data science

This paper presents a physics-assisted deep-learning model to facilitate transfer learning in unconventional reservoirs by integrating the complementary strengths of physics-based and data-driven predictive models.

The promise of DataOps, the application of agile DevOps methods and tools to data engineering, is compelling even though the term has progressed through the hype cycle for years and, for many, little impact has been achieved. The potential remains strong, though. If impact is elusive, there are likely two main causes.

Registration is open for the SPE Europe Energy GeoHackathon, which will be held in October and November. It will be preceded by 4-week online bootcamp sessions on data science and geothermal energy, which will begin on 2 October.

A Houston startup that is developing a technology to detect methane leaks has moved on to Phase 2 of Chevron's business accelerator.

Geochemical parameters such as total organic carbon (TOC) provides valuable information to understand rock organic richness and maturity and, therefore, optimize hydrocarbon exploration. This article presents a novel work flow to predict continuous high-resolution TOC profiles using machine learning.

Two wings and a few hours can replace dozens of boots and many months in site selection, planning, and management.

Whether inconsistent, incomplete, ambiguous, or just plain wrong, bad data is a big barrier to digital transformation.

University of Houston researchers develop oil recovery tools with ‘significantly higher accuracy’ than current methods.

This article presents a deep-learning approach, the long short-term memory network, for adaptive hydrocarbon production forecasting that takes historical operational and production information as input sequences to predict oil production as a function of operational plans.

This paper describes an approach implemented by the operator to solve research and development challenges by creating in-house infrastructure of both software and hardware.