پیوندهای مفید
اخبار و اعلانات
آمار
| تعداد نشریات | 127 |
| تعداد شمارهها | 7,237 |
| تعداد مقالات | 77,625 |
| تعداد مشاهده مقاله | 161,094,071 |
| تعداد دریافت فایل اصل مقاله | 120,790,287 |
A Novel Hybrid Deep Learning Model for Methane Plume Detection in Oil and Gas Sectors Using PRISMA Satellite | ||
| Earth Observation and Geomatics Engineering | ||
| دوره 10، شماره 1، مهر 2026، صفحه 51-60 اصل مقاله (460.09 K) | ||
| نوع مقاله: Original Article | ||
| شناسه دیجیتال (DOI): 10.22059/eoge.2026.410068.1214 | ||
| نویسندگان | ||
| Emadoddin Hemmati* 1؛ Mehdi Mokhtarzadeh2 | ||
| 1Faculty of Geodesy and Geomatics Engineering & Remote Sensing Institute, K. N. Toosi University of Technology, Tehran, Iran | ||
| 2Department of Photogrammetry and Remote Sensing, Faculty of Geodesy and Geomatics Engineering, K. N. Toosi University of Technology | ||
| چکیده | ||
| Accurate monitoring of methane (CH₄) emissions from oil and gas infrastructure is critical for near-term climate change mitigation. While hyperspectral satellites like PRISMA provide high-fidelity data, the optimal deep learning architecture for segmenting faint methane plumes remains undetermined. This study provides the first systematic comparison of convolutional and transformer-based models for this task. We evaluate four architectures: an attention-enhanced U-Net++, Segformer, and two novel hybrids – SwinV2-UPP (SwinV2 encoder + U-Net++ decoder) and SwinV2-Former (SwinV2 encoder + MLP decoder). Models are trained on 73 manually delineated methane plumes from 34 PRISMA scenes across global oil and gas basins, augmented to 1,446 patches. SwinV2-UPP achieved the highest F1-score of 0.834, a 4.0% improvement over the convolutional baseline (0.802). Notably, SwinV2-Former achieved state-of-the-art precision of 0.910 – outperforming SwinV2-UPP by 2.5% – demonstrating exceptional false-positive minimization. In zero-shot generalization, SwinV2-UPP maintained the highest F1 (0.725), while SwinV2-Former achieved the best precision (0.857). We reveal a critical architectural trade-off: SwinV2-UPP balances precision and recall (F1=0.834) for comprehensive plume mapping, whereas SwinV2-Former prioritizes high-confidence detection (precision=0.910) for regulatory applications where false positives are costly. These findings provide a framework for selecting optimal deep learning architectures based on specific methane monitoring objectives. | ||
| کلیدواژهها | ||
| Methane؛ Hyperspectral؛ PRISMA؛ Swin؛ CNN | ||
|
آمار تعداد مشاهده مقاله: 14 تعداد دریافت فایل اصل مقاله: 4 |
||
سامانه مدیریت نشریات علمی. قدرت گرفته از سیناوب