Methane detection improves by fusing multiple satellite data sources
MethaneFuse: Learning from Multi-Sensor Satellite Observations for Methane Plume Detection
Computer Vision and Pattern RecognitionMachine Learning
Summary
Detecting methane gas leaks from space is tricky because satellites don’t always capture complete data at once due to factors like clouds and timing. The authors built a new dataset combining reports of methane plumes with images from several satellites, even when not all data types are present at the same time. They created a method called MethaneFuse that learns to spot methane plumes using this mixed, incomplete data. This approach improves detection accuracy and reduces false alarms compared to previous methods using only single satellite data.
What this means in practice
- •For environmental monitoring teams: Detect methane emissions more accurately by combining incomplete satellite data from different sensors to improve leak identification on a larger scale.
- •For oil and gas operation safety teams: Implement multi-sensor satellite data analysis tools that reduce false alarms in methane leak detection, supporting timely responses to emission events.
Authors
Yuyao Wang, Juliana Y. Leung, Di Niu
Abstract
Methane plume detection from satellite imagery is constrained by incomplete observations: public satellites provide complementary spatial, spectral, and atmospheric evidence, but real plume cases rarely contain fully paired multi-sensor measurements because of revisit schedules, cloud coverage, acquisition quality, and the transient nature of emissions. Most learning-based detectors rely on single-sensor inputs, especially Sentinel-2 (S2), leaving many reported plume cases unusable. We construct MethaneUnion, a temporal multi-sensor dataset built from Carbon Mapper plume reports and matched S2, Landsat 8/9 (L8/9), EMIT, and Sentinel-5P (S5P) observations. Built on MethaneUnion, MethaneFuse learns from heterogeneous satellite observations under partial sensor availability without requiring complete four-sensor measurements. MethaneUnion expands usable coverage from 3,211 valid S2-matched plume cases to 8,981 reported plume cases with multi-sensor observations. At the representative 480 m setting, MethaneFuse achieves 84.87 F1 and 93.62 AUROC, improving over the strongest baseline by 5.65 F1 and 8.30 AUROC points while reducing false positives by 8.19 points. Sensor-availability experiments show that MethaneFuse improves detection when S2 is available and transfers plume knowledge to L8/9, EMIT, and S5P when S2 is unavailable. These results demonstrate the value of learning from incomplete heterogeneous sensor observations for practical methane plume detection.