Vermilion Energy), GPS and land levelling (Rijkswaterstaat). Challenges are combining datasets and overcome 3D space and time variations, enabling deep learning networks to work properly. More-over, a hybrid approach is taken, where physical models and physical relations are combined with data-driven AI algorithms. Explainability is added to the models to understand the contributions of anthropogenic causes of subsidence.

Process

Contact

  • Madelon Molhoek (contact person), Kay Koster, Merijn de Bakker, Thibault Candela, Joanna Esteves Martins, Peter Fokker, Camilla van Wirdum., Consultant Datascience, TNO, e-mail: madelon.molhoek@tno.nl