AI/machine learning
As carbon capture scales up worldwide, the real challenge lies deep underground—where smart reservoir management determines whether CO₂ stays put for good.
This article is the third in a Q&A series from the SPE Research and Development Technical Section focusing on emerging energy technologies. In this piece, Zikri Bayraktar, a senior machine learning engineer with SLB’s Software Technology and Innovation Center, discusses the expanding use of artificial intelligence in the upstream sector.
This article presents a results-driven case study from an ongoing collaboration between a midstream oil and gas company and Neuralix Inc.
-
The Offshore Technology Conference was cancelled for the first time ever due to the COVID-19 pandemic. But the flow of ideas continues. As proof, this curated summary of technical papers highlights unique concepts that might someday reduce the offshore sector’s heavy cost burdens. -
The Internet giant is walking away from the exploraiton and production business following a report that claimed it was undermining its own climate initiatives by offering its machine-learning tools.
-
The AI-driven tool will detect anomalies in subsea oil and gas infrastructure.
-
Despite streams of data being available on platforms about the condition of topside and drilling equipment, most experts agree that only a small fraction of such data is used. Whether for a fleet or single platform, AI can transform an offshore enterprise.
-
An AI-based application enabled operators to preempt ESP failures while optimizing production.
-
Artificial intelligence systems can be trained to recognize visual content in drawings and provide a simplified context. The complete paper highlights the use of AI to process a scanned drawing and redrawing it on a digital platform.
-
Artificial intelligence is already part of the work done in an office near you, and, before you know it, it will be in your office as well. Gaining familiarity and an understanding of it will serve you well.
-
Time-stamped data anomalies can lead to more-accurate identification and faster diagnosis.
-
"Sooner or later, we will get machines that are at least as intelligent as humans are," says Christof Koch, chief scientist and president of the Allen Institute for Brain Science in Seattle, Washington.
-
Increasing accuracy in models is often obtained through the first steps of data transformations. This guide explains the difference between the key feature-scaling methods of standardization and normalization and demonstrates when and how to apply each approach.
