# Plume Segmentation from MethaneSAT with Cross-Sensor Transfer Learning and Physics-Informed Postprocessing

arXiv: https://arxiv.org/abs/2605.24273 · HTML: https://mlsanity.com/paper/2605.24273/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 87 references that are in the map.
- First posted on arXiv 22 May 2026.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention](https://mlsanity.com/paper/2305.07027/) (2023)
- [Unsupervised domain adaptation in brain lesion segmentation with adversarial networks](https://mlsanity.com/paper/1612.08894/) (2016)
- [Fast and Accurate Retrieval of Methane Concentration from Imaging Spectrometer Data Using Sparsity Prior](https://mlsanity.com/paper/2003.02978/) (2020)
- [HyperspectralViTs: General Hyperspectral Models for On-board Remote Sensing](https://mlsanity.com/paper/2410.17248/) (2024)
- [Towards Operational Automated Greenhouse Gas Plume Detection and Delineation](https://mlsanity.com/paper/2505.21806/) (2025)
- [Unlocking the Potential: Multi-task Deep Learning for Spaceborne Quantitative Monitoring of Fugitive Methane Plumes](https://mlsanity.com/paper/2401.12870/) (2024)
- [AI for operational methane emitter monitoring from space](https://mlsanity.com/paper/2408.04745/) (2024)
- [Multi-Platform Methane Plume Detection via Model and Domain Adaptation](https://mlsanity.com/paper/2506.06348/) (2025)
- [Global monitoring of methane point sources using deep learning on hyperspectral radiance measurements from EMIT](https://mlsanity.com/paper/2604.10094/) (2026)
- [Deep Learning for Clouds and Cloud Shadow Segmentation in Methane Satellite and Airborne Imaging Spectroscopy](https://mlsanity.com/paper/2509.19665/) (2025)
- [AttMetNet: Attention-Enhanced Deep Neural Network for Methane Plume Detection in Sentinel-2 Satellite Imagery](https://mlsanity.com/paper/2512.02751/) (2025)

## Abstract (arXiv)

Automated detection and masking of individual methane plumes from satellite imagery is important for operational emission attribution and quantification. We present a machine learning framework for plume detection from MethaneSAT retrieved column-averaged dry-air mole fractions of methane. We address two core challenges: the scarcity of labeled MethaneSAT data and the need for inference reliability across diverse atmospheric and surface conditions. We first demonstrate that Mask R-CNN with a ResNet-50 backbone outperforms a U-Net semantic segmentation baseline on both MethaneAIR (an airborne version of MethaneSAT) and MethaneSAT data, with pixel-level F1 score gains of 10.49 and 5.48 percentage points respectively. To address MethaneSAT data scarcity, we evaluate three cross-sensor transfer strategies leveraging MethaneAIR flights and synthetic plumes. Mask R-CNN with ResNet-50 fine-tuned from MethaneAIR pre-trained weights is the most effective strategy, achieving instance-level precision of 0.60 and recall of 0.98 at the baseline operating point. A physics-informed post-processing pipeline converts detections into two operationally distinct modes. The first is a high-sensitivity mode that applies morphological filtering and proximity-based merging for comprehensive emission screening, achieving precision of 0.71 and recall of 0.94. The second is a high-precision mode that additionally applies a distribution-based classifier for confident source attribution, achieving precision of 0.92 and recall of 0.70. Manual review of detections classified as false positives against our wavelet-based reference plume mask labels shows that some correspond to real methane enhancements... Our data and code used in this work are publicly available at: https://doi.org/10.7910/DVN/FR959H