Automated Identification of Thermokarst Lakes Using Machine Learning in the Ice-Rich Permafrost Landscape of Central Yakutia (Eastern Siberia)
The current rate and magnitude of temperature rise in the Arctic are disproportionately high compared to global averages. Along with other natural and anthropogenic disturbances, this warming has caused widespread permafrost degradation and soil subsidence, resulting in the formation of thermokarst...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , , , |
Format: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2023
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs15051226 |
id |
ftmdpi:oai:mdpi.com:/2072-4292/15/5/1226/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/2072-4292/15/5/1226/ 2023-08-20T04:04:14+02:00 Automated Identification of Thermokarst Lakes Using Machine Learning in the Ice-Rich Permafrost Landscape of Central Yakutia (Eastern Siberia) Lara Hughes-Allen Frédéric Bouchard Antoine Séjourné Gabriel Fougeron Emmanuel Léger agris 2023-02-23 application/pdf https://doi.org/10.3390/rs15051226 EN eng Multidisciplinary Digital Publishing Institute Environmental Remote Sensing https://dx.doi.org/10.3390/rs15051226 https://creativecommons.org/licenses/by/4.0/ Remote Sensing; Volume 15; Issue 5; Pages: 1226 Mask R-CNN remote sensing Yedoma permafrost thermokarst greenhouse gas emissions Text 2023 ftmdpi https://doi.org/10.3390/rs15051226 2023-08-01T08:57:07Z The current rate and magnitude of temperature rise in the Arctic are disproportionately high compared to global averages. Along with other natural and anthropogenic disturbances, this warming has caused widespread permafrost degradation and soil subsidence, resulting in the formation of thermokarst (thaw) lakes in areas of ice-rich permafrost. These lakes are hotspots of greenhouse gas emissions (CO2 and CH4), but with substantial spatial and temporal heterogeneity across Arctic and sub-Arctic regions. In Central Yakutia (Eastern Siberia, Russia), nearly half of the landscape has been affected by thermokarst processes since the early Holocene, resulting in the formation of more than 10,000 partly drained lake depressions (alas lakes). It is not yet clear how recent changes in temperature and precipitation will affect existing lakes and the formation of new thermokarst lakes. A multi-decadal remote sensing analysis of lake formation and development was conducted for two large study areas (~1200 km2 each) in Central Yakutia. Mask Region-Based Convolutional Neural Networks (R-CNN) instance segmentation was used to semi-automate lake detection in Satellite pour l’Observation de la Terre (SPOT) and declassified US military (CORONA) images (1967–2019). Using these techniques, we quantified changes in lake surface area for three different lake types (unconnected alas lake, connected alas lake, and recent thermokarst lake) since the 1960s. Our results indicate that unconnected alas lakes are the dominant lake type, both in the number of lakes and total surface area coverage. Unconnected alas lakes appear to be more susceptible to changes in precipitation compared to the other two lake types. The majority of recent thermokarst lakes form within 1 km of observable human disturbance and their surface area is directly related to air temperature increases. These results suggest that climate change and human disturbances are having a strong impact on the landscape and hydrology of Central Yakutia. This will likely affect ... Text Arctic Climate change Ice permafrost Thermokarst Yakutia Siberia MDPI Open Access Publishing Arctic Remote Sensing 15 5 1226 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
Mask R-CNN remote sensing Yedoma permafrost thermokarst greenhouse gas emissions |
spellingShingle |
Mask R-CNN remote sensing Yedoma permafrost thermokarst greenhouse gas emissions Lara Hughes-Allen Frédéric Bouchard Antoine Séjourné Gabriel Fougeron Emmanuel Léger Automated Identification of Thermokarst Lakes Using Machine Learning in the Ice-Rich Permafrost Landscape of Central Yakutia (Eastern Siberia) |
topic_facet |
Mask R-CNN remote sensing Yedoma permafrost thermokarst greenhouse gas emissions |
description |
The current rate and magnitude of temperature rise in the Arctic are disproportionately high compared to global averages. Along with other natural and anthropogenic disturbances, this warming has caused widespread permafrost degradation and soil subsidence, resulting in the formation of thermokarst (thaw) lakes in areas of ice-rich permafrost. These lakes are hotspots of greenhouse gas emissions (CO2 and CH4), but with substantial spatial and temporal heterogeneity across Arctic and sub-Arctic regions. In Central Yakutia (Eastern Siberia, Russia), nearly half of the landscape has been affected by thermokarst processes since the early Holocene, resulting in the formation of more than 10,000 partly drained lake depressions (alas lakes). It is not yet clear how recent changes in temperature and precipitation will affect existing lakes and the formation of new thermokarst lakes. A multi-decadal remote sensing analysis of lake formation and development was conducted for two large study areas (~1200 km2 each) in Central Yakutia. Mask Region-Based Convolutional Neural Networks (R-CNN) instance segmentation was used to semi-automate lake detection in Satellite pour l’Observation de la Terre (SPOT) and declassified US military (CORONA) images (1967–2019). Using these techniques, we quantified changes in lake surface area for three different lake types (unconnected alas lake, connected alas lake, and recent thermokarst lake) since the 1960s. Our results indicate that unconnected alas lakes are the dominant lake type, both in the number of lakes and total surface area coverage. Unconnected alas lakes appear to be more susceptible to changes in precipitation compared to the other two lake types. The majority of recent thermokarst lakes form within 1 km of observable human disturbance and their surface area is directly related to air temperature increases. These results suggest that climate change and human disturbances are having a strong impact on the landscape and hydrology of Central Yakutia. This will likely affect ... |
format |
Text |
author |
Lara Hughes-Allen Frédéric Bouchard Antoine Séjourné Gabriel Fougeron Emmanuel Léger |
author_facet |
Lara Hughes-Allen Frédéric Bouchard Antoine Séjourné Gabriel Fougeron Emmanuel Léger |
author_sort |
Lara Hughes-Allen |
title |
Automated Identification of Thermokarst Lakes Using Machine Learning in the Ice-Rich Permafrost Landscape of Central Yakutia (Eastern Siberia) |
title_short |
Automated Identification of Thermokarst Lakes Using Machine Learning in the Ice-Rich Permafrost Landscape of Central Yakutia (Eastern Siberia) |
title_full |
Automated Identification of Thermokarst Lakes Using Machine Learning in the Ice-Rich Permafrost Landscape of Central Yakutia (Eastern Siberia) |
title_fullStr |
Automated Identification of Thermokarst Lakes Using Machine Learning in the Ice-Rich Permafrost Landscape of Central Yakutia (Eastern Siberia) |
title_full_unstemmed |
Automated Identification of Thermokarst Lakes Using Machine Learning in the Ice-Rich Permafrost Landscape of Central Yakutia (Eastern Siberia) |
title_sort |
automated identification of thermokarst lakes using machine learning in the ice-rich permafrost landscape of central yakutia (eastern siberia) |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2023 |
url |
https://doi.org/10.3390/rs15051226 |
op_coverage |
agris |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic Climate change Ice permafrost Thermokarst Yakutia Siberia |
genre_facet |
Arctic Climate change Ice permafrost Thermokarst Yakutia Siberia |
op_source |
Remote Sensing; Volume 15; Issue 5; Pages: 1226 |
op_relation |
Environmental Remote Sensing https://dx.doi.org/10.3390/rs15051226 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/rs15051226 |
container_title |
Remote Sensing |
container_volume |
15 |
container_issue |
5 |
container_start_page |
1226 |
_version_ |
1774714639798501376 |