Big Pressure - Hybrid modelling with machine learning for overpressure and mud weight prediction
Project overview
Unexpected high overpressures in the subsurface are still a challenge on the Norwegian Continental Shelf, even after decades of oil and gas exploration and production. Unpredicted overpressures may lead to challenges in drilling operations, such as mud loss, kicks, and in the worst case, loss of wells.
Project goals
to combine physics based modelling and 3D pressure stochastic pressure simulations with data driven machine learning to improve the workflow for pore pressure prediction along a planned well path.
Results and effects
- Better predictions of the pore pressure in the subsurface
- Robust update of pressures and mud weigth ahead of bit
- Safer and cheaper drilling operations
The BigPressure project is divived into 5 work packages:
- WP1: Hybrid pressure modelling
- WP2: Pressure from logs
- WP3: Hybrid machine learning while drilling
- WP4: Case studies
- WP5: Management and outreach
