The use of Artificial Intelligence (AI) to analyse and classify planetary datasets has been driven by major breakthroughs in Machine Learning (ML) and Deep Learning (DL), in particular to train algorithms for recognition applied to massive amounts of data. Potential applications of ML in planetary science have exploded in the last decade but bespoke tools for the field are still rare.
Europlanet 2024 RI will develop a number of ML tools based on science cases submitted by the planetary science community. The cases address various science challenges and will be applicable to many planetary datasets, creating higher-level data products that can be deposited, accessed and further analysed through Europlanet 2024 RI’s suite of Virtual Access services. All tools will also be linked via the VA services of VESPA, GMAP and SPIDER (where appropriate).
The main objectives of Europlanet 2024 RI’s ML Joint Research Activity are:
- To develop ML tools, designed for and tested on planetary science cases submitted by the community, and to provide sustainable, open access to the resulting products, together with support documentation.
- To foster wider use of ML technologies in data driven space research, demonstrate ML capabilities and generate a wider discussion on further possible applications of ML.
- To identify scientific and commercial applications for the ML tools developed through the JRA tasks.
Coordinator: Dr Ute Amerstorfer, Österreichische Akademie der Wissenschaften, Institut für Weltraumforschung, Schmiedlstraße 6, 8042 Graz, Austria
Europlanet 2024 RI Machine Learning is led by IWF-OEAW with input from the KNOW Center Graz, the University of Passau, ACRI-ST, DLR, INAF, IAP-CAS and Armagh Observatory and Planetarium.
Europlanet Machine Learning in the news:
Find out more about Europlanet 2024 RI’s other Virtual Access services and tools:
Back to Europlanet 2024 RI Homepage