Artificial Intelligence for Cold Regions (AI-CORE)
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.
This project is open access and publicly accessible.
Collections in this community
Change pattern identification of outlet glaciers in Greenland Outlet glaciers in Greenland experience a combination of seasonal and climate-driven change. Nearby glaciers exhibit very different retreat and advance behavior despite being situated in similar climatic conditions. This ...
Anonymous users may not see all communities or collections. Please log in to see your accessible communities and colletions.
Data product of Greenland glacier calving front locations delineated by deep learning, 2013 to 2021 (Technische Universität Dresden, 2023)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 ...
Manually delineated glacier calving fronts of 23 Greenland and 2 Antarctic outlet glaciers from 2013 to 2021 and source code for automated extraction by deep learning (Technische Universität Dresden, 2022)Supplementary material to the manuscript: Loebel, E., Scheinert, M., Horwath, M., Heidler, K., Christmann, J., Phan, L., Humbert, A., Zhu, X. (2022): Extracting glacier calving fronts by deep learning: the benefit of ...