Semantic Segmentation of Heterogeneous Data by Deep Learning for the Prevention of Natural Hazards

When:
15/09/2022 – 16/09/2022 all-day
2022-09-15T02:00:00+02:00
2022-09-16T02:00:00+02:00

Offre en lien avec l’Action/le Réseau : – — –/– — –

Laboratoire/Entreprise : Laboratoire/Entreprise : PRISME / BRGM
Durée : 36 months
Contact : yves.lucas@univ-orleans.fr
Date limite de publication : 2022-09-15

Contexte :
The aim of this thesis is to evaluate the contribution of artificial intelligence to better assess the vulnerability of assets facing natural hazards, by unfolding impact scenarios in a multi-risk and multi-scale perspective. The highly multimodal and heterogeneous character of remote sensing data (visible, IR, hyperspectral, lidar, radar, topography, spectral libraries of materials ….) to characterize a territory, brings out a new methodological challenge: to develop network architectures adapted for the classification and semantic segmentation of these massive and complex data. This thesis work is also in synergy with the actions carried out at BRGM (H2020 COCLICO, VIGIRISKS, ANR RICOCHET projects) and the ANR-IA where joint work has been initiated between PRISME and BRGM

Sujet :
Complete description is available in the attached file.

Profil du candidat :
The candidate should have obtained a Master’s degree in computer science. Autonomy, scientific rigor and a strong motivation for the proposed subject will be undeniable assets to successfully complete the thesis.

Candidates must send the following documents in a single pdf file :
CV + cover letter + Master grades – optional letters of recommendation.

Contacts:

yves.lucas@univ-orleans.fr
a.hohmann@brgm.fr
c.negulescu@brgm.fr

Formation et compétences requises :
The candidate should have a broad knowledge of image processing, including deep learning techniques and their implementation in software and hardware. Fundamental notions in remote sensing are also required. Fluency in English is essential.

Adresse d’emploi :
Polytech Orléans · 12, rue de Blois, BP 6744 · 45067 cedex 2 Orléans , France

BRGM 3 avenue Claude-Guillemin, BP 36009 45060 Orléans Cedex 02 France

Document attaché : 202205111304_these_BRGM_PRISME_annonce_MADICS.pdf