AttMetNet: Attention-Enhanced Deep Neural Network for Methane Plume Detection in Sentinel-2 Satellite Imagery

2025-12-02

AI Summary

Methane plume detection in Sentinel-2 imagery suffers from high false-positive rates due to sensitivity to surface background variability and heterogeneous land cover. Method: We propose the first methane-aware deep learning framework, embedding the Normalized Methane Difference Index (NDMI)—a physics-informed spectral feature—into an attention-enhanced U-Net architecture, and adopting focal loss to improve hard-sample learning. NDMI guides the network to prioritize spectral responses in methane absorption bands, while channel-spatial attention jointly suppresses background interference. Contribution/Results: Evaluated on real-world methane leakage data, our method reduces false positives by 32.7% and improves F1-score by 18.4% over state-of-the-art approaches, achieving an IoU of 0.652. It delivers superior precision–recall trade-off and strong generalization robustness under diverse surface conditions.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Methane is a powerful greenhouse gas that contributes significantly to global warming. Accurate detection of methane emissions is the key to taking timely action and minimizing their impact on climate change. We present AttMetNet, a novel attention-enhanced deep learning framework for methane plume detection with Sentinel-2 satellite imagery. The major challenge in developing a methane detection model is to accurately identify methane plumes from Sentinel-2's B11 and B12 bands while suppressing false positives caused by background variability and diverse land cover types. Traditional detection methods typically depend on the differences or ratios between these bands when comparing the scenes with and without plumes. However, these methods often require verification by a domain expert because they generate numerous false positives. Recent deep learning methods make some improvements using CNN-based architectures, but lack mechanisms to prioritize methane-specific features. AttMetNet introduces a methane-aware architecture that fuses the Normalized Difference Methane Index (NDMI) with an attention-enhanced U-Net. By jointly exploiting NDMI's plume-sensitive cues and attention-driven feature selection, AttMetNet selectively amplifies methane absorption features while suppressing background noise. This integration establishes a first-of-its-kind architecture tailored for robust methane plume detection in real satellite imagery. Additionally, we employ focal loss to address the severe class imbalance arising from both limited positive plume samples and sparse plume pixels within imagery. Furthermore, AttMetNet is trained on the real methane plume dataset, making it more robust to practical scenarios. Extensive experiments show that AttMetNet surpasses recent methods in methane plume detection with a lower false positive rate, better precision recall balance, and higher IoU.

Problem

• Detects methane plumes in Sentinel-2 satellite imagery
• Suppresses false positives from background variability and land cover
• Addresses class imbalance with limited positive plume samples

Innovation

• Attention-enhanced U-Net architecture for methane detection
• Integration of NDMI with deep learning for feature selection
• Focal loss to address class imbalance in plume samples