machine learning

Earlier this year, 19 teams competed in a machine-learning contest held by the Data Analytics Study Group of SPE’s Gulf Coast Section. The was the first competition of its kind for SPE. Here, the organizers of the contest present some of the techniques used and lessons learned from the Machine Learning Challenge 2021.

Physics-based simulations plus machine-learning exercises are yielding a more comprehensive look at production volumes from unconventional assets.

Algorithms are taking over the world, or so we are led to believe, given their growing pervasiveness in multiple fields of human endeavor such as consumer marketing, finance, design and manufacturing, health care, politics, and sports. The focus of this article is to examine where things stand in regard to the application of these techniques for managing subsurface en…

The authors develop an innovative machine-learning method to determine salt structures directly from gravity data.

The work and the provided methodology provide a significant improvement in facies classification.

Phase 1 covers the modeling and monitoring of assets for six ADNOC Group companies. The four phases of the project are expected to be completed by 2022.

A new study confirms the success of a natural-gas leak-detection tool pioneered by Los Alamos National Laboratory scientists that uses sensors and machine learning to locate leak points at oil and gas fields, promising new automatic, affordable sampling across a vast natural gas infrastructure.

The complete paper discusses the successful application of a data-driven approach to analyze production data and identify root causes of slugging in a subsea production system on the Norwegian Continental Shelf.

To drive progress in the field of data science, the authors propose 10 challenge areas for the research community to pursue. Because data science is broad, with methods drawing from computer science, statistics, and other disciplines, these challenge areas speak to the breadth of issues.

Automated image-processing algorithms can improve the quality and speed in classifying the morphology of heterogeneous carbonate rock. Several commercial products have produced petrophysical properties from 2D images and, to a lesser extent, from 3D images.