Thematic map creation is a process that implies several steps to be accomplished regardless of the type of the map to be produced, starting from data collection, through data exploitation and ending with maps publication as print, image, and GIS format. An example are geological, lithological, and geomorphological maps, in which most of the highest time-consuming tasks are those related to the discretization of single objects by identifying a set of unique characteristics that describe uniquely those objects. Commonly these tasks introduce interpretative biases due to the different experience of the mappers who's performing it. In this setting, Deep Learning Computer Vision techniques could play a key-role but lack the availability of a complete set of tools specific for planetary mapping. The aim of this work is to develop a comprehensive set of ready-to-use tools for landforms mapping, in which users have full access to the workflow and over all the processes involved, granting complete control and customization capabilities. In this work are presented both the developed tools and the approach that has been used and that is based on consolidated Deep Learning methodologies and open-source libraries commonly applied in other fields of Computer Vision. The toolset and the approach presented have been tested in the science case of mapping sinkhole-like landforms on Mars and results are presented.

The Europlanet H2020 program started on 1/9/2015 for 4 years. It includes an activity to adapt Virtual Observatory (VO) techniques to Planetary Science data called VESPA. The objective is to facilitate searches in big archives as well as sparse databases, to provide simple data access and on-line visualization, and to allow small data providers to make their data available in an interoperable environment with minimum effort. The VESPA system has been hugely improved during the first three years of Europlanet H2020: the infrastructure has been upgraded to describe data in many fields more accurately; the main user search interface (http://vespa.obspm.fr) has been redesigned to provide more flexibility; alternative ways to access Planetary Science data services from VO tools have been implemented; VO tools are being improved to handle specificities of Solar System data, e.g. measurements in reflected light, coordinate systems, etc. Current steps include the development of a connection between the VO world and GIS tools, and integration of Heliophysics, planetary plasmas, and mineral spectroscopy data to support of the analysis of observations. Existing data services have been updated, and new ones have been designed. The global objective is already overstepped, with 42 services open (including ESA’s PSA) and ~15 more being finalized. A procedure to install data services has been documented, and hands-on sessions are organized twice a year at EGU and EPSC; this is intended to favour the installation of services by individual research teams, e.g. to distribute derived data related to a published study. In complement, regular discussions are held with big data providers, starting with space agencies (IPDA). Common projects with PDS have been engaged, with the goal to connect PDS4 and EPN-TAP based on a local data dictionary. In parallel, a Solar System Interest Group has been established in IVOA; the goal is here to adapt existing astronomy standards to Planetary Science. The Europlanet 2020 Research Infrastructure project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 654208. [1] Erard et al 2014, Astronomy & Computing 7-8, 71-80. http://arxiv.org/abs/1407.4886