Scientists from the Los Alamos National Laboratory have devised a system for autonomously detecting gas leaks on oil and gas infrastructure.

The autonomous, low-cost, fast leak detection system (ALFaLDS) relies on sensors enhanced with machine learning to detect the presence of methane — a greenhouse gas — and ethane

Capable of detecting, locating and quantifying natural gas leaks in real-time measurements of methane and ethane, ALFaLDS also relies on atmospheric wind measurement data that is analyzed via machine learning code that has been designed for leak detection.

The system, according to its developers, could potentially result in a 90% reduction in methane emissions if used throughout the oil and gas industry to detect gas leaks quickly, thereby improving how fast they are fixed.

The system is detailed in the journal Atmospheric Environment: X.

To contact the author of this article, email mdonlon@globalspec.com