The winner of the Exploration Innovation Prize is Aker BP and their development of in-house machine learning models also referred to as the Exploration Robot.
The recipient has developed an innovative and game-changing way to bridge a gap that has already led to better and more efficient exploration and that we have likely just seen the beginning of.
The jury recognized that Aker BP has made a significant breakthrough. The oil and gas industry has been scrambling to translate the progress within machine learning into tangible and valuable new ways of working with subsurface data.
Granted, we have already seen that this effort has led to countless new proof of concepts, tools, and new features in existing software. Moreover, the larger operators have all developed innovation labs in the hopes of harnessing their internal capabilities to achieve competitive advantage in strategic important applications.
However, the oil and gas industry has struggled to bridge the gap between R&D and scalable daily use for internally developed machine learning capabilities.
The presentation, given by Peder Aursand, Value Stream Manager and Data Scientist in Aker BP at the NCS Exploration conference in Oslo, demonstrated that the company has been able to close the gap between the research and development of machine learning models, and putting them to daily use within the organization.
Aursand told us that they have achieved implementation by:
- Recognizing that the models should work for the explorationists and not the other way around
- Facing the trust issues head-on and incorporating explainability and uncertainty quantification by default in the models.
- Making the models available for the explorationists in the tools and software they are familiar with and already use on a daily basis.
The jury believes that Aker BP has made the leap and bridged the gap.
They have not only developed workable machine learning models that can assist the geologists and geophysicists in reconstructing missing well logs, performing lithology predictions, doing shale volume calculations, getting a map view of potentially missed pay intervals, or getting an unbiased assessment of log quality with fewer resources than traditionally used but also made sure that the new tools are actually being used.
Aker BP has empowered cultural and structural change within their organization, and the jury believes that this is likely more important than the machine learning models themselves. Aker BP has made a digital transformation and facilitated a future-facing exploration department.
The Exploration Innovation Prize is awarded to a license group, company, or team that during the last few years has given a courageous and innovative technological contribution to exploration for oil and gas on the Norwegian continental shelf.
The recipient has matured an exploration technology with high potential leading to increased G&G knowledge or future commercial oil & gas discoveries.