SwRI will be exhibiting at the CH4 Connections – The Methane Emissions Conference, Booth No. 4.
Wednesday, September 18
4:30 p.m. – 5:45 p.m.
Vendor Showcase rapid-fire session
“Airborne Deep Learning to Detect Methane Leaks,” Heath Spidle
SLED/M was initially developed for stationary applications, such as fence-line monitoring of midstream facilities, but we are currently advancing the technology to perform autonomous commercial aerial inspections via drones. Conventional detection systems, designed to locate larger leaks, suffer from false positives and missed detections, which hamper effectiveness and utilization by industry. SwRI designed SLED/M to identify small methane leaks that typically go unnoticed along pipelines and storage facilities. By optimizing algorithms to reliably detect leaks under a variety of environmental conditions, SLED/M substantially reduces false positives. The system detects and pinpoints small methane leaks, known as fugitive emissions, by pairing passive optical sensing data with artificial intelligence algorithms and embedded edge computing.