Multi-Platform Methane Plume Detection via Model and Domain Adaptation

2025-06-02

AI Summary

To address the degradation in methane plume detection performance across airborne (AVIRIS-NG) and spaceborne (EMIT) hyperspectral platforms—caused by fundamental differences in imaging mechanisms—this paper proposes an end-to-end cross-platform detection framework integrating domain translation and transfer learning. We introduce CycleGAN for the first time to perform unsupervised domain alignment between airborne and spaceborne hyperspectral methane data, mitigating distribution shift. The framework synergistically combines a pre-trained CNN with hyperspectral matched filtering to jointly optimize feature-level and pixel-level representations. Evaluated on EMIT data, our method significantly outperforms a spaceborne-specific classifier trained in isolation, achieving substantial gains in detection accuracy and robustness. This work establishes a scalable, reusable cross-platform modeling paradigm for multi-source remote sensing in collaborative carbon monitoring.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

Prioritizing methane for near-term climate action is crucial due to its significant impact on global warming. Previous work used columnwise matched filter products from the airborne AVIRIS-NG imaging spectrometer to detect methane plume sources; convolutional neural networks (CNNs) discerned anthropogenic methane plumes from false positive enhancements. However, as an increasing number of remote sensing platforms are used for methane plume detection, there is a growing need to address cross-platform alignment. In this work, we describe model- and data-driven machine learning approaches that leverage airborne observations to improve spaceborne methane plume detection, reconciling the distributional shifts inherent with performing the same task across platforms. We develop a spaceborne methane plume classifier using data from the EMIT imaging spectroscopy mission. We refine classifiers trained on airborne imagery from AVIRIS-NG campaigns using transfer learning, outperforming the standalone spaceborne model. Finally, we use CycleGAN, an unsupervised image-to-image translation technique, to align the data distributions between airborne and spaceborne contexts. Translating spaceborne EMIT data to the airborne AVIRIS-NG domain using CycleGAN and applying airborne classifiers directly yields the best plume detection results. This methodology is useful not only for data simulation, but also for direct data alignment. Though demonstrated on the task of methane plume detection, our work more broadly demonstrates a data-driven approach to align related products obtained from distinct remote sensing instruments.

Problem

• Improve spaceborne methane plume detection using airborne data
• Address cross-platform alignment for methane plume detection
• Align data distributions between airborne and spaceborne contexts

Innovation

• Transfer learning refines airborne-trained classifiers
• CycleGAN aligns airborne and spaceborne data distributions
• Unsupervised image translation enhances plume detection