This is an old revision of the document!
Table of Contents
General introduction to our ML activity
Objectives
The main objectives of the machine learning work package are:
- To develop machine learning (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
The goal is to build a multipurpose toolset for ML-based data analysis that will be applicable to a range of scientific research questions in planetary science with minor or easily-achievable customization efforts.
The tools will be shared and made accessible to the wider planetary science community through this webpage, the ML Portal. The ML work package will also provide documentation and tutorials, to support the beneficiaries and the users of the ML tools.
Work Package Beneficiaries and Partners
| Work Package Beneficiaries and Partners |
|
| ACRI-ST | ACRI-ST, France |
| AOP | Armagh Observatory and Planetarium, Ireland |
| DLR | Deutsches Zentrum für Luft- und Raumfahrt, Germany |
| KNOW | Know-Center GmbH, Austria |
| IAP-CAS | Institute of Atmospheric Physics, Academy of Sciences of Czech Republic, Czech Republic |
| INAF | National Institute for Astrophysics, Italy |
| IWF-OEAW | Space Research Institute, Austrian Academy of Sciences, Austria |
| LMSU | M.V. Lomonosov Moscow State University, Russia |
| UNIPASSAU | University of Passau, Germany |
Science Cases
During the proposal phase of Europlanet 2024 RI, the scientific community was asked to submit so-called science cases - problems where machine learning approaches seem promising. The following science cases where selected and are now worked on in our work package.
| Proposer | Science Case |
|---|---|
| IAP-CAS | Detection of plasma boundary crossings at planetary magnetospheres and solar wind (magnetospheres, plasma environments and space weather) |
| Classification of plasma wave emissions in electromagnetic spectra (planetary and solar radio emissions) | |
| INAF | Mineral identification via reflectance spectra (planetary surfaces/compositions/interiors) [possible applications foreseen in GMAP] |
| DLR | Classification of surface composition on the surface of Mercury (planetary surfaces/compositions/interiors) [resulting data products can be used for GMAP] |
| AOP | Abundance of asteroids in Earth-like orbits from STEREO images (small bodies, asteroids & comets) |
| GMAP | Automatic recognition and analysis of planetary surface features (planetary surfaces/compositions/interiors) |
| IWF-OEAW | Detection and classification of CMEs and CIRs in in-situ solar wind data (magnetospheres, plasma environments and space weather) |
| LMSU | Search for magnetopause/shockwave crossings on Mercury based on MESSENGER data (magnetospheres, plasma environments and space weather) |