These innovations are proposed to companies through a R&D project to be started early 2020. The main objective of the project is to go beyond what is currently available in commercial tools by offering a solution, compatible with the workflows in companies (commercial simulators, CRS mapping…), to account for uncertainties and risks in petroleum exploration.
We are looking forward to see you there.
In case you cannot attend the conference, do not hesitate in This email address is being protected from spambots. You need JavaScript enabled to view it. for more information on the project.
Understanding and being able to quantify the uncertainties during petroleum system assessment are the keys to deliver pertinent and in-depth analysis for relevant decision-making in petroleum exploration. This turns petroleum system modeling (PSM) a powerful and every time more vital tool as it is multi-physics, multi-disciplinary and allows for sensitivity analysis and scenario testing. However, PSM can be very time consuming, as it requires a lot of data and fully simulates the physical evolution of the sedimentary basins. Consequently, it is hardly used in the first phases of exploration projects or while drilling, when companies need to make decisions in a short period of time, or to accurately assess the risks associated to the petroleum systems.
New techniques of machine learning, which drastically reduce the time required to perform physic-based simulations, including geological uncertainties, recently emerged. For instance, methodologies based on an extension of the proxy model approach, initially used in meteorological modeling, are very well suited to deal with spatial outputs such are 2D or 3D geological results. They can be coupled with regressions, principal component analysis or clustering, to learn the behavior of the petroleum systems and reduce the time required for the studies. They pave the way to innovative methods to evaluate petroleum systems and more accurately assess the exploration risks in a timeframe compatible with operational work.
Therefore, we developed a new methodology to increase the effectiveness of these highly technological simulations. It relies both on expert systems, which enhance and guide the determination of the risks related to the studied petroleum systems, and on machine learning techniques, to provide robust and rapid risk evaluations at exploration scale in each phase of the basin maturity. As a result, our approach can be used in early basin exploration to assess the source rock maturity while interpreting the seismic, to assess the whole petroleum system providing maps of risks compatible with common risk segment mapping methods or for fast model update while drilling. Thus, this can lead to a drastic increase in the use of PSM during all the phases of sedimentary basins exploration and production.
Pore pressure prediction (P10 on the overpressure) in the Levant Basin using the C6+ approach to accurately account for risks and uncertainties in petroleum exploration
We thank Beicip-Franlab for providing a license of TemisFlow and Fadi Nader for the scientific discussions on the Levant Basin.
