https://opara.zih.tu-dresden.de/xmlui/handle/123456789/5679 In “Artificial Intelligence for Cold Regions” (AI-CORE) we will develop a collaborative approach for applying Artificial Intelligence (AI) methods in earth observation and thereby breaking new ground for researching the cryosphere. Rapidly changing ice sheets and thawing permafrost are big societal challenges, hence quantifying these changes and understanding the mechanisms are of major importance. Given the vast extent of polar regions and the availability of exponentially increasing satellite remote sensing data, intelligent data analysis is urgently required to exploit the full information in satellite time series. So far, extensive competences in data science, AI implementation, and processing infrastructures are decentralized and distributed among the individual Helmholtz centers. In the era of big data, cloud computing and extensive earth observation programs, a core challenge is to establish and consolidate a joint platform for AI applications by combining existing competences and infrastructures with new developments serving especially AI applications. Four geo-scientific use cases from cryosphere research will be used to demonstrate the new collaborative AI approach. These use cases are challenging due to diverse, extensive, and inhomogeneous input data and their high relevance is given in the context of climate change. To address these case studies, several AI methods will be developed, tested, evaluated, and implemented in the data processing infrastructure of the project members by combining all distributed capabilities into a joint platform. A “best practice” approach will be identified to solve each of the individual research questions. Once established, this knowledge and the AI-CORE platform can be used even beyond the exemplary use cases to address current and upcoming challenges in data processing, management, data science, and big data. The experience of this collaborative approach will be of very high value for the next research program PoF IV. Furthermore, the networking and knowledge exchange among AI-CORE members will facilitate synergies between methodsbased research and direct AI applications beyond the immediate use cases. 2026-04-05T09:16:13Z https://opara.zih.tu-dresden.de/xmlui/handle/123456789/6056 Manually delineated glacier calving front locations of 27 marine-terminating glaciers from 2013 to 2021 Loebel, Erik; Scheinert, Mirko; Horwath, Martin; Humbert, Angelika; Sohn, Julia; Heidler, Konrad; Liebezeit, Charlotte; Zhu, Xiao Xiang This dataset provides 898 manually delineated glacier calving front positions of 23 Greenland glaciers, two glaciers at the Antarctic Peninsula, one glacier in Svalbard and one glacier in Patagonia from 2013 to 2021. For manual delineation, we used optical Landsat-8 imagery. The dataset is composed of two parts. Firstly we provide ocean masks and frontal positions as Polygon or LineString Shapefiles respectively. Secondly, we provide 1220 input raster subsets (9 layers each) with their corresponding, manually delineated, segmentation masks. Input raster subsets have dimensions of 512 pixels by 512 pixels and are available in both png and georeferenced tif format. These machine learning ready raster subsets are optimized for training and validating artificial neural networks. 2024-01-01T00:00:00Z https://opara.zih.tu-dresden.de/xmlui/handle/123456789/6044 Terminus area change of 17 key glaciers of the Antarctic Peninsula from 2013 to 2023 derived from remote sensing and deep learning Loebel, Erik; Baumhoer, Celia A.; Dietz, Andreas; Scheinert, Mirko; Horwath, Martin Glacier terminus area changes are derived using the rectilinear box method applied to time series of glacier calving front locations. Terminus changes are provided in text file and image format. The following glaciers are included in this data record: Birley Glacier, Bleriot Glacier, Cayley Glacier, Crane Glacier, Dinsmore-Bombardier-Edgeworth Glacier system, Drygalski Glacier, Fleming Glacier, Hariot Glacier, Hektoria-Green-Evans Glacier system, Hugi Glacier, Jorum Glacier, Murphy Wilkinson Glacier, Prospect Glacier, Sjogren Glacier, Stringfellow Glacier, Trooz Glacier and Widdowson Glacier. 2023-01-01T00:00:00Z https://opara.zih.tu-dresden.de/xmlui/handle/123456789/6029 Historical Greenland glacier calving front locations from 1973 until 2013 Liebezeit, Charlotte; Loebel, Erik This product contains 170 Greenland glacier calving front positions from the following glaciers: Hagen Bræ, Helheim Glacier, Kangiata Nunaata Sermia, Nioghalvfjerdsbræ, Tracy Glacier and Zachariae Isstrøm. The glacier calving front positions have been manually derived from multispectral Landsat-8 imagery and are stored in an ESRI shapefile format using the WGS 84 / NSIDC Sea Ice Polar Stereographic North (EPSG:3413) Coordinate Reference System. Hagen Bræ covers the years 1985-2013 and Nioghalvfjerdsbræ between 1985-1994 on a nearly yearly basis. For Zachariae Isstrøm, calving fronts are featured every year between 1985-1993. With two calving fronts per year, except for 1984, Helheim Glacier involves the years 1979-1988. Irregular coverage with up to 3 calving front locations in one year show Kangiata Nunaata Sermia between 1978-2012 and Tracy Glacier covering the years 1973-2013. 2023-01-01T00:00:00Z https://opara.zih.tu-dresden.de/xmlui/handle/123456789/5823 Data product of Greenland glacier calving front locations delineated by deep learning, 2013 to 2021 Loebel, Erik; Scheinert, Mirko; Horwath, Martin; Humbert, Angelika; Sohn, Julia; Heidler, Konrad; Liebezeit, Charlotte; Zhu, Xiao Xiang Glacier calving front positions are derived by applying a deep learning method to multispectral Landsat-8 imagery. The product contains 9243 calving front positions across 23 Greenland outlet glaciers from March 2013 to December 2021. Calving front positions are stored in ESRI shapefile format. Due to the high temporal resolution of this data product, mostly achieving sub-weekly sampling outside polar night, it provides unique opportunities to study seasonal and sub-seasonal terminus changes. The quality of these automatically extracted calving front locations has been validated against three independent validation datasets and is comparable to that of manually digitised fronts. The following glaciers are included in this data product: Kangiata Nunaata Sermia, Helheim Glacier, Kangerdlussuaq Glacier, Jakobshavn Isbræ, Eqip Sermia, Store Glacier, Rink Isbræ, Daugaard Jensen Glacier, Ingia Isbræ, Upernavik Isstrøm, Waltershausen Glacier, Hayes Glacier, Sverdrup Glacier, Kong Oscar Glacier, Døcker Smith Glacier, Harald Molke Bræ, Tracy Glacier, Humboldt Glacier, Zachariae Isstrøm, Nioghalvfjerdsbræ, Hagen Bræ, Academy Glacier and Ryder Glacier. 2023-01-01T00:00:00Z