A Novel Method for Automated Supraglacial Lake Mapping in Antarctica Using Sentinel-1 SAR Imagery and Deep Learning
Supraglacial meltwater accumulation on ice sheets can be a main driver for accelerated ice discharge, mass loss, and global sea-level-rise. With further increasing surface air temperatures, meltwater-induced hydrofracturing, basal sliding, or surface thinning will cumulate and most likely trigger un...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/2/197 |
| _version_ | 1827603072874971136 |
|---|---|
| author | Mariel Dirscherl Andreas J. Dietz Christof Kneisel Claudia Kuenzer |
| author_facet | Mariel Dirscherl Andreas J. Dietz Christof Kneisel Claudia Kuenzer |
| author_sort | Mariel Dirscherl |
| collection | DOAJ |
| description | Supraglacial meltwater accumulation on ice sheets can be a main driver for accelerated ice discharge, mass loss, and global sea-level-rise. With further increasing surface air temperatures, meltwater-induced hydrofracturing, basal sliding, or surface thinning will cumulate and most likely trigger unprecedented ice mass loss on the Greenland and Antarctic ice sheets. While the Greenland surface hydrological network as well as its impacts on ice dynamics and mass balance has been studied in much detail, Antarctic supraglacial lakes remain understudied with a circum-Antarctic record of their spatio-temporal development entirely lacking. This study provides the first automated supraglacial lake extent mapping method using Sentinel-1 synthetic aperture radar (SAR) imagery over Antarctica and complements the developed optical Sentinel-2 supraglacial lake detection algorithm presented in our companion paper. In detail, we propose the use of a modified U-Net for semantic segmentation of supraglacial lakes in single-polarized Sentinel-1 imagery. The convolutional neural network (CNN) is implemented with residual connections for optimized performance as well as an Atrous Spatial Pyramid Pooling (ASPP) module for multiscale feature extraction. The algorithm is trained on 21,200 Sentinel-1 image patches and evaluated in ten spatially or temporally independent test acquisitions. In addition, George VI Ice Shelf is analyzed for intra-annual lake dynamics throughout austral summer 2019/2020 and a decision-level fused Sentinel-1 and Sentinel-2 maximum lake extent mapping product is presented for January 2020 revealing a more complete supraglacial lake coverage (~770 km<sup>2</sup>) than the individual single-sensor products. Classification results confirm the reliability of the proposed workflow with an average Kappa coefficient of 0.925 and a <inline-formula><math display="inline"><semantics><mrow><msub><mi mathvariant="normal">F</mi><mn>1</mn></msub></mrow></semantics></math></inline-formula>-score of 93.0% for the supraglacial water class across all test regions. Furthermore, the algorithm is applied in an additional test region covering supraglacial lakes on the Greenland ice sheet which further highlights the potential for spatio-temporal transferability. Future work involves the integration of more training data as well as intra-annual analyses of supraglacial lake occurrence across the whole continent and with focus on supraglacial lake development throughout a summer melt season and into Antarctic winter. |
| first_indexed | 2024-03-09T05:32:33Z |
| format | Article |
| id | doaj.art-aab7d1569523473baa9ba9baf93ab48c |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T05:32:33Z |
| publishDate | 2021-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-aab7d1569523473baa9ba9baf93ab48c2023-12-03T12:31:52ZengMDPI AGRemote Sensing2072-42922021-01-0113219710.3390/rs13020197A Novel Method for Automated Supraglacial Lake Mapping in Antarctica Using Sentinel-1 SAR Imagery and Deep LearningMariel Dirscherl0Andreas J. Dietz1Christof Kneisel2Claudia Kuenzer3German Remote Sensing Data Center (DFD), German Aerospace Center (DLR), Muenchener Str. 20, 82234 Wessling, GermanyGerman Remote Sensing Data Center (DFD), German Aerospace Center (DLR), Muenchener Str. 20, 82234 Wessling, GermanyInstitute of Geography and Geology, University Wuerzburg, Am Hubland, 97074 Wuerzburg, GermanyGerman Remote Sensing Data Center (DFD), German Aerospace Center (DLR), Muenchener Str. 20, 82234 Wessling, GermanySupraglacial meltwater accumulation on ice sheets can be a main driver for accelerated ice discharge, mass loss, and global sea-level-rise. With further increasing surface air temperatures, meltwater-induced hydrofracturing, basal sliding, or surface thinning will cumulate and most likely trigger unprecedented ice mass loss on the Greenland and Antarctic ice sheets. While the Greenland surface hydrological network as well as its impacts on ice dynamics and mass balance has been studied in much detail, Antarctic supraglacial lakes remain understudied with a circum-Antarctic record of their spatio-temporal development entirely lacking. This study provides the first automated supraglacial lake extent mapping method using Sentinel-1 synthetic aperture radar (SAR) imagery over Antarctica and complements the developed optical Sentinel-2 supraglacial lake detection algorithm presented in our companion paper. In detail, we propose the use of a modified U-Net for semantic segmentation of supraglacial lakes in single-polarized Sentinel-1 imagery. The convolutional neural network (CNN) is implemented with residual connections for optimized performance as well as an Atrous Spatial Pyramid Pooling (ASPP) module for multiscale feature extraction. The algorithm is trained on 21,200 Sentinel-1 image patches and evaluated in ten spatially or temporally independent test acquisitions. In addition, George VI Ice Shelf is analyzed for intra-annual lake dynamics throughout austral summer 2019/2020 and a decision-level fused Sentinel-1 and Sentinel-2 maximum lake extent mapping product is presented for January 2020 revealing a more complete supraglacial lake coverage (~770 km<sup>2</sup>) than the individual single-sensor products. Classification results confirm the reliability of the proposed workflow with an average Kappa coefficient of 0.925 and a <inline-formula><math display="inline"><semantics><mrow><msub><mi mathvariant="normal">F</mi><mn>1</mn></msub></mrow></semantics></math></inline-formula>-score of 93.0% for the supraglacial water class across all test regions. Furthermore, the algorithm is applied in an additional test region covering supraglacial lakes on the Greenland ice sheet which further highlights the potential for spatio-temporal transferability. Future work involves the integration of more training data as well as intra-annual analyses of supraglacial lake occurrence across the whole continent and with focus on supraglacial lake development throughout a summer melt season and into Antarctic winter.https://www.mdpi.com/2072-4292/13/2/197AntarcticaAntarctic ice sheetsupraglacial lakesice sheet hydrologySentinel-1remote sensing |
| spellingShingle | Mariel Dirscherl Andreas J. Dietz Christof Kneisel Claudia Kuenzer A Novel Method for Automated Supraglacial Lake Mapping in Antarctica Using Sentinel-1 SAR Imagery and Deep Learning Remote Sensing Antarctica Antarctic ice sheet supraglacial lakes ice sheet hydrology Sentinel-1 remote sensing |
| title | A Novel Method for Automated Supraglacial Lake Mapping in Antarctica Using Sentinel-1 SAR Imagery and Deep Learning |
| title_full | A Novel Method for Automated Supraglacial Lake Mapping in Antarctica Using Sentinel-1 SAR Imagery and Deep Learning |
| title_fullStr | A Novel Method for Automated Supraglacial Lake Mapping in Antarctica Using Sentinel-1 SAR Imagery and Deep Learning |
| title_full_unstemmed | A Novel Method for Automated Supraglacial Lake Mapping in Antarctica Using Sentinel-1 SAR Imagery and Deep Learning |
| title_short | A Novel Method for Automated Supraglacial Lake Mapping in Antarctica Using Sentinel-1 SAR Imagery and Deep Learning |
| title_sort | novel method for automated supraglacial lake mapping in antarctica using sentinel 1 sar imagery and deep learning |
| topic | Antarctica Antarctic ice sheet supraglacial lakes ice sheet hydrology Sentinel-1 remote sensing |
| url | https://www.mdpi.com/2072-4292/13/2/197 |
| work_keys_str_mv | AT marieldirscherl anovelmethodforautomatedsupraglaciallakemappinginantarcticausingsentinel1sarimageryanddeeplearning AT andreasjdietz anovelmethodforautomatedsupraglaciallakemappinginantarcticausingsentinel1sarimageryanddeeplearning AT christofkneisel anovelmethodforautomatedsupraglaciallakemappinginantarcticausingsentinel1sarimageryanddeeplearning AT claudiakuenzer anovelmethodforautomatedsupraglaciallakemappinginantarcticausingsentinel1sarimageryanddeeplearning AT marieldirscherl novelmethodforautomatedsupraglaciallakemappinginantarcticausingsentinel1sarimageryanddeeplearning AT andreasjdietz novelmethodforautomatedsupraglaciallakemappinginantarcticausingsentinel1sarimageryanddeeplearning AT christofkneisel novelmethodforautomatedsupraglaciallakemappinginantarcticausingsentinel1sarimageryanddeeplearning AT claudiakuenzer novelmethodforautomatedsupraglaciallakemappinginantarcticausingsentinel1sarimageryanddeeplearning |