Preprints
https://doi.org/10.5194/egusphere-2024-2565
https://doi.org/10.5194/egusphere-2024-2565
03 Sep 2024
 | 03 Sep 2024

A Data-Efficient Deep Transfer Learning Framework for Methane Super-Emitter Detection in Oil and Gas Fields Using Sentinel-2 Satellite

Shutao Zhao, Yuzhong Zhang, Shuang Zhao, Xinlu Wang, and Daniel J. Varon

Abstract. Efficiently detecting large methane point sources (super-emitters) in oil and gas fields is crucial for informing stakeholders for mitigation actions. Satellite measurements by multispectral instruments, such as Sentinel-2, offer global and frequent coverage. However, methane signals retrieved from satellite multispectral images are prone to surface and atmospheric artifacts that vary spatially and temporally, making it challenging to build a detection algorithm that applies everywhere. Hence, laborious manual inspection is often necessary, hindering widespread deployment of the technology. Here, we propose a novel deep-transfer-learning-based methane plume detection framework. It consists of two components: an adaptive artifact removal algorithm (low reflectance artifact detection, LRAD) to reduce artifacts in methane retrievals, and a deep subdomain adaptation network (DSAN) to detect methane plumes. To train the algorithm, we compile a dataset comprising 1627 Sentinel-2 images from 6 known methane super-emitters reported in the literatures. We evaluate the ability of the algorithm to discover new methane sources with a suite of transfer tasks, in which training and evaluation data come from different regions. Results show that the DSAN (average macro-F1 score 0.86) outperforms two convolutional neural networks (CNN), MethaNet (average macro-F1 score 0.7) and ResNet-50 (average macro-F1 score 0.77), in transfer tasks. The transfer-learning algorithm overcomes the issue of conventional CNNs that their performance degrades substantially in regions outside training data. We apply the algorithm trained with known sources to an unannotated region in the Algerian Hassi Messaoud oil field and reveal 34 anomalous emission events during a one-year period, which are attributed to 3 methane super-emitters associated with production and transmission infrastructure. These results demonstrate the potential of our deep-transfer-learning-based method towards efficient methane super-emitter discovery using Sentinel-2 across different oil and gas fields worldwide.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Share

Journal article(s) based on this preprint

09 Apr 2025
A data-efficient deep transfer learning framework for methane super-emitter detection in oil and gas fields using the Sentinel-2 satellite
Shutao Zhao, Yuzhong Zhang, Shuang Zhao, Xinlu Wang, and Daniel J. Varon
Atmos. Chem. Phys., 25, 4035–4052, https://doi.org/10.5194/acp-25-4035-2025,https://doi.org/10.5194/acp-25-4035-2025, 2025
Short summary
Shutao Zhao, Yuzhong Zhang, Shuang Zhao, Xinlu Wang, and Daniel J. Varon

Interactive discussion

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2024-2565', Anonymous Referee #1, 06 Nov 2024
  • RC2: 'Comment on egusphere-2024-2565', Anonymous Referee #2, 03 Dec 2024

Interactive discussion

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2024-2565', Anonymous Referee #1, 06 Nov 2024
  • RC2: 'Comment on egusphere-2024-2565', Anonymous Referee #2, 03 Dec 2024

Peer review completion

AR: Author's response | RR: Referee report | ED: Editor decision | EF: Editorial file upload
AR by Yuzhong Zhang on behalf of the Authors (26 Jan 2025)  Author's response   Author's tracked changes   Manuscript 
ED: Publish as is (04 Feb 2025) by Qiang Zhang
AR by Yuzhong Zhang on behalf of the Authors (09 Feb 2025)

Journal article(s) based on this preprint

09 Apr 2025
A data-efficient deep transfer learning framework for methane super-emitter detection in oil and gas fields using the Sentinel-2 satellite
Shutao Zhao, Yuzhong Zhang, Shuang Zhao, Xinlu Wang, and Daniel J. Varon
Atmos. Chem. Phys., 25, 4035–4052, https://doi.org/10.5194/acp-25-4035-2025,https://doi.org/10.5194/acp-25-4035-2025, 2025
Short summary
Shutao Zhao, Yuzhong Zhang, Shuang Zhao, Xinlu Wang, and Daniel J. Varon
Shutao Zhao, Yuzhong Zhang, Shuang Zhao, Xinlu Wang, and Daniel J. Varon

Viewed

Total article views: 668 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
484 139 45 668 52 16 13
  • HTML: 484
  • PDF: 139
  • XML: 45
  • Total: 668
  • Supplement: 52
  • BibTeX: 16
  • EndNote: 13
Views and downloads (calculated since 03 Sep 2024)
Cumulative views and downloads (calculated since 03 Sep 2024)

Viewed (geographical distribution)

Total article views: 681 (including HTML, PDF, and XML) Thereof 681 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 09 Apr 2025
Download

The requested preprint has a corresponding peer-reviewed final revised paper. You are encouraged to refer to the final revised version.

Short summary
We target at the challenge of detecting methane super-emitters in oil and gas fields, which is critical for mitigating climate change. Traditional satellite-based detectors struggle due to interference from complex surfaces. We developed a novel method using deep-transfer-learning that improves detection efficiency and accuracy by reducing artifacts and adapting methane knowledge to different regions. Application revealed significant methane emissions, demonstrating the potential of our method.
Share