Mapping Onshore CH<sub>4</sub> Seeps in Western Siberian Floodplains Using Convolutional Neural Network
Onshore seeps are recognized as strong sources of methane (CH<sub>4</sub>), the second most important greenhouse gas. Seeps actively emitting CH<sub>4</sub> were recently found in floodplains of West Siberian rivers. Despite the origin of CH<sub>4</sub> in these s...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/11/2661 |
| _version_ | 1797491819206934528 |
|---|---|
| author | Irina Terentieva Ilya Filippov Aleksandr Sabrekov Mikhail Glagolev |
| author_facet | Irina Terentieva Ilya Filippov Aleksandr Sabrekov Mikhail Glagolev |
| author_sort | Irina Terentieva |
| collection | DOAJ |
| description | Onshore seeps are recognized as strong sources of methane (CH<sub>4</sub>), the second most important greenhouse gas. Seeps actively emitting CH<sub>4</sub> were recently found in floodplains of West Siberian rivers. Despite the origin of CH<sub>4</sub> 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<sup>2</sup> 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<sub>4</sub> flux in entire Western Siberia. |
| first_indexed | 2024-03-10T00:54:44Z |
| format | Article |
| id | doaj.art-5ac33a516aba4378a67d66cf47a95706 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T00:54:44Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-5ac33a516aba4378a67d66cf47a957062023-11-23T14:45:23ZengMDPI AGRemote Sensing2072-42922022-06-011411266110.3390/rs14112661Mapping Onshore CH<sub>4</sub> Seeps in Western Siberian Floodplains Using Convolutional Neural NetworkIrina Terentieva0Ilya Filippov1Aleksandr Sabrekov2Mikhail Glagolev3A.N. Severtsov Institute of Ecology and Evolution, Russian Academy of Sciences, Moscow 119071, RussiaA.N. Severtsov Institute of Ecology and Evolution, Russian Academy of Sciences, Moscow 119071, RussiaA.N. Severtsov Institute of Ecology and Evolution, Russian Academy of Sciences, Moscow 119071, RussiaA.N. Severtsov Institute of Ecology and Evolution, Russian Academy of Sciences, Moscow 119071, RussiaOnshore seeps are recognized as strong sources of methane (CH<sub>4</sub>), the second most important greenhouse gas. Seeps actively emitting CH<sub>4</sub> were recently found in floodplains of West Siberian rivers. Despite the origin of CH<sub>4</sub> 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<sup>2</sup> 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<sub>4</sub> flux in entire Western Siberia.https://www.mdpi.com/2072-4292/14/11/2661Western Siberiaseepsfloodplainsmethane emissionconvolutional neural networkssentinel-2 |
| spellingShingle | Irina Terentieva Ilya Filippov Aleksandr Sabrekov Mikhail Glagolev Mapping Onshore CH<sub>4</sub> Seeps in Western Siberian Floodplains Using Convolutional Neural Network Remote Sensing Western Siberia seeps floodplains methane emission convolutional neural networks sentinel-2 |
| title | Mapping Onshore CH<sub>4</sub> Seeps in Western Siberian Floodplains Using Convolutional Neural Network |
| title_full | Mapping Onshore CH<sub>4</sub> Seeps in Western Siberian Floodplains Using Convolutional Neural Network |
| title_fullStr | Mapping Onshore CH<sub>4</sub> Seeps in Western Siberian Floodplains Using Convolutional Neural Network |
| title_full_unstemmed | Mapping Onshore CH<sub>4</sub> Seeps in Western Siberian Floodplains Using Convolutional Neural Network |
| title_short | Mapping Onshore CH<sub>4</sub> Seeps in Western Siberian Floodplains Using Convolutional Neural Network |
| title_sort | mapping onshore ch sub 4 sub seeps in western siberian floodplains using convolutional neural network |
| topic | Western Siberia seeps floodplains methane emission convolutional neural networks sentinel-2 |
| url | https://www.mdpi.com/2072-4292/14/11/2661 |
| work_keys_str_mv | AT irinaterentieva mappingonshorechsub4subseepsinwesternsiberianfloodplainsusingconvolutionalneuralnetwork AT ilyafilippov mappingonshorechsub4subseepsinwesternsiberianfloodplainsusingconvolutionalneuralnetwork AT aleksandrsabrekov mappingonshorechsub4subseepsinwesternsiberianfloodplainsusingconvolutionalneuralnetwork AT mikhailglagolev mappingonshorechsub4subseepsinwesternsiberianfloodplainsusingconvolutionalneuralnetwork |