Workshop Overview
As the wheel of time has been spinning faster since the not-so-distant past, human beings are playing catch-up with the disruptive technologies around them. We are using machines to keep up with the rapid evolution of data, machines and knowledge. In an effort to solve complex problems, the level of machine exploitation has reached unprecedented horizons. Using Subsurface Intelligence (SI), we can aim to advance towards new methods and technologies to help us achieve different realizations, answers and point of views of our current reservoir models. Higher accuracy, lower uncertainty and quantifiable outputs have always been highly demanded in our industry to achieve better decision making, in addition to minimizing hours and manpower. Coupling our latest understanding of subsurface physical processes with machine learning, we have a greater chance to meet the demand and deliver on our energy commitments.
Subsurface Intelligence strives to deliver on that objective by harnessing today’s technologies and advancements in data science. The pure conventional methods utilized in the last century have been great in defining the obvious targets. However, as easy targets become scarce, we need to be equipped with unconventional and highly efficient tools to explore and develop what couldn’t be found with conventional means. The integration between the different data domains in arriving at models and representations of the subsurface is key to unlocking and maximizing their potential.
The fast paced advancements in the AI realm - owing to technology advancements of cloud, HPC and software algorithms - have already penetrated the E&P industry in multiple domains. The geoscience applications utilizing these technologies are progressing and will require a workforce with an entirely new skill set, to be able to design and implement such solutions. Upgrading the conventional approaches with the new advancements and constraining solutions has become more important than ever before. Understanding uncertainty in domain data as well as the methods used will be key to ranking models and determining the level of SI reached.
The Second EAGE Subsurface Intelligence Workshop, planned to take place in Manama, Bahrain on 28-31 October, aims to bring together bright minds from E&P Companies including NOC’s, ICO’s and service companies together with Academia and young professionals to engage in discussions, exchange ideas and experiences to jointly discuss the state of advancements today and align plans for the future. As part of the workshop, all attendees will have a chance to take part in the EAGE GeoHack: a two-day coding, problem solving and social hackathon on 28-29 October. Focusing on solving big data geoscience problems in the energy industry, the GeoHack will facilitate a suitable atmosphere where software developers, engineers and geoscientists will spend intensive hours to hack, test and experiment with the latest advancements in machine learning algorithms against open-source subsurface data, such as seismic, logs, cores, to solve data mining, geological interpretation and quantitative reservoir characterization problems. It is a great opportunity for companies to benchmark machine learning algorithms performance, expose the most promising technologies, and understand successes and pitfalls in machine learning.
The deadline to submit abstracts for the workshop technical programme is 20 June, and the technical committee welcomes submissions on a wide range of topics, including:
State of AI in the geosciences
AI in the seismic domain
Integration of physics and data-driven approaches in geoscience
Uncertainty in AI methods used for reservoir characterization
Data management for AI/ML
Case Studies