99749b06-345e-4aef-ae4e-d18995f46a75 Dataseries German Aerospace Center (DLR) geoservice@dlr.de 2025-06-12T11:30:21 ISO 19115-1:2014/19139 EPSG:3031 PolarLakes - Sentinel-1/2 - Antarctica, Bi-weekly/Annually 2025-06-11T00:00:00 https://geoservice.dlr.de/catalogue/srv/metadata/99749b06-345e-4aef-ae4e-d18995f46a75 The PolarLakes dataset provides bi-weekly observations of supraglacial lakes on Antarctic ice shelves, utilizing imagery from Sentinel-2 and Sentinel-1 to address time series gaps caused by frequent cloud cover. These observations detect the extents of supraglacial lakes with a U-Net model for every two weeks from November to March, with each sensor operating independently before the data is merged. The resulting bi-weekly product reflects the maximum lake extents for the first and second halves of each month. When combined for an entire season, the dataset consolidates all bi-weekly records over these five months, allowing for analysis of the maximum lake extent per season and the frequency of lake formation, which can occur up to ten times (5 months á two weeks). The year indicated in the dataset corresponds to January of the melt season, as this month typically experiences the highest melt rates (e.g., 2023 refers to the season from November 2022 to March 2023). The aggregation of all annual datasets creates a recurrence layer that illustrates the frequency of lake presence throughout the entire observation period, which spans from 2014 to 2024, depending on satellite data availability for each ice shelf. The PolarLakes dataset provides valuable insights into the dynamics of supraglacial lakes and serves as a crucial resource for hydrological and climate modeling. The PolarLakes Dataset provides bi-weekly maximum supraglacial lake extents. This dataset helps to understand bi-weekly changes in surface hydrology on Antarctic ice shelves during austral summer (November to March). Celia Baumhoer German Aerospace Center (DLR) celia.baumhoer@dlr.de https://geoservice.dlr.de/catalogue/srv/api/records/99749b06-345e-4aef-ae4e-d18995f46a75/attachments/PolarLakes_ql.jpg large_thumbnail https://geoservice.dlr.de/catalogue/srv/api/records/99749b06-345e-4aef-ae4e-d18995f46a75/attachments/PolarLakes_ql_s.jpg thumbnail DLR EOC supraglacial lakes Antarctica hydrology ice sheet water deep learning Sentinel-1 Sentinel-2 opendata Hydrography Land cover GEMET - INSPIRE themes, version 1.0 2008-06-01 geonetwork.thesaurus.local.theme.inspire-theme regional Nutzungseinschränkungen: Das DLR ist nicht haftbar für Schäden, die sich aus der Nutzung ergeben. / Use Limitations: DLR not liable for damage resulting from use. There are no limitations on public access to spatial data sets and services. Nutzungsbedingungen: Lizenz, https://creativecommons.org/licenses/by/4.0 / terms of use: https://creativecommons.org/licenses/by/4.0/ {"id": "cc-by/4.0", "name": "Creative Commons Namensnennung – 4.0 International (CC BY 4.0)", "url": "http://dcat-ap.de/def/licenses/cc-by/4.0", "quelle": "Copyright DLR (year of production)"} 20000 environment -180.00 180.00 -90.00 -60.00 2014-11-01 2024-03-31 GeoTiff https://download.geoservice.dlr.de/POLARLAKES/files/ WWW:LINK-1.0-http--link EOC Download Service EOC Download Service https://geoservice.dlr.de/web/datasets/polarlakes WWW:LINK-1.0-http--link EOC Geoservice Dataset EOC Geoservice Dataset Conformity_001 INSPIRE Commission Regulation (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services 2010-12-08 See the referenced specification true PolarLakes maximum lake extents are derived from Sentinel-1 SAR and Sentinel-2 optical imagery between November and March to cover the melt season in Antarctica. A deep neural network detects lake extensions in Sentinel-1 and Sentinel-2 data seperately. For each first (day 1-15) and second (day 16-30/31) half of the month, the detected lake areas are combined to a bi-weekly maximum lake extent. We assessed the accuracy of lake detection with a comprehensive validation. F1-score detection accuracies in Sentinel-1 data is 93% and in Sentinel-2 data 91%.