Catégorie : Workshops

Conférence de clôture de la Chaire d’excellence internationale Blaise Pascal attribuée en 2017 à Mihai Datcu

Lieu et date :

Mardi 18 février 2020, 9h30-12h45, au Conservatoire national des arts et métiers (Cnam), 292 rue St Martin, Paris 3ème, amphi Jean Baptiste Say (amphi Y, voir http://www.cnam.fr/adresses-et-plans/, lien « Amphithéâtres et salles de conférence »)

Programme :

09h30-10h00 : Accueil café

10h00-10h30 : Allocutions d’introduction
Olivier Faron
Administrateur Général du Conservatoire National des Arts et Métiers
Cendrine Cruzille
Directrice de la recherche et des transferts de technologies à la région Île-de-France
Philippe Bidaud
Scientific Director for Information Processing and Intelligent Systems in ONERA, and Professor at Université Pierre et Marie Curie
10h30 -11h15 : présentation par Mihai Datcu  « Earth Observation Data Science and beyond ». Vous pouvez voir les transparents projetés et écouter l’enregistrement audio de la conférence.
11h15 -12h30 : Table ronde « Artificial Intelligence for Earth Observation: present and future », animée par Mihai Datcu avec la participation de :

• Prof. Mioara Mandea, Solid Earth Programme Manager Innovation, Application and Science Directorate, CNES – Centre National d’Etudes Spatiales, Paris
• Dr. Elise Koeniguer, Ingénieur de recherche au Département Traitement de  l’Information et Systèmes, ONERA, Palaiseau
• Prof. Patrick Gallinari, Machine Learning and Information Access, LIP6, Sorbonne Universités
• Dr. Patrick Gatellier, Coordinator of the AI On-Demand European platform: AI4EU, Thales

Vous pouvez voir l’enregistrement vidéo de la table ronde.
12h30 : Remerciements par Michel Crucianu, Professeur de sciences informatiques, Cnam

Résumé :

Satellites are the only global Earth Observation (EO) data source. The field of  EO is presently at a key turning point, EO Big Data are now freely and openly accessible, the areas of Artificial Intelligence (AI) are explosively progressing and the computational and communication capacities are immense. This context and trends bring the AI paradigms and EO methodologies and applications in a new era. The theoretical and technological progress is amplifying the use of the EO broadening the impact in all major domains, climate, food security, urbanization, only to enumerate few. The presentation is an overview of the achievements in the frame of the International Blaise Pascal Chair of Excellence for EO Data Science in these areas, concluding with a vision of the AI4EO domains.

Talk by Mihai Datcu
(TerraData Workshop: ESIEE, Cité Descartes, 6 – 8 avenue Blaise Pascal, Marne la Vallée, June 25th, 2018, 14:00)
The sensory gap is the dissimilarity between the actual nature of an object and the information extracted from the signals recorded by a sensor observing this object. Earth Observation (EO) images are sensor records, gathering the signature of the observed scenes in a specific electromagnetic spectrum, therefore an indirect signature of the imaged scenes. The challenge is in inverting the physically meaningful parameters of the scene from these observations. The lecture is presenting a communication channel model for the parameter retrieval problem. The source is the ensemble of EO data, and the information contained in the data is a message. Modeling the data processing chain as a communication channel allows measuring and quantifying the amount of information each feature descriptor can provide about a set of images. The generative Bayesian models, as Latent Dirichlet Allocation (LDA), Restricted Boltzmann Machine, Generative Adversarial Networks and the latest Deep Learning paradigms are discussed and exemplified as solutions for the EO sensory gap.

Joint ONERA – CNAM Workshop
(ONERA, Palaiseau, April 5th, 2018, 10:00 – 15:00)
Mihai Datcu presented an overview of the particularities of Artificial Intelligence (AI) in the fields of Earth Observation (EO). The focus was on the methods of Deep Learning and their specificities for multispectral and Synthetic Aperture Radar. Have been presented various relevant examples, which differentiate the methods in EO from other areas as Computer Vision. The conclusion emphasizing the main research directions of importance in EO both in theory and in practical applications.
The lecture was followed by the presentation of the recent results obtained at ONERA in the field and live discussion and debate on the perspectives of AI in EO.