Supraglacial lake outlines over Northeast Greenland from 2016 to 2022 using deep learning methods based on Sentinel-2 imagery
Fuente:
PANGAEA
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Dataset Open Access |
| Lingua: | en |
| Pubblicazione: |
PANGAEA
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1867168231263830016 |
|---|---|
| author | Lutz, Katrina Bahrami, Zahra Braun, Matthias Holger |
| author_facet | Lutz, Katrina Bahrami, Zahra Braun, Matthias Holger |
| collection | Datos científicos de ciencias marinas y ambientales |
| contents | Supraglacial lakes form annually in surface depressions around the periphery of Greenland. Here, a deep learning method based on U-Net was employed to segment supraglacial lakes in Northeast Greenland on Zachariæ Isstrøm and 79N Glacier over the 2016 to 2022 summer melt seasons (April to September). A deep learning-based cloud segmentation model specifically trained for polar regions was also developed and utilized to remove cloudy images from the supraglacial lake time series. While the deep learning lake segmentation model is able to overcome some of the downfalls of traditional thresholding methods such as false inclusion of shadows and inadaptability to new scenes and atmospheric conditions, it still encounters some problems with large, extensive shadows and with slushy light blue ice on peak melt days. |
| format | Dataset Open Access |
| id | pangaea_https___doi_org_10_1594_PANGAEA_973251 |
| institution | PANGAEA |
| language | en |
| publishDate | 2024 |
| publisher | PANGAEA |
| record_format | pangaea |
| spellingShingle | Supraglacial lake outlines over Northeast Greenland from 2016 to 2022 using deep learning methods based on Sentinel-2 imagery Lutz, Katrina Bahrami, Zahra Braun, Matthias Holger 79°N Glacier; 79NGreenland; Binary Object; deep learning; File content; Greenland; Greenland Ice Sheet/Ocean Interaction: From process understanding to the assessment of a coupled, regional system in change; GROCE2; MULT; Multiple investigations; Northeast Greenland; Sentinel-2; Supraglacial lake area detection according to Lutz et al. (2023); supraglacial lakes; Zachariæ Isstrøm Supraglacial lakes form annually in surface depressions around the periphery of Greenland. Here, a deep learning method based on U-Net was employed to segment supraglacial lakes in Northeast Greenland on Zachariæ Isstrøm and 79N Glacier over the 2016 to 2022 summer melt seasons (April to September). A deep learning-based cloud segmentation model specifically trained for polar regions was also developed and utilized to remove cloudy images from the supraglacial lake time series. While the deep learning lake segmentation model is able to overcome some of the downfalls of traditional thresholding methods such as false inclusion of shadows and inadaptability to new scenes and atmospheric conditions, it still encounters some problems with large, extensive shadows and with slushy light blue ice on peak melt days. |
| title | Supraglacial lake outlines over Northeast Greenland from 2016 to 2022 using deep learning methods based on Sentinel-2 imagery |
| topic | 79°N Glacier; 79NGreenland; Binary Object; deep learning; File content; Greenland; Greenland Ice Sheet/Ocean Interaction: From process understanding to the assessment of a coupled, regional system in change; GROCE2; MULT; Multiple investigations; Northeast Greenland; Sentinel-2; Supraglacial lake area detection according to Lutz et al. (2023); supraglacial lakes; Zachariæ Isstrøm |
| url | https://doi.org/10.1594/PANGAEA.973251 |