The Digital Underground: Integrating petroleum geoscience with data science principles to create an intelligent subsurface platform

Abstract

Summary The history of hydrocarbon exploration consistently indicates the advantages of integrating knowledge and data derived from different disciplines such as basin modelling, structural geology and geophysics. We have designed a complete subsurface workflow or platform, that we call Digital Underground. It combines semi-automated data wrangling, highly accessible structured analytics ready data in large databases, direct integration of data analytics and machine learning technology, tracking of data provenance, enabling reproducible scientific workflows, and the practical use of ML methods by the geoscientist in making their decisions. The workflow uses ML approaches at different scales, from core to seismic, and basin to prospect scale; while providing dynamic access to large amounts of data throughout. The workflow includes four main stages starting with well data analysis and ending up in integration of data-driven distributions of different properties required for risk and volumetric estimations together with corresponding uncertainties. We have shown the advantage of the platform by testing it on several examples. ML technology paired with solid data science practice; facilitates the integration of data and disciplines, enables geoscientists to exceed current best practice with the ML tools, and paves the way to the "new" best practice which is integrated data science and geoscience.