Retrieving freeze-thaw states using deep learning with remote sensing data in permafrost landscapes
The soil freeze–thaw (FT) cycle is a critical component of the terrestrial cryosphere and plays a significant role in hydrological, ecological, climatic, and biogeochemical processes within permafrost landscapes. The FT states can be monitored with in-situ field measurements, but these procedures ar...
Published in: | International Journal of Applied Earth Observation and Geoinformation |
---|---|
Main Authors: | , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Elsevier
2024
|
Subjects: | |
Online Access: | https://doi.org/10.1016/j.jag.2023.103616 https://doaj.org/article/c64a347503a14307b8a1b1deca693047 |
id |
ftdoajarticles:oai:doaj.org/article:c64a347503a14307b8a1b1deca693047 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:c64a347503a14307b8a1b1deca693047 2024-02-11T10:07:51+01:00 Retrieving freeze-thaw states using deep learning with remote sensing data in permafrost landscapes Yueli Chen Shile Li Lingxiao Wang Magdalena Mittermeier Monique Bernier Ralf Ludwig 2024-02-01T00:00:00Z https://doi.org/10.1016/j.jag.2023.103616 https://doaj.org/article/c64a347503a14307b8a1b1deca693047 EN eng Elsevier http://www.sciencedirect.com/science/article/pii/S1569843223004405 https://doaj.org/toc/1569-8432 1569-8432 doi:10.1016/j.jag.2023.103616 https://doaj.org/article/c64a347503a14307b8a1b1deca693047 International Journal of Applied Earth Observations and Geoinformation, Vol 126, Iss , Pp 103616- (2024) Freeze-thaw state Permafrost landscape Sentinel-1 Backscatter Deep Learning CNN Physical geography GB3-5030 Environmental sciences GE1-350 article 2024 ftdoajarticles https://doi.org/10.1016/j.jag.2023.103616 2024-01-14T01:38:24Z The soil freeze–thaw (FT) cycle is a critical component of the terrestrial cryosphere and plays a significant role in hydrological, ecological, climatic, and biogeochemical processes within permafrost landscapes. The FT states can be monitored with in-situ field measurements, but these procedures are costly and limited to single chosen sites. Remote sensing data provides the opportunity to collect information repeatedly across extensive geographical areas. To explore a more effective way to monitor the FT states in the terrestrial cryosphere, in this study, we used microwave and optical remote sensing data and introduced the Deep Learning approach to simulate the soil FT states in the western part of Nunavik, Canada.Two networks, Multilayer Perceptron (MLP) and Convolutional Neural Network (CNN), were trained and tested with over 35,000 and approximately 54,000 randomly selected data samples, respectively. The trained CNN networks outperformed the MLP networks, achieving the highest testing accuracy of 95.67% and the highest validation accuracy of 87.28% based on ground truth data from 32 measurement stations from all seasons across the year. This study proposed the reference periods concept for convenient labeling in data preparation and tested different combinations of influence variables to achieve better transferability of the method for future studies. Our findings offer a more effective way to monitor FT states in the terrestrial cryosphere, offering valuable insights into the consequences of climate change on permafrost landscapes. Moreover, the suggested deep learning approach can be easily expanded when additional input sources are accessible. This expansion has the potential to further improve the model's performance for the FT retrieval. Article in Journal/Newspaper permafrost Nunavik Directory of Open Access Journals: DOAJ Articles Nunavik International Journal of Applied Earth Observation and Geoinformation 126 103616 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Freeze-thaw state Permafrost landscape Sentinel-1 Backscatter Deep Learning CNN Physical geography GB3-5030 Environmental sciences GE1-350 |
spellingShingle |
Freeze-thaw state Permafrost landscape Sentinel-1 Backscatter Deep Learning CNN Physical geography GB3-5030 Environmental sciences GE1-350 Yueli Chen Shile Li Lingxiao Wang Magdalena Mittermeier Monique Bernier Ralf Ludwig Retrieving freeze-thaw states using deep learning with remote sensing data in permafrost landscapes |
topic_facet |
Freeze-thaw state Permafrost landscape Sentinel-1 Backscatter Deep Learning CNN Physical geography GB3-5030 Environmental sciences GE1-350 |
description |
The soil freeze–thaw (FT) cycle is a critical component of the terrestrial cryosphere and plays a significant role in hydrological, ecological, climatic, and biogeochemical processes within permafrost landscapes. The FT states can be monitored with in-situ field measurements, but these procedures are costly and limited to single chosen sites. Remote sensing data provides the opportunity to collect information repeatedly across extensive geographical areas. To explore a more effective way to monitor the FT states in the terrestrial cryosphere, in this study, we used microwave and optical remote sensing data and introduced the Deep Learning approach to simulate the soil FT states in the western part of Nunavik, Canada.Two networks, Multilayer Perceptron (MLP) and Convolutional Neural Network (CNN), were trained and tested with over 35,000 and approximately 54,000 randomly selected data samples, respectively. The trained CNN networks outperformed the MLP networks, achieving the highest testing accuracy of 95.67% and the highest validation accuracy of 87.28% based on ground truth data from 32 measurement stations from all seasons across the year. This study proposed the reference periods concept for convenient labeling in data preparation and tested different combinations of influence variables to achieve better transferability of the method for future studies. Our findings offer a more effective way to monitor FT states in the terrestrial cryosphere, offering valuable insights into the consequences of climate change on permafrost landscapes. Moreover, the suggested deep learning approach can be easily expanded when additional input sources are accessible. This expansion has the potential to further improve the model's performance for the FT retrieval. |
format |
Article in Journal/Newspaper |
author |
Yueli Chen Shile Li Lingxiao Wang Magdalena Mittermeier Monique Bernier Ralf Ludwig |
author_facet |
Yueli Chen Shile Li Lingxiao Wang Magdalena Mittermeier Monique Bernier Ralf Ludwig |
author_sort |
Yueli Chen |
title |
Retrieving freeze-thaw states using deep learning with remote sensing data in permafrost landscapes |
title_short |
Retrieving freeze-thaw states using deep learning with remote sensing data in permafrost landscapes |
title_full |
Retrieving freeze-thaw states using deep learning with remote sensing data in permafrost landscapes |
title_fullStr |
Retrieving freeze-thaw states using deep learning with remote sensing data in permafrost landscapes |
title_full_unstemmed |
Retrieving freeze-thaw states using deep learning with remote sensing data in permafrost landscapes |
title_sort |
retrieving freeze-thaw states using deep learning with remote sensing data in permafrost landscapes |
publisher |
Elsevier |
publishDate |
2024 |
url |
https://doi.org/10.1016/j.jag.2023.103616 https://doaj.org/article/c64a347503a14307b8a1b1deca693047 |
geographic |
Nunavik |
geographic_facet |
Nunavik |
genre |
permafrost Nunavik |
genre_facet |
permafrost Nunavik |
op_source |
International Journal of Applied Earth Observations and Geoinformation, Vol 126, Iss , Pp 103616- (2024) |
op_relation |
http://www.sciencedirect.com/science/article/pii/S1569843223004405 https://doaj.org/toc/1569-8432 1569-8432 doi:10.1016/j.jag.2023.103616 https://doaj.org/article/c64a347503a14307b8a1b1deca693047 |
op_doi |
https://doi.org/10.1016/j.jag.2023.103616 |
container_title |
International Journal of Applied Earth Observation and Geoinformation |
container_volume |
126 |
container_start_page |
103616 |
_version_ |
1790606658718662656 |