Detection of Methane Plumes in Hyperspectral Images From Sentinel-5p by Coupling Anomaly Detection and Pattern Recognition

Abstract

Abstract. Reducing methane emissions is essential to tackle climate change. Here, we address the problem of detecting large methane leaks using hyperspectral data from the Sentinel-5P satellite. For that we exploit the fine spectral sampling of Sentinel-5P data to detect methane absorption features visible in the shortwave infrared wavelength range (SWIR). Our method involves three separate steps: i) background subtraction, ii) detection of local maxima in the negative logarithmic spectrum of each pixel and iii) anomaly detection in the background-free image. In the first step, we remove the impact of the albedo using albedo maps and the impact of the atmosphere by using a principal component analysis (PCA) over a time series of past observations. In the second step, we count for each pixel the number of local maxima that correspond to a subset of local maxima in the methane absorption spectrum. This counting method allows us to set up a statistical a contrario test that controls the false alarm rate of our detections. In the last step we use an anomaly detector to isolate potential methane plumes and we intersect those potential plumes with what have been detected in the second step. This process strongly reduces the number of false alarms. We validate our method by comparing the detected plumes against a dataset of plumes manually annotated on the Sentinel-5P L2 methane product.

Automatic Methane Plumes Detection in Time Series of Sentinel-5p L1b Images

“…(Lauvaux et al, 2021) We can see that for all locations, we have a detection rate of at least 80%. In particular, the average detection rate is 88% which exceeds the detection rate of the automatic detection method proposed by (Ouerghi et al, 2021), which is 74%.…”

“…To validate the method, we compare our detections with a recently proposed dataset (Lauvaux et al, 2021) of manually annotated plumes on the Sentinel-5P L2 methane product. We also compare our detection rate to the detection rate of the method proposed by (Ouerghi et al, 2021) which is also an automatic detection method. We then show that our method can complement the Sentinel-5P L2 methane product for the detection of methane plumes by detecting plumes that are not visible in the L2 product.…”

A versatile spaceborne architecture for immediate monitoring of the global methane pledge

“…This was mainly because, in localized regions, the methane budgets responded to the changes in not only the super-emitters but also the background. Assisted by artificial intelligence techniques in the future (Ouerghi et al, 2021;Paoletti et al, 2018;Yang et al, 2018;Yu et al, 2017;Zhang et al, 2018), our framework can derive a global, operational, and open-access methane monitoring network. As expected, multiple hotspots of interest result, and here we focused on those in the United States, China, Iraq, Kuwait, and Algeria.…”

Statistical modeling of deep features reduces false alarms in video change detection

“…Change detection may also serve climate and humanitarian causes. Satellite image time series can be used to monitor urban development [4] of specific regions and the variability of gas concentrations in the atmosphere across time [5,6].…”