ALFaLDS is deployed during blind tests at the model oil and gas test facility at Fort Collins, Colorado. (Photo courtesy of Los Alamos National Laboratory)

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

“Our automated leak location system finds gas leaks fast, including small ones from failing infrastructure. It also lowers cost, compared to current methods for fixing gas leaks, which are labor intensive, expensive, and slow,” said lead scientist Manvendra Dubey. “Our sensors outperformed competing techniques in sensitivity for detecting methane and ethane. In addition, our neural network can be coupled to any sensor, which makes our tool very powerful and will enable market penetration.”

The Autonomous, Low-cost, Fast Leak Detection System (ALFaLDS) was developed to discover accidental releases of methane, a potent greenhouse gas. The system detects, locates, and quantifies a natural gas leak based on real-time methane and ethane (in natural gas) and atmospheric wind measurements that are analyzed by a machine-learning code trained to locate leaks. The code is trained using Los Alamos National Laboratory’s high-resolution plume dispersion models and the training is finessed on-site by controlled releases.

Test results using blind releases at an oil and gas well pad facility at Colorado State University in Fort Collins, Colorado, demonstrated that the ALFaLDS locates the engineered methane leaks precisely and quantifies their size. This novel capability for locating leaks with high skill, speed, and accuracy at lower cost, promises new automatic, affordable sampling of fugitive gas leaks at well pads and oil and gas fields.

ALFaLDS’s success in locating and quantifying fugitive methane leaks at natural gas facilities could lead to a 90 percent reduction in methane emissions if implemented by the industry.

The system uses a small sensor, which makes it also ideal for deployment on cars and drones. The Los Alamos team is developing the sensors integrated with a mini 3D sonic anemometer and powerful machine-learning code. The code is autonomous and can read data from any gas and wind sensors to help find leaks fast and minimize fugitive emissions from the network of natural gas extraction, production, and consumption.

Source