European Planetary Science Congress 2018
16–21 September 2018
TU Berlin | Berlin | Germany


Machine Learning for Planetary Science in times of increasing data volume and complexity (co-organized)
Convener: Mario D'Amore  | Co-conveners: Stéphane Erard , Jörn Helbert 
Oral programme
 / Wed, 19 Sep, 08:30–10:00  / Room Neptune
Poster programme
 / Attendance Tue, 18 Sep, 18:15–20:00  / Display Tue, 18 Sep, 08:00–20:00  / Poster area

Machine Learning (ML) is the subfield of computer science that gives "computers the ability to learn without being explicitly programmed." As tactical and strategic planning timelines compress and increasingly large nonlinear datasets are acquired, autonomy and machine intelligence has to play a more critical role in the interpretation of data from planetary exploration missions and laboratory measurements. There is a need for capable systems to be developed that can rapidly and intelligently extract information from these datasets in a manner useful for scientific analysis. The community is starting to respond to this need by applying machine learning approaches on various levels. This session will explore research that leverages machine learning methods to enhance our scientific understanding of planetary data and increase the return of planetary exploration missions. This does include data analysis on ground as well on board to increase autonomy and/or decrease data volume and novel approaches to mission timeline planning.