Model Adjusted Generalized Tests for Methane Plume Detection on Hyperspectral Images

Reducing methane emissions is essential to tackle climate change. Here, we address the problem of detecting automatically point source methane leaks using high resolution hyperspectral images from the PRISMA satellite. We test the Generalized Likelihood Ratio Test (GLRT) for plume detection and compare it to the Matched Filter (MF). We then propose an improvement of the GLRT by using an adjustment coefficient. We introduce this new method under the name: Model Adjusted GLRT (MA-GLRT). We show that the MA-GLRT method reduces the fraction of false detections compared to the MF and the standard GLRT without preventing the detection of plumes. To validate the method, we use a dataset of manually annotated plumes on PRISMA images. We then show that our method outperforms the matched filter and the GLRT in terms of F1 score.