MaDICS est un Groupement de Recherche (GDR) du CNRS créé en 2015. Il propose un écosystème pour promouvoir et animer des activités de recherche interdisciplinaires en Sciences des Données. Il est un forum d’échanges et d’accompagnement pour les acteurs scientifiques et non-scientifiques (industriels, médiatiques, culturels,…) confrontés aux problèmes du Big Data et des Sciences des données.
Pour en savoir plus…
Les activités de MaDICS sont structurées à travers des Actions et Ateliers. Les Actions rassemblent les acteurs d’une thématique précise pendant une durée limitée (entre deux et quatre ans). La création d’une Action est précédée par un ou plusieurs Ateliers qui permettent de consolider les thématiques et les objectifs de l’action à venir.
Le site de MaDICS propose plusieurs outils de support et de communication ouverts à la communauté concernée par les Sciences des Données:
- Manifestations MaDICS : Le GDR MaDICS labellise des Manifestations comme des conférences, workshops ou écoles d’été. Toute demande de labellisation est évaluée par le Comité de Direction du GDR. Une labellisation rend possible un soutien financier pour les jeunes chercheuses et chercheurs. Une labellisation peut aussi être accompagnée d’une demande de soutien financier pour des missions d’intervenants ou de participants à la manifestation.
Pour en savoir plus… - Réseaux MaDICS : pour mieux cibler les activités d’animation de la recherche liées à la formation et à l’innovation, le GDR MaDICS a mis en place un Réseau Formation destiné à divers publics (jeunes chercheurs, formation continue,…), un Réseau Innovation pour faciliter et intensifier la diffusion des recherches en Big Data, Sciences des Données aux acteurs industriels et un Club de Partenaires qui soutiennent et participent aux activités du GDR.
Pour en savoir plus… - Espace des Doctorants : Les doctorants et les jeunes chercheurs représentent un moteur essentiel de la recherche et le GDR propose des aides à la mobilité et pour la participation à des manifestations MaDICS.
Pour en savoir plus… - Outils de communication : Le site MaDICS permet de diffuser des informations diverses (évènements, offres d’emplois, proposition de thèses, …) liées aux thématiques de recherche du GDR. Ces informations sont envoyées à tous les abonnés de la liste de diffusion MaDICS et publiés dans un Calendrier public (évènements) et une page d’offres d’emplois.
Adhésion au GDR MaDICS : L’adhésion au GDR MaDICS est gratuite pour les membres des laboratoires ou des établissements de recherche publics. Les autres personnes peuvent adhérer au nom de l’entreprise ou à titre individuel en payant une cotisation annuelle.
Pour en savoir plus…
Manifestations à venir
Journées Ecoles Conférences et Séminaires
Actions et Ateliers :
DAE DatAstro DSChem EXMIA GeoKIF HELP Musiscale SaD-2HN SIMDAC SimpleText TIDS
Date : 2025-08-11 => 2025-08-14
Lieu : Ghent, Belgium
This workshop aims at bringing together people from industry and academia, including researchers, developers, and practitioners from a variety of fields working on graphs and knowledge graphs, network management, data science, and cybersecurity. The workshop will allow attendees to share and discuss their latest findings from both theoretical and practical perspectives, namely in terms of graph-based security data representation, analysis, processing and visualization. The workshop attendees may benefit from sharing experience on graph-based data analysis regardless of the specific application. Moreover, researchers and practitioners will have an opportunity to familiarize themselves with recent advances in graph analysis, mining and learning, and other approaches that could be used in their work. The workshop aims to highlight the latest research and experience in graph-based approaches in cybersecurity. The workshop also seeks papers describing new datasets with real attack scenarios, graph modeling tools evaluated on existing and proposed datasets, and systematization of knowledge (SoK) papers.
Notre site web : www.madics.fr
Suivez-nous sur Tweeter : @GDR_MADICS
Pour vous désabonner de la liste, suivre ce lien.
Date : 2025-08-25 => 2025-08-26
Lieu : Institut Henri Poincaré, Paris
We are organizing a two-day workshop on causal inference, combining theoretical and applied research, as part of the Causalit-AI group from the PEPR IA program.
The event will feature 8 keynote talks and a poster session.
Registration is free but mandatory.
Notre site web : www.madics.fr
Suivez-nous sur Tweeter : @GDR_MADICS
Pour vous désabonner de la liste, suivre ce lien.
Date : 2025-09-19
Lieu : Porto, Portugal
MACLEAN: MAChine Learning for EArth ObservatioN
19 September 2025
KEY DATES
Paper submission deadline: June 14, 2025
Paper acceptance notification: July 14, 2025
Paper camera-ready deadline: TBA
CONTEXT
The huge amount of data currently produced by modern Earth Observation (EO) missions has raised up new challenges for the Remote Sensing communities. EO sensors are now able to offer (very) high spatial resolution images with revisit time frequencies never achieved before considering different kind of signals, e.g., multi-(hyper)spectral optical, radar, LiDAR and Digital Surface Models.
In this context, modern machine learning techniques can play a crucial role to deal with such amount of heterogeneous, multi-scale and multi-modal data. Some examples of techniques that are gaining attention in this domain include deep learning, domain adaptation, semi-supervised approach, time series analysis and active learning.
Even though the use of machine learning and the development of ad-hoc techniques are gaining increasing popularity in the EO domain, we can witness that a significant lack of interaction between domain experts and machine learning researchers still exists.
The objective of this workshop is to supply an international forum where machine learning researchers and domain-experts can meet each other, in order to exchange, debate and draw short and long term research objectives around the exploitation and analysis of EO data via Machine Learning techniques. Among the workshop’s objectives, we want to give an overview of the current machine learning researches dealing with EO data, and, on the other hand, we want to stimulate concrete discussions to pave the way to new machine learning frameworks especially tailored to deal with such data.
TOPICS
– Supervised Classification of Multi(Hyper)-spectral data
– Supervised Classification of Satellite Image Time Series data
– Unsupervised Learning of EO Data
– Deep Learning approaches to deal with EO Data
– Machine Learning approaches for the analysis of multi-scale EO Data
– Machine Learning approaches for the analysis of multi-source EO Data
– Semi-supervised classification approaches for EO Data
– Active learning for EO Data
– Transfer Learning and Domain Adaptation for EO Data
– Interpretability and explainability of machine learning methods in the context of EO data analysis
– Bayesian machine learning for EO Data
– Dimensionality Reduction and Feature Selection for EO Data
– Graphicals models for EO Data
– Structured output learning for EO Data
– Multiple instance learning for EO Data
– Multi-task learning for EO Data
– Online learning for EO Data
– Embedding and Latent factor for EO Data
– Foundation Models for Earth Observation
– Multi-Modal approaches for EO Data
– Self-supervised learning for EO Data
– Physics-informed machine learning for EO Data
INVITED SPEAKERS:
– Prof. Dr. Elif Sertel – Istanbul Technical University, Istanbul, TR, https://web.itu.edu.tr/~sertele/
Keynote title : TBA
SUBMISSION
We welcome original contributions, either theoretical or empirical, describing ongoing projects or completed work. Contributions can be of two types: either short position papers (up to 6 pages including references) or full research papers (up to 10 pages including references). Papers must be written in LNCS format, i.e., accordingly to the ECML-PKDD 2024 submission format. Accepted contributions will be made available electronically through the Workshop web page.
Post-proceedings will be also published at the CCIS (Communications in Computer and Information Science) series.
WORKSHOP WEBSITE:
https://sites.google.com/view/maclean25
SUBMISSION WEBSITE:
TBA
PC-CHAIRS
Thomas Corpetti, CNRS, LETG-Rennes COSTEL UMR 6554 CNRS, Rennes, France, thomas.corpetti@cnrs.fr
Roberto Interdonato, CIRAD, UMR Tetis, Montpellier, France, roberto.interdonato@cirad.fr
Cassio Fraga Dantas, INRAE, UMR Tetis, Montpellier, France, cassio.fraga-dantas@inrae.fr
Dino Ienco, INRAE, UMR Tetis, Montpellier, France, dino.ienco@inrae.fr
Minh-Tan Pham, Univ. Bretagne-Sud, UMR 6074, IRISA, Vannes, France, minh-tan.pham@irisa.fr
Notre site web : www.madics.fr
Suivez-nous sur Tweeter : @GDR_MADICS
Pour vous désabonner de la liste, suivre ce lien.
Date : 2025-09-19
Lieu : Porto, Portugal
MACLEAN: MAChine Learning for EArth ObservatioN
https://sites.google.com/view/maclean25
19 September 2025
KEY DATES
Paper submission deadline: June 14, 2025
Paper acceptance notification: July 14, 2025
Paper camera-ready deadline: TBA
CONTEXT
The huge amount of data currently produced by modern Earth Observation (EO) missions has raised up new challenges for the Remote Sensing communities. EO sensors are now able to offer (very) high spatial resolution images with revisit time frequencies never achieved before considering different kind of signals, e.g., multi-(hyper)spectral optical, radar, LiDAR and Digital Surface Models.
In this context, modern machine learning techniques can play a crucial role to deal with such amount of heterogeneous, multi-scale and multi-modal data. Some examples of techniques that are gaining attention in this domain include deep learning, domain adaptation, semi-supervised approach, time series analysis and active learning.
Even though the use of machine learning and the development of ad-hoc techniques are gaining increasing popularity in the EO domain, we can witness that a significant lack of interaction between domain experts and machine learning researchers still exists.
The objective of this workshop is to supply an international forum where machine learning researchers and domain-experts can meet each other, in order to exchange, debate and draw short and long term research objectives around the exploitation and analysis of EO data via Machine Learning techniques. Among the workshop’s objectives, we want to give an overview of the current machine learning researches dealing with EO data, and, on the other hand, we want to stimulate concrete discussions to pave the way to new machine learning frameworks especially tailored to deal with such data.
TOPICS
– Supervised Classification of Multi(Hyper)-spectral data
– Supervised Classification of Satellite Image Time Series data
– Unsupervised Learning of EO Data
– Deep Learning approaches to deal with EO Data
– Machine Learning approaches for the analysis of multi-scale EO Data
– Machine Learning approaches for the analysis of multi-source EO Data
– Semi-supervised classification approaches for EO Data
– Active learning for EO Data
– Transfer Learning and Domain Adaptation for EO Data
– Interpretability and explainability of machine learning methods in the context of EO data analysis
– Bayesian machine learning for EO Data
– Dimensionality Reduction and Feature Selection for EO Data
– Graphicals models for EO Data
– Structured output learning for EO Data
– Multiple instance learning for EO Data
– Multi-task learning for EO Data
– Online learning for EO Data
– Embedding and Latent factor for EO Data
– Foundation Models for Earth Observation
– Multi-Modal approaches for EO Data
– Self-supervised learning for EO Data
– Physics-informed machine learning for EO Data
INVITED SPEAKERS:
– Prof. Dr. Elif Sertel – Istanbul Technical University, Istanbul, TR, https://web.itu.edu.tr/~sertele/
Keynote title : TBA
SUBMISSION
We welcome original contributions, either theoretical or empirical, describing ongoing projects or completed work. Contributions can be of two types: either short position papers (up to 6 pages including references) or full research papers (up to 10 pages including references). Papers must be written in LNCS format, i.e., accordingly to the ECML-PKDD 2025 submission format. Accepted contributions will be made available electronically through the Workshop web page.
Post-proceedings will be also published at the CCIS (Communications in Computer and Information Science) series.
WORKSHOP WEBSITE:
https://sites.google.com/view/maclean25
SUBMISSION WEBSITE:
https://cmt3.research.microsoft.com/ECMLPKDDWorkshopTrack2025/Submission/Index
PC-CHAIRS
Thomas Corpetti, CNRS, LETG-Rennes COSTEL UMR 6554 CNRS, Rennes, France, thomas.corpetti@cnrs.fr
Roberto Interdonato, CIRAD, UMR Tetis, Montpellier, France, roberto.interdonato@cirad.fr
Cassio Fraga Dantas, INRAE, UMR Tetis, Montpellier, France, cassio.fraga-dantas@inrae.fr
Dino Ienco, INRAE, UMR Tetis, Montpellier, France, dino.ienco@inrae.fr
Minh-Tan Pham, Univ. Bretagne-Sud, UMR 6074, IRISA, Vannes, France, minh-tan.pham@irisa.fr
Notre site web : www.madics.fr
Suivez-nous sur Tweeter : @GDR_MADICS
Pour vous désabonner de la liste, suivre ce lien.
Date : 2025-09-23 => 2025-09-26
Lieu : Tampere, Finland
Overview
TPDL is an international forum focused on Digital Libraries, Document Analysis/Recognition, and Information Retrieval and their associated technical, practical, and social issues. The conference encompasses the many meanings of the term digital libraries, embracing the whole spectrum of the GLAM (Gallery, Library, Archive, and Museum) community; information access and operational information systems with all manner of digital content; new means of selecting, collecting, organizing, distributing, and accessing digital content; and theoretical models of information media, including document genres and electronic publishing.
Topics
Topics in 2025 include but are not limited to, theories, models, standards, tools, and applications on the following themes:
- Publishing Science
- Information Management Science
- Monitoring and Assessment of Science
- Knowledge Creation and Dissemination
- AI and Machine Learning Applications in Digital Libraries
- Digital Humanities and Cultural Heritage
- Human-Computer Interaction in Digital Libraries
- Information Retrieval
- Retrieval Augmented Generation (RAG) in the context of Digital Libraries
- Recommender Systems in Digital Libraries
- Document Analysis and Recognition
Also see the detailed list of topics of the main conference, here: https://tpdl2025.github.
Important Dates
All deadlines are 23:59 (11:59 pm) in the AoE (Anywhere on Earth) time zone on the date specified.
- Demonstration paper submission deadline: June 12, 2025
- Notification of acceptance for demonstration papers: July 13, 2025
- Camera-ready submission: July 27, 2025
Contribution Types
Demonstration papers (8 pages + unlimited references) present high-quality, original research, applications or tools that are of relevance to the TPDL community. Accepted papers will be published in the conference proceedings. At least one author of each accepted demonstration must register and attend the conference. The Demo Track invites researchers to present their research prototypes and operational systems to the community, receive expert feedback, share insights, and exchange knowledge on the development and implementation of innovative systems. Proposals from startups and industry participants are also welcome.
- Submissions should clearly define the purpose, scope, and audience of the demo.
- Each paper should include a section describing the exact demonstration scenarios, which include how the audience will experience the demo, the artifact’s functionalities, user interface and interaction options, etc.
- All submissions should provide a URL to a live online version of their demo or, alternatively, provide a URL to a video (up to 5 minutes) showcasing the main features of their demo.
- Demonstrations that make their source code freely available are especially encouraged.
Awards
Springer will sponsor the TPDL 2025 Best Demonstration Paper Award, which will be announced during the TPDL Banquet.
Submission Guidelines
Accepted papers will be published in the conference proceedings. All submissions must be written in English and use the Springer LNCS proceedings templates, either for LaTeX or for Word, see Springer LNCS guidelines: https://www.
Every paper must be submitted in PDF format using the CMT online submission system after selecting the TPDL2025 – Demos Track: https://cmt3.research.
Failure to comply with the submission guidelines will lead to direct rejection without review.
Demonstration submissions are single-blind. You are not expected to take measures to conceal your identity from reviewers. Authors should note that changes to the author list after the submission deadline are not allowed without permission from the PC Chairs.
In addition, the corresponding author of each accepted paper, acting on behalf of all of the authors of that paper, must complete and sign a Consent-to-Publish form. The corresponding author signing the copyright form should match the corresponding author marked on the paper. Once the paper has been submitted, changes relating to its authorship cannot be made.
Dual Submission Policy
Papers submitted to TPDL 2025 must be substantially different from those previously published, accepted for publication, or currently under review at other venues. Exceptions include:
- Papers presented or to be presented at conferences or workshops without published proceedings.
- Papers previously available only as technical reports (e.g., in institutional archives or on preprint platforms like arXiv).
Demonstration Chairs
Liana Ermakova, Université de Bretagne Occidentale, France
Yannis Tzitzikas, University of Crete and FORTH, Greece
Notre site web : www.madics.fr
Suivez-nous sur Tweeter : @GDR_MADICS
Pour vous désabonner de la liste, suivre ce lien.
Date : 2025-09-23 => 2025-09-26
Lieu : Tampere, Finland
TPDL 2025 – The 29th International Conference on Theory and Practice of
Digital Libraries
Call for demonstration papers
*23-26 September 2025 – Tampere, Finland *
*Website*: https://tpdl2025.github.io/Calls/demos.html
*Submission deadline*: June 12, 2025 (AoE)
*Overview*
TPDL is an international forum focused on Digital Libraries, Document
Analysis/Recognition, and Information Retrieval and their associated
technical, practical, and social issues. The conference encompasses the
many meanings of the term digital libraries, embracing the whole spectrum
of the GLAM (Gallery, Library, Archive, and Museum) community; information
access and operational information systems with all manner of digital
content; new means of selecting, collecting, organizing, distributing, and
accessing digital content; and theoretical models of information media,
including document genres and electronic publishing.
*Topics*
Topics in 2025 include but are not limited to, theories, models, standards,
tools, and applications on the following themes:
– Publishing Science
– Information Management Science
– Monitoring and Assessment of Science
– Knowledge Creation and Dissemination
– AI and Machine Learning Applications in Digital Libraries
– Digital Humanities and Cultural Heritage
– Human-Computer Interaction in Digital Libraries
– Information Retrieval
– Retrieval Augmented Generation (RAG) in the context of Digital
Libraries
– Recommender Systems in Digital Libraries
– Document Analysis and Recognition
Also see the detailed list of topics of the main conference, here:
https://tpdl2025.github.io/Calls/researchtrack.html
*Important Dates*
All deadlines are 23:59 (11:59 pm) in the AoE (Anywhere on Earth) time zone
on the date specified.
– Demonstration paper submission deadline: June 12, 2025
– Notification of acceptance for demonstration papers: July 13, 2025
– Camera-ready submission: July 27, 2025
*Contribution Types*
Demonstration papers (8 pages + unlimited references) present high-quality,
original research, applications or tools that are of relevance to the TPDL
community. Accepted papers will be published in the conference proceedings.
At least one author of each accepted demonstration must register and attend
the conference. The Demo Track invites researchers to present their
research prototypes and operational systems to the community, receive
expert feedback, share insights, and exchange knowledge on the development
and implementation of innovative systems. Proposals from startups and
industry participants are also welcome.
– Submissions should clearly define the purpose, scope, and audience of
the demo.
– Each paper should include a section describing the exact demonstration
scenarios, which include how the audience will experience the demo, the
artifact=E2=80=99s functionalities, user interface and interaction optio=
ns, etc.
– All submissions should provide a URL to a live online version of their
demo or, alternatively, provide a URL to a video (up to 5 minutes)
showcasing the main features of their demo.
– Demonstrations that make their source code freely available are
especially encouraged.
*Awards*
Springer will sponsor the TPDL 2025 Best Demonstration Paper Award, which
will be announced during the TPDL Banquet.
*Submission Guidelines*
Accepted papers will be published in the conference proceedings. All
submissions must be written in English and use the Springer LNCS
proceedings templates, either for LaTeX or for Word, see Springer LNCS
guidelines:
https://www.springer.com/gp/computer-science/lncs/conference-proceedings-gu=
idelines
Every paper must be submitted in PDF format using the CMT online submission
system after selecting the TPDL2025 – Demos Track:
https://cmt3.research.microsoft.com/TPDL2025.
Failure to comply with the submission guidelines will lead to direct
rejection without review.
Demonstration submissions are single-blind. You are not expected to take
measures to conceal your identity from reviewers. Authors should note that
changes to the author list after the submission deadline are not allowed
without permission from the PC Chairs.
In addition, the corresponding author of each accepted paper, acting on
behalf of all of the authors of that paper, must complete and sign a
Consent-to-Publish form. The corresponding author signing the copyright
form should match the corresponding author marked on the paper. Once the
paper has been submitted, changes relating to its authorship cannot be made=
.
*Dual Submission Policy*
Papers submitted to TPDL 2025 must be substantially different from those
previously published, accepted for publication, or currently under review
at other venues. Exceptions include:
– Papers presented or to be presented at conferences or workshops
without published proceedings.
– Papers previously available only as technical reports (e.g., in
institutional archives or on preprint platforms like arXiv).
*Demonstration Chairs*
Liana Ermakova, Universit=C3=A9 de Bretagne Occidentale, France
Yannis Tzitzikas, University of Crete and FORTH, Greece
Notre site web : www.madics.fr
Suivez-nous sur Tweeter : @GDR_MADICS
Pour vous désabonner de la liste, suivre ce lien.
Date : 2025-09-25
Lieu : Kremlin Bicêtre
L’ingénierie des connaissances par ses volets modélisation, acquisition et exploitation contribuent à l’essor de l’IA tout en bénéficiant à travers notamment l’extraction automatisée de connaissances, l’intégration de représentations symboliques (ontologies, règles) dans des modèles neuronaux et le raisonnement sur des connaissances complexes. Mais comment ces bénéfices mutuels sont-ils aujourd’hui explorés et mis en œuvre dans divers domaines d’application ? Quels enjeux et quels défis posent-ils ?
L’ensemble des groupes de travail de l’association EGC a le plaisir de vous inviter à une journée scientifique autour de ces thématiques intitulée
“L’Ingénierie des Connaissances à l’ère de l’apprentissage Neuro-Symbolique, des Modèles HYbrides et autres approches (HYNSIC)”
Cette journée se tiendra le 25 septembre juin 2025 à Paris, sur le campus de l’EPITA au Kremlin Bicêtre(14-16 rue Voltaire 94270 Le Kremlin-Bicêtre). En métro : ligne 7, Porte d’Italie ou le Kremlin Bicètre.
Nous aurons 3 à 4 conférences invitées qui seront annoncées dès qu’elle seront confirmées.
Vous êtes doctorant, chercheur, affilié à une entreprise ou à un acteur public ? Venez présenter vos travaux (interventions ou posters) ou simplement assister aux échanges.
Dans les deux cas, l’inscription est gratuite mais obligatoire (le déjeuner sera pris en charge).
Appel à participation
Merci de remplir ce formulaire pour manifester votre intérêt pour cette journée (nous vous demanderons de confirmer votre inscription début septembre) :
https://framaforms.org/inscription-a-la-journee-hynsic-ingenierie-des-connaissances-a-travers-apprentissage-neuro
Appel à communication
Si vous souhaitez présenter vos travaux, vous pouvez d’ores et déjà et avant le 8 septembre envoyer un titre et un résumé (une à deux pages) de votre présentation à malika.smail@loria.fr (sujet : Journée HYNSIC).
Notre site web : www.madics.fr
Suivez-nous sur Tweeter : @GDR_MADICS
Pour vous désabonner de la liste, suivre ce lien.
Date : 2025-10-27 => 2025-10-30
Lieu : Montpellier
La 29è réunion des sciences de la terre (RST) aura lieu du 27 au 30 octobre 2025, au Corum à Montpellier.
rst-montpellier.sciencesconf.org
Dans le thème GÉOPATRIMOINE – COLLECTIONS – DIFFUSION & MÉDIATION SCIENTIFIQUE, une session est proposé à la croisée des géosciences et de l’informatique.
Cette session s’intitule GeoKIF: Formalisation de la connaissance et de l’interprétation en géologie.
Description et objectif : La gestion des données en géosciences est confrontée à des défis scientifiques et techniques liés (i) à leur nature volumineuse, variée, et complexe (aspects spatio-temporel et multidimensionnel), (ii) aux incertitudes (notamment épistémiques), ainsi qu’à (iii) l’évolution des technologies. Cette session abordera principalement les travaux sur le développement d’approches numériques permettant un traitement efficace des données, en prenant en compte (i) leur variété structurelle : graphes, nuage de points, données textuelles structurées ou non, (ii) leur variété en termes de qualité, et (iii) les modèles IA pour analyser ou interpréter ces données ? Cette session se focalisera sur les problématiques de la structuration de la donnée et en particulier en relation avec les connaissances et interprétations qui y sont liées, et sur l’évolution des méthodes de calcul et de représentation des données.
Nous vous invitons à contribuer à cette session soit par la présentation de travaux de recherche soit par la présentation d’avancées technologiques ou services divers mis à la disposition de la profession.
Les instructions pour la soumission se trouvent ici : https://rst-montpellier.sciencesconf.org/resource/page/id/6
Cette session est proposée dans le cadre de l’atelier GeoKIF du GDR CNRS MaDICS (https://www.madics.fr/ateliers/geokif/).
Notre site web : www.madics.fr
Suivez-nous sur Tweeter : @GDR_MADICS
Pour vous désabonner de la liste, suivre ce lien.
Date : 2024-10-04 => 2026-10-04
Chers collègues,
Nous avons le plaisir de vous annoncer le lancement d’une action IA dans le cadre du PPR Océan & Climat (https://www.ocean-climat.fr/). Cette action nationale vise à soutenir le développement de solutions nativement IA pour la modélisation, la prévision et l’observation des océans.
Suivant une démarche inspirée des avancées récentes pour la prévision météorologique court-terme, la première phase (octobre 2024-septembre 2025) visera via un appel à propositions à définir de manière collaborative des “data challenges” dont la mise en oeuvre (e.g., jeux de données, cadre d’évaluation) bénéficiera du soutien du PPR en termes d’ingénierie support. La deuxième phase (septembre 2025-décembre 2027) s’appuiera sur la sélection de 8 à 9 postdoctorats de deux ans pour laquelle un appel sera ouvert début 2025.
Nous organisons deux webinaires les 4/10 et 11/10 (12.00-13.00) pour présenter cette action et répondre à toute question (cf. lien zoom ci-dessous). Nous vous invitons également à rejoindre un espace slack dédié en complétant le formulaire d’inscription ci-dessous. Nous proposons que cet espace slack soit la plateforme principale pour les échanges autour de cette action.
Merci de faire suivre ce mail à toute personne potentiellement intéressée.
N’hésitez pas à me contacter pour tout complément d’information.
Bien cordialement,
Ronan Fablet pour le comité de suivi
Exemples de data challenges:
– WeatherBench 2.0 : https://sites.research.google/weatherbench/
– Ocean Data Challenge – Global SSH mapping: https://2023a-ssh-mapping-ose.readthedocs.io/en/latest/
Dates importantes :
– 4 et 11 Octobre 2024, 12.00-13.00: wébinaires (cf. lien zoom ci-dessous)
– 18 Octobre 2024 : date limite de proposition de “data challenges”
– 19 Octobre – 22 Novembre 2024 : mise en commun et révision des data challenges proposés
– 13 Décembre 2024 : publication des data challenges sélectionnés
– Janvier 2024 : ouverture de l’appel postdocs
– Septembre 2025 : démarrage des postdocs et workshop de lancement des data challenges
Formulaire d’inscription : https://forms.gle/R7QhGe4VwBrXXPWV7
Lien zoom du webinaire du 04/10/2024, 12.00-13.00:
https://cnrs.zoom.us/j/91635362763?pwd=bv146gsjDkT9SQ7lUcxHY1n4bi0jpU.1
Lien zoom du webinaire du 11/10/2024, 12.00-13.00:
https://univ-grenoble-alpes-fr.zoom.us/j/93226799086?pwd=agYwgn1IYRYhwD3x63VXyhCSfRZDns.1
Notre site web : www.madics.fr
Suivez-nous sur Tweeter : @GDR_MADICS
Pour vous désabonner de la liste, suivre ce lien.