用跨传感器迁移学习和物理后处理，提升甲烷卫星图像的泄漏检测精度。
Plume Segmentation from MethaneSAT with Cross-Sensor Transfer Learning and Physics-Informed Postprocessing
- 用预训练的掩码R-CNN模型，从航空数据迁移学习来补足卫星标注数据不足。
- 高灵敏度模式召回率达94%，高精度模式准确率达92%，可区分不同排放场景。
- 结合物理规律后处理，适合环境监测与碳排放源追踪任务使用。
自动化识别卫星影像中的单个甲烷泄漏羽流对排放归因与量化至关重要。本文提出一种基于甲烷卫星（MethaneSAT）柱平均干空气甲烷摩尔分数的泄漏检测机器学习框架。针对标注数据稀缺和跨大气与地表条件推理可靠性两大挑战，我们证明：采用ResNet-50骨干的掩码R-CNN在MethaneAIR（甲烷卫星机载版本）和甲烷卫星数据上均优于语义分割的U-Net，像素级F1得分分别提升10.49和5.48。为缓解甲烷卫星数据不足问题，评估三种跨传感器迁移策略，利用甲烷航空飞行数据与合成羽流。以甲烷航空预训练权重微调的掩码R-CNN表现最优，在基线工作点实现实例级精确率0.60、召回率0.98。通过物理信息后处理流程，生成两种操作模式：高灵敏度模式采用形态学滤波与邻近合并，实现精确率0.71、召回率0.94，适用于全面筛查；高精度模式进一步引入分布分类器，实现精确率0.92、召回率0.70，用于可信源定位。人工审查误报样本发现，部分被保守标注排除的情况实为真实甲烷增强，表明报告精确率是真实性能的下限。数据与代码公开于https://doi.org/10.7910/DVN/FR959H。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。