safety

SPE’s newly renamed Safety Technical Section expands the reach of human factors by integrating safety, risk management, and system resilience expertise while preserving dedicated leadership and technical focus.

As drilling operations become increasingly digital, computer vision is emerging as a continuous safety layer that complements, not replaces, established safety practices. The challenge is no longer whether artificial intelligence can detect hazards, but how operators should deploy, integrate, and govern these systems to improve safety without adding operational comple…

From AI-enabled walking rigs to subsea drones and autonomous inspection robots, robotics is rapidly moving from pilot projects to field deployment. The technology promises not only greater efficiency but also a fundamental shift in how the industry approaches safety and asset management.

A report commissioned by Havtil, the Norwegian Ocean Industry Authority, calls for better dialogue regarding pore-pressure uncertainty and higher-end drilling techniques like managed pressure drilling as methods to reduce the risk of well-control events.

This paper proposes a shift in the timing of risk modeling to much further back within the job life cycle, recognizing each function’s role in the mitigation of risk.

The National Academies of Sciences, Engineering, and Medicine recommend continued state and federal funding, data-sharing, and new technologies to mitigate the risks posed by orphan wells.

This paper explores the transformative effect of unmanned aerial systems on operational efficiency, safety, and emergency response within the Khurais oil fields in Saudi Arabia. By integrating sophisticated drone technology, improvements have been achieved in routine inspections, leak detection, and emergency scenarios.

The SPE Human Factors Technical Section has been officially renamed the SPE Safety Technical Section. The new name better reflects how safety is managed today across interconnected areas like human performance, risk management, and system resilience.

This study explores the use of autoencoder models with convolutional neural networks to present a framework and prototype for early and accurate kick detection during offshore oilwell drilling.

The companies have released the Event Learning Taxonomy CLUE, which aims to improve the understanding of incidents beyond individual blame and toward clearer reporting and increased learning.