Reducing Drilling Risk with AI Fault Interpretation
The Valhall field is located in the Norwegian sector of the North Sea, at 70m water depth. Producing oil from the Upper Cretaceous chalk for over 35 years, the densely faulted field is heavily compartmentalised. As the reservoir is depleted through production it compacts, resulting in significant subsidence extending up to the seabed.
To see if any further structural knowledge could be gathered from their data, earlier this year AkerBP undertook an AI Fault Interpretation project with Geoteric. Their data-driven AI technology was able to delineate with a high degree of accuracy the faults that are present in the reservoir interval and in the overburden.
The AkerBP Lead Geophysicist stated: “AI fault interpretations are proving to be very useful inputs for well planning. They are full field from the shallow overburden to the reservoir,our most comprehensive fault interpretations to date”, adding: “This has improved the rigour of our work so that our decisions are based on a better understanding of where faults may introduce drilling risks, and so that we can better understand lateral changes in our reservoir”.
Further Reading on Geoteric's AI Seismic Interpretation Software
Advancing Subsurface Understanding and Maximising Operational Efficiency with AI
Mark Brownless, Chief Geoscientist, Geoteric
Subsurface interpretation using AI is here and being used on live projects. It is delivering clear improvements in subsurface understanding at a time when it has never been more important to make the correct decision to drill or to drop.
This article appeared in May, 2020
Trusting AI in the Subsurface
Before widescale adoption of artificial intelligence across the subsurface arena, there is still one outstanding question; can it be trusted?
This article appeared in April, 2020
Artificial Intelligence and Seismic Interpretation
James Lowell, Peter Szafian and Nicola Tessen; Geoteric
The key to all seismic interpretation is the interpreter’s experience and knowledge, so why should artificial intelligence change that? The reality is, it shouldn't.
This article appeared in Vol. 16, No. 2 - 2019