arXiv subjects

Ilse Aben

Publications and source records attributed to Ilse Aben.

5 recordsLinked to original sources

arXiv2026

Explainable Comparison of Feature-Based and Deep Learning Models for TROPOMI Methane Plume Screening

Continuous and global detection of large methane emissions is a crucial step for global warming mitigation. Satellite observations, such as from S5P/TROPOMI, combined with plume detection algorithms, can play a key role in this effort. However, not all TROPOMI plume detections that look like methane emission plumes are the result of actual emissions. A significant part of the plume-like features in the data are retrieval artifacts. Such artifacts could be the result of variations in elevation or albedo gradients, high concentrations of aerosols, coastal lines, water bodies, etc. Previous work approached the problem of plume-artifact classification by means of a Support Vector Machine Classifier (SVC), trained on an extensive set of observation-based scalar features designed by domain experts. However, such an approach limits the information scope received by the algorithm to what is deemed to be important by the experts, breaks the spatial relationship between pixels, and loses information during the process of statistical aggregation. In this study, we compare feature-based (SVC, Random Forest, XGBoost) and image-based (ResNet-18, ResNet-34) models for methane plume-artifact classification under balanced and imbalanced evaluation settings. To interpret the results, we apply SHAP-based explainability to both model families. Our findings provide practical guidance for model selection in operational methane-screening workflows such as the CAMS Methane Hotspot Explorer.

cs.LG↗

arXiv2025

Mitigating representation bias caused by missing pixels in methane plume detection

Most satellite images have systematically missing pixels (i.e., missing data not at random (MNAR)) due to factors such as clouds. If not addressed, these missing pixels can lead to representation bias in automated feature extraction models. In this work, we show that spurious association between the label and the number of missing values in methane plume detection can cause the model to associate the coverage (i.e., the percentage of valid pixels in an image) with the label, subsequently under-detecting plumes in low-coverage images. We evaluate multiple imputation approaches to remove the dependence between the coverage and a label. Additionally, we propose a weighted resampling scheme during training that removes the association between the label and the coverage by enforcing class balance in each coverage bin. Our results show that both resampling and imputation can significantly reduce the representation bias without hurting balanced accuracy, precision, or recall. Finally, we evaluate the capability of the debiased models using these techniques in an operational scenario and demonstrate that the debiased models have a higher chance of detecting plumes in low-coverage images.

cs.CV↗

arXiv2023

Daily detection and quantification of methane leaks using Sentinel-3: a tiered satellite observation approach with Sentinel-2 and Sentinel-5p

The twin Sentinel-3 satellites have multi-band radiometers which observe in methane-sensitive shortwave infrared bands with daily global coverage and 500 m ground pixel resolution. We investigate the methane observation capability of Sentinel-3 and how its coverage-resolution combination fits between Sentinel-5p and Sentinel-2 within a tiered observation approach for methane leak monitoring. Sentinel-5p measures methane with high precision and daily global coverage, allowing worldwide leak detection but with a coarse spatial resolution of 7 km x 5.5 km. The Sentinel-2 twin satellites have multi-band instruments that can identify source locations of major leaks (> 1 t/h) with their methane observations of 20 m resolution under favorable observational conditions, but these satellites lack daily global coverage We show that methane enhancements can be retrieved from the shortwave infrared band measurements of Sentinel-3. We report the lowest emission detections by Sentinel-3 in the 8-20 t/h range, depending on location and wind conditions. We demonstrate Sentinel-3's capability of identification and monitoring of methane leaks using two case studies. Near Moscow, Sentinel-3 shows that two major short-term leaks, separated by 30 km, occurred simultaneously at a gas pipeline and appear as a single methane plume in Sentinel-5p data. For another Sentinel-5p leak detection near the Hassi Messaoud oil/gas field in Algeria, Sentinel-3 identifies the leaking facility emitting continuously for 6 days, and Sentinel-2 pinpoints the source of the leak at an oil/gas well. Sentinel-2 and Sentinel-3 also show the 6-day leak was followed by a four-month period of burning of the leaking gas, suggesting a gas well blowout to be the cause of the leak.

physics.ao-ph↗

arXiv2022

A high-resolution gridded inventory of coal mine methane emissions for India and Australia

Coal mines are globally an important source of methane and also one of the largest point sources of methane. We present a high-resolution 0.1deg x 0.1deg bottom-up gridded emission inventory for methane emissions from coal mines in India and Australia, which are among the top five coal-producing countries in 2018. The aim is to reduce the uncertainty in local coal mine methane emissions and to improve the spatial localization to support monitoring and mitigation of these emissions. For India, we improve the spatial allocation of the emissions by identifying the exact location of surface and underground coal mines and we use a tier-2 Intergovernmental Panel on Climate Change (IPCC) methodology to estimate the emissions from each coal mine using country-specific emission factors. For Australia, we estimate the emission for each coal mine by distributing the state-level reported total emissions using proxies of coal production and the coal basin-specific gas content profile of underground mines. Comparison of our total coal mine methane emission from India with existing global inventories showed our estimates are about a factor 3 lower, but well within the range of the national Indian estimate reported to the United Nations framework convention on climate change (UNFCCC). For both countries, the new spatial distribution of the emissions shows a large difference from the global inventories. Our improved emissions dataset will be useful for air quality or climate modeling and while assessing the satellite methane observations.

physics.ao-ph↗

arXiv2021

Methane Emissions from Super-emitting Coal Mines in Australia quantified using TROPOMI Satellite Observations

Two years of satellite observations were used to quantify methane emission from coal mines in Queensland, the largest coal-producing state in Australia. The six analyzed surface and underground coal mines are estimated to emit 570+/-98 Gg a-1 in 2018-2019. Together, they account for 7% of the national coal production, while emitting 55+/-10% of the reported methane emission from coal mining in Australia. Our results indicate that for two of the three locations our satellite-based estimates are significantly higher than reported to the Australian government. Most remarkably, 40% of the quantified emission came from a single surface mine (Hail Creek) located in a methane-rich coal basin. Our findings call for increased monitoring and investment in methane recovery technologies for both surface and underground mines.

physics.ao-ph↗