Robust Small Methane Plume Segmentation in Satellite Imagery

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tran, Khai Duc Minh, Van Nguyen, Hoa, Rawi, Aimuni Binti Muhammad, Athinarayanarao, Hareeshrao, Vo, Ba-Ngu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912549032689664
author Tran, Khai Duc Minh
Van Nguyen, Hoa
Rawi, Aimuni Binti Muhammad
Athinarayanarao, Hareeshrao
Vo, Ba-Ngu
author_facet Tran, Khai Duc Minh
Van Nguyen, Hoa
Rawi, Aimuni Binti Muhammad
Athinarayanarao, Hareeshrao
Vo, Ba-Ngu
contents This paper tackles the challenging problem of detecting methane plumes, a potent greenhouse gas, using Sentinel-2 imagery. This contributes to the mitigation of rapid climate change. We propose a novel deep learning solution based on U-Net with a ResNet34 encoder, integrating dual spectral enhancement techniques (Varon ratio and Sanchez regression) to optimise input features for heightened sensitivity. A key achievement is the ability to detect small plumes down to 400 m2 (i.e., for a single pixel at 20 m resolution), surpassing traditional methods limited to larger plumes. Experiments show our approach achieves a 78.39% F1-score on the validation set, demonstrating superior performance in sensitivity and precision over existing remote sensing techniques for automated methane monitoring, especially for small plumes.
format Preprint
id arxiv_https___arxiv_org_abs_2508_16282
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Robust Small Methane Plume Segmentation in Satellite Imagery
Tran, Khai Duc Minh
Van Nguyen, Hoa
Rawi, Aimuni Binti Muhammad
Athinarayanarao, Hareeshrao
Vo, Ba-Ngu
Computer Vision and Pattern Recognition
Signal Processing
This paper tackles the challenging problem of detecting methane plumes, a potent greenhouse gas, using Sentinel-2 imagery. This contributes to the mitigation of rapid climate change. We propose a novel deep learning solution based on U-Net with a ResNet34 encoder, integrating dual spectral enhancement techniques (Varon ratio and Sanchez regression) to optimise input features for heightened sensitivity. A key achievement is the ability to detect small plumes down to 400 m2 (i.e., for a single pixel at 20 m resolution), surpassing traditional methods limited to larger plumes. Experiments show our approach achieves a 78.39% F1-score on the validation set, demonstrating superior performance in sensitivity and precision over existing remote sensing techniques for automated methane monitoring, especially for small plumes.
title Robust Small Methane Plume Segmentation in Satellite Imagery
topic Computer Vision and Pattern Recognition
Signal Processing
url https://arxiv.org/abs/2508.16282