Search papers, labs, and topics across Lattice.
To address the severe data sparsity caused by incomplete satellite passes, the authors construct MethaneUnion, an 8,981-case benchmark uniting Carbon Mapper plume reports with Sentinel-2, Landsat 8/9, EMIT, and Sentinel-5P observations, alongside MethaneFuse, a model designed to learn across heterogeneous sensors under partial availability. This multi-modal formulation overcomes the operational bottleneck of single-sensor dependence, which previously discarded most transient emission events lacking full coverage. At a 480 m resolution, MethaneFuse achieves an 84.87 F1 and 93.62 AUROC鈥攕urpassing the strongest baseline by 5.65 F1 points while reducing false positives by 8.19 points and maintaining cross-sensor transfer when primary inputs are missing.
Fragmented satellite data no longer means blind spots: learning over incomplete multi-sensor constellations nearly triples usable methane plume events while slashing false positives by 8.19 points.
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.
