Mapping Onshore CH 4 Seeps in Western Siberian Floodplains Using Convolutional Neural Network

• Published in: Remote Sensing
• Main Authors: Irina Terentieva, Ilya Filippov, Aleksandr Sabrekov, Mikhail Glagolev
• Format: Article in Journal/Newspaper
• Language: English
• Published: MDPI AG 2022
• Subjects: Western Siberia; seeps; floodplains; methane emission; convolutional neural networks; sentinel-2; Science; Q; ob river; Siberia
• Online Access: https://doi.org/10.3390/rs14112661; https://doaj.org/article/5ac33a516aba4378a67d66cf47a95706

Onshore seeps are recognized as strong sources of methane (CH 4 ), the second most important greenhouse gas. Seeps actively emitting CH 4 were recently found in floodplains of West Siberian rivers. Despite the origin of CH 4 in these seeps is not fully understood, they can make substantial contribution in regional greenhouse gas emission. We used high-resolution satellite Sentinel-2 imagery to estimate seep areas at a regional scale. Convolutional neural network based on U-Net architecture was implemented to overcome difficulties with seep recognition. Ground-based field investigations and unmanned aerial vehicle footage were coupled to provide reliable training dataset. The seep areas were estimated at 2885 km 2 or 1.5% of the studied region; most seep areas were found within the Ob’ river floodplain. The overall accuracy of the final map reached 86.1%. Our study demonstrates that seeps are widespread throughout the region and provides a basis to estimate seep CH 4 flux in entire Western Siberia.