Mapping Onshore CH 4 Seeps in Western Siberian Floodplains Using Convolutional Neural Network
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 contribut...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2022
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs14112661 https://doaj.org/article/5ac33a516aba4378a67d66cf47a95706 |
id |
ftdoajarticles:oai:doaj.org/article:5ac33a516aba4378a67d66cf47a95706 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:5ac33a516aba4378a67d66cf47a95706 2023-05-15T17:48:47+02:00 Mapping Onshore CH 4 Seeps in Western Siberian Floodplains Using Convolutional Neural Network Irina Terentieva Ilya Filippov Aleksandr Sabrekov Mikhail Glagolev 2022-06-01T00:00:00Z https://doi.org/10.3390/rs14112661 https://doaj.org/article/5ac33a516aba4378a67d66cf47a95706 EN eng MDPI AG https://www.mdpi.com/2072-4292/14/11/2661 https://doaj.org/toc/2072-4292 doi:10.3390/rs14112661 2072-4292 https://doaj.org/article/5ac33a516aba4378a67d66cf47a95706 Remote Sensing, Vol 14, Iss 2661, p 2661 (2022) Western Siberia seeps floodplains methane emission convolutional neural networks sentinel-2 Science Q article 2022 ftdoajarticles https://doi.org/10.3390/rs14112661 2022-12-31T02:30:10Z 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. Article in Journal/Newspaper ob river Siberia Directory of Open Access Journals: DOAJ Articles Remote Sensing 14 11 2661 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Western Siberia seeps floodplains methane emission convolutional neural networks sentinel-2 Science Q |
spellingShingle |
Western Siberia seeps floodplains methane emission convolutional neural networks sentinel-2 Science Q Irina Terentieva Ilya Filippov Aleksandr Sabrekov Mikhail Glagolev Mapping Onshore CH 4 Seeps in Western Siberian Floodplains Using Convolutional Neural Network |
topic_facet |
Western Siberia seeps floodplains methane emission convolutional neural networks sentinel-2 Science Q |
description |
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. |
format |
Article in Journal/Newspaper |
author |
Irina Terentieva Ilya Filippov Aleksandr Sabrekov Mikhail Glagolev |
author_facet |
Irina Terentieva Ilya Filippov Aleksandr Sabrekov Mikhail Glagolev |
author_sort |
Irina Terentieva |
title |
Mapping Onshore CH 4 Seeps in Western Siberian Floodplains Using Convolutional Neural Network |
title_short |
Mapping Onshore CH 4 Seeps in Western Siberian Floodplains Using Convolutional Neural Network |
title_full |
Mapping Onshore CH 4 Seeps in Western Siberian Floodplains Using Convolutional Neural Network |
title_fullStr |
Mapping Onshore CH 4 Seeps in Western Siberian Floodplains Using Convolutional Neural Network |
title_full_unstemmed |
Mapping Onshore CH 4 Seeps in Western Siberian Floodplains Using Convolutional Neural Network |
title_sort |
mapping onshore ch 4 seeps in western siberian floodplains using convolutional neural network |
publisher |
MDPI AG |
publishDate |
2022 |
url |
https://doi.org/10.3390/rs14112661 https://doaj.org/article/5ac33a516aba4378a67d66cf47a95706 |
genre |
ob river Siberia |
genre_facet |
ob river Siberia |
op_source |
Remote Sensing, Vol 14, Iss 2661, p 2661 (2022) |
op_relation |
https://www.mdpi.com/2072-4292/14/11/2661 https://doaj.org/toc/2072-4292 doi:10.3390/rs14112661 2072-4292 https://doaj.org/article/5ac33a516aba4378a67d66cf47a95706 |
op_doi |
https://doi.org/10.3390/rs14112661 |
container_title |
Remote Sensing |
container_volume |
14 |
container_issue |
11 |
container_start_page |
2661 |
_version_ |
1766154940399484928 |