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

• URL: http://arxiv.org/abs/2605.24273v1
• Date: Fri, 22 May 2026 22:53:57 GMT
• Title: Plume Segmentation from MethaneSAT with Cross-Sensor Transfer Learning and Physics-Informed Postprocessing
• Abstract summary: We present a machine learning framework for plume detection from MethaneSAT retrieved column-averaged dry-air mole fractions of methane.<n>We address two core challenges: the scarcity of labeled MethaneSAT data and the need for inference reliability across diverse atmospheric and surface conditions.
• Score: 8.061443907684147
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 U-Net semantic segmentation on both MethaneAIR (an airborne version of MethaneSAT) and MethaneSAT data, with pixel-level F1 score gains of 10.49 and 5.48 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 a near-perfect 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 ground truth labels reveals that a meaningful fraction of cases correspond to real methane enhancements excluded by conservative labeling criteria, indicating that precision values reported are lower bounds on true detection performance... Our data and code are available at: https://doi.org/10.7910/DVN/FR959H

Related papers

• ER-KANs: Efficient and Robust Kolmogorov-Arnold Networks for Data-Scarce Scientific Machine Learning [0.0]
  We show that ChebyKAN's test MSE increases by a factor of 10.6x when training data is corrupted with sigma=0.1 noise.<n> ER-KAN combines three design choices targeting the noisy, data-scarce setting.
  arXiv  Detail & Related papers  (2026-08-14T16:15:37Z)
• Condensing Large-Scale Datasets Directly with Minimal Information Loss [34.43216741538152]
  CIM is a novel, metric-driven framework that abandons the flawed dual-compression paradigm.<n> CIM explicitly quantifies and minimizes the information gap between the original and synthetic datasets.
  arXiv  Detail & Related papers  (2026-07-01T13:21:44Z)
• Methane-Plume Segmentation From Hyperspectral Satellite Imagery Via Multimodal Deep Learning [0.11666234644810893]
  We propose a multimodal deep learning model that integrates a feature-guided methane enhancement mechanism.<n>Our method is evaluated on the MPDataset, where it outperforms the state-of-the-art with improvements of +0.92 in MIoU, +0.87 in MPrecision and +1.01 in Recall.
  arXiv  Detail & Related papers  (2026-06-24T22:12:16Z)
• Benchmarking IoT Time-Series AD with Event-Level Augmentations [34.864214444544565]
  We introduce an evaluation protocol with unified event-level augmentations that simulate real-world issues.<n>We evaluate 14 representative models on five public anomaly datasets.
  arXiv  Detail & Related papers  (2026-02-17T09:45:44Z)
• Function-Space Decoupled Diffusion for Forward and Inverse Modeling in Carbon Capture and Storage [65.51149575007149]
  We present Fun-DDPS, a generative framework that combines function-space diffusion models with differentiable neural operator surrogates for both forward and inverse modeling.<n>Fun-DDPS produces physically consistent realizations free from the high-frequency artifacts observed in joint-state baselines.
  arXiv  Detail & Related papers  (2026-02-12T18:58:12Z)
• Hunting for "Oddballs" with Machine Learning: Detecting Anomalous Exoplanets Using a Deep-Learned Low-Dimensional Representation of Transit Spectra with Autoencoders [35.61099185492068]
  This study explores the application of autoencoder-based machine learning techniques for anomaly detection to identify exoplanet atmospheres with unconventional chemical signatures.<n>We use the Atmospheric Big Challenge (ABC) database to construct an anomaly detection scenario by defining CO2-rich atmospheres as anomalies and CO2-poor atmospheres as the normal class.<n>We benchmarked four different anomaly detection strategies: Autoencoder Reconstruction Loss, One-Class Support Vector Machine (1 class-SVM), K-means Clustering, and Local Outlier Factor (LOF)
  arXiv  Detail & Related papers  (2026-01-05T18:15:53Z)
• A Universal and Robust Framework for Multiple Gas Recognition Based-on Spherical Normalization-Coupled Mahalanobis Algorithm [16.05394499283827]
  This study proposes the Spherical Normalization coupled Mahalanobis (SNM) module, a universal post-processing module for open-set gas recognition.<n>Experiments on the Vergara dataset demonstrate that the Transformer+SNM configuration achieves near-theoretical-limit performance in discriminating among multiple target gases.
  arXiv  Detail & Related papers  (2025-12-28T05:33:05Z)
• Pix2Geomodel: A Next-Generation Reservoir Geomodeling with Property-to-Property Translation [2.004012818482403]
  This study introduces Pix2Geomodel, a novel conditional generative adversarial network (cGAN) framework based on Pix2Pix.<n>It is designed to predict reservoir properties (facies, porosity, permeability, and water saturation) from the Rotliegend reservoir of the Groningen gas field.<n>Results demonstrated high accuracy for facies (PA 0.88, FWIoU 0.85) and water saturation (PA 0.96, FWIoU 0.95), with moderate success for porosity (PA 0.70, FWIoU 0.55) and permeability (PA 0.74, FWIoU 0.60), and robust translation performance
  arXiv  Detail & Related papers  (2025-06-21T15:58:27Z)
• Multi-Platform Methane Plume Detection via Model and Domain Adaptation [0.16678439732526815]
  We develop a spaceborne methane plume classifier using data from the EMIT imaging spectroscopy mission.<n>We use CycleGAN, an unsupervised image-to-image translation technique, to align the data distributions between airborne and spaceborne contexts.
  arXiv  Detail & Related papers  (2025-06-02T00:38:41Z)
• HyperspectralViTs: General Hyperspectral Models for On-board Remote Sensing [21.192836739734435]
  On-board processing of hyperspectral data with machine learning models would enable unprecedented amount of autonomy for a wide range of tasks.<n>This can enable early warning system and could allow new capabilities such as automated scheduling across constellations of satellites.<n>We propose fast and accurate machine learning architectures which support end-to-end training with data of high spectral dimension.
  arXiv  Detail & Related papers  (2024-10-22T17:59:55Z)
• Machine Learning for Methane Detection and Quantification from Space -- A survey [49.7996292123687]
  Methane (CH_4) is a potent anthropogenic greenhouse gas, contributing 86 times more to global warming than Carbon Dioxide (CO_2) over 20 years. This work expands existing information on operational methane point source detection sensors in the Short-Wave Infrared (SWIR) bands. It reviews the state-of-the-art for traditional as well as Machine Learning (ML) approaches.
  arXiv  Detail & Related papers  (2024-08-27T15:03:20Z)
• Unsupervised Fault Detection using SAM with a Moving Window Approach [0.0]
  We present an unsupervised method that uses the high end Segment Anything Model (SAM) and a moving window approach. We aim to overcome these challenges without requiring fine tun ing or labeled data.
  arXiv  Detail & Related papers  (2024-07-08T18:12:29Z)
• Sub-token ViT Embedding via Stochastic Resonance Transformers [51.12001699637727]
  Vision Transformer (ViT) architectures represent images as collections of high-dimensional vectorized tokens, each corresponding to a rectangular non-overlapping patch. We propose a training-free method inspired by "stochastic resonance" The resulting "Stochastic Resonance Transformer" (SRT) retains the rich semantic information of the original representation, but grounds it on a finer-scale spatial domain, partly mitigating the coarse effect of spatial tokenization.
  arXiv  Detail & Related papers  (2023-10-06T01:53:27Z)
• Neural Network Virtual Sensors for Fuel Injection Quantities with Provable Performance Specifications [71.1911136637719]
  We show how provable guarantees can be naturally applied to other real world settings. We show how specific intervals of fuel injection quantities can be targeted to maximize robustness for certain ranges.
  arXiv  Detail & Related papers  (2020-06-30T23:33:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.