Differences

This shows you the differences between two versions of the page.

--- general [2021/01/18 10:34] – admin
+++ general [2021/10/12 10:26] (current) – admin
@@ Line 8: / Line 8: @@
   * 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 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. We provide both, trained models as well as ML code, all of which are free to use and to be adapted by the user. The term "ML tool" refers in our case to [[https://github.com/epn-ml|ML codes, notebooks, or trained models]], with which data can be analyzed. Applying our tools to data will result in (high-level and derived) data products, which will be made available via VESPA, together with the original data.
-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.
+The tools are shared and made accessible to the wider planetary science community through this webpage, the ML Portal, and our [[https://github.com/epn-ml|GitHub organization]]. The ML work package also provides documentation, [[:tutorials|]], and [[:workshops|workhops]], to support the [[:beneficiaries|]] and the community users of the ML tools.
-===== Work Package Beneficiaries and Partners =====
+===== Methodology =====
-| \\ **Work Package Beneficiaries and Partners** ||
+In order to reach our goal of building versatile ML based tools for data analysis in planetary science, we pursue a bottom up approach, i.e., building tools that solve a diverse set of specific problems in planetary science with the aim of generalizing the solutions as much as possible. To achieve this, the community was asked to provide scientific use cases during the proposal phase of the project. Out of these proposed cases, a representative set of [[:science_cases|science cases]] was selected and the respective institutes were included as [[:beneficiaries|]].
-| \\ 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 =====
+The idea is that the technical partners (KNOW, Uni-Passau and ACRI-ST) will closely collaborate with the scientific partners of our WP to build tools that solve “real life” scientific problems and at the same time provide the flexibility necessary to adapt the resulting toolset to other related problems in planetary science with passable effort.
-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.
+A careful assessment of these [[:science_cases|science cases]] provided a solid basis to determine the technologies that would be best fitted to build the tools. It turned out that ML tools to classify, filter and search time series data as well as Deep Learning (DL) based classifiers of 2D (e.g., surface images or spectra) and video data, such as Convolutional Neural Networks (CNNs) and Deep Neural Networks (DNNs) in general as well as other techniques (as e.g., Self Organizing Maps) will be applied. Supervised as well as unsupervised approaches, with the latter also being able to leverage unlabelled data, are the technologies expected to benefit the community the most.
-^Proposer  ^Science Case  |
+Furthermore, we investigate automated pre-processing methods based on automated machine learning in order to optimize the pre-processing step per [[:science_cases|science case]]. The respective [[https://github.com/epn-ml|tools]] are built in an iterative process, continuously assessed and validated by the scientific partners as well as the planetary science community in general. Hands on sessions at conferences and [[:workshops|]] support the process of gathering feedback to validate and further optimize the developed solutions.
-|IAP-CAS  |[[:science_cases:iap_science_cases:boundaries|Detection of plasma boundary crossings at planetary magnetospheres and solar wind ]](magnetospheres, plasma environments and space weather)  |
-| ::: |[[:science_cases:iap_science_cases:waves|Classification of plasma wave emissions in electromagnetic spectra]] (planetary and solar radio emissions)  |
+===== Timeline =====
-|INAF  |[[:science_cases:inaf_science_case|Mineral identification via reflectance spectra]] (planetary surfaces/compositions/interiors) \\  [possible applications foreseen in GMAP]  |
-|DLR  |[[:science_cases:dlr_science_case|Classification of surface composition on the surface of Mercury]] (planetary surfaces/compositions/interiors) \\  [resulting data products can be used for GMAP]  |
+We plan to have applicable and working ML tools for all of our science cases at the end of the workpackage, which will be in July 2023. Of course, as soon as a working prototype is available, we will put the corresponding codes on our [[https://github.com/epn-ml|GitHub account]].
-|AOP  |[[:science_cases:aop_science_case|Abundance of asteroids in Earth-like orbits from STEREO images]] (small bodies, asteroids & comets)  |
-|GMAP  |[[:science_cases:gmap_science_cases|Automatic recognition and analysis of planetary surface features]] (planetary surfaces/compositions/interiors)  |
+The integration of the data sets and the data products of the first science cases (the [[:science_cases:iwf_science_case|IWF science case]], the [[:science_cases:lmsu_science_case|LMSU science case]], as well as the [[:science_cases:gmap_science_cases|GMAP science cases]]) into VESPA will start in winter 2021. We will then continuously include the data sets from the other science cases.
-|IWF-OEAW  |[[:science_cases:iwf_science_case|Detection and classification of CMEs and CIRs in in-situ solar wind data]] (magnetospheres, plasma environments and space weather)  |
-|LMSU  |[[:science_cases:lmsu_science_case|Search for magnetopause/shockwave crossings on Mercury based on MESSENGER data]] (magnetospheres, plasma environments and space weather)  |