Robust Small Methane Plume Segmentation in Satellite Imagery
By: Khai Duc Minh Tran , Hoa Van Nguyen , Aimuni Binti Muhammad Rawi and more
Potential Business Impact:
Finds tiny methane leaks to fight climate change.
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.
Similar Papers
AttMetNet: Attention-Enhanced Deep Neural Network for Methane Plume Detection in Sentinel-2 Satellite Imagery
CV and Pattern Recognition
Finds methane leaks from space.
Deep Learning for Clouds and Cloud Shadow Segmentation in Methane Satellite and Airborne Imaging Spectroscopy
CV and Pattern Recognition
Finds methane leaks by seeing through clouds.
Optimizing Methane Detection On Board Satellites: Speed, Accuracy, and Low-Power Solutions for Resource-Constrained Hardware
CV and Pattern Recognition
Finds methane leaks faster from space.