En poursuivant votre navigation sur ce site, vous acceptez le dépôt de cookies dans votre navigateur. (En savoir plus)

Thesis on a "deep learning" approach for the automatic detection of diffraction images for 4D-STEM data H/F.

This offer is available in the following languages:
Français - Anglais

Date Limite Candidature : vendredi 2 juillet 2021

Assurez-vous que votre profil candidat soit correctement renseigné avant de postuler. Les informations de votre profil complètent celles associées à chaque candidature. Afin d’augmenter votre visibilité sur notre Portail Emploi et ainsi permettre aux recruteurs de consulter votre profil candidat, vous avez la possibilité de déposer votre CV dans notre CVThèque en un clic !

Faites connaître cette offre !

General information

Reference : UMR7314-ARNDEM-005
Workplace : AMIENS
Date of publication : Friday, June 11, 2021
Scientific Responsible name : Arnaud Demortière
Type of Contract : PhD Student contract / Thesis offer
Contract Period : 36 months
Start date of the thesis : 4 October 2021
Proportion of work : Full time
Remuneration : 2 135,00 € gross monthly

Description of the thesis topic

The PhD student will develop image processing algorithms based on the "deep learning" approach for the automatic identification of diffraction images
from the 4D-STEM acquisition. It will be a question of identifying from diffraction images, the lattice parameters, the symmetries and the different phases present.
CNN networks will be trained from known simulated and experimental data for which crystal structures are known.
The second part of the work will consist of using the "compressed sensing" approach to limit the effects of electron doses in our liquid TEM device. The idea is to improve this reverse sampling approach by integrating GAN networks to generate data consistent with the reference images.

Work Context

The doctoral student will carry out this work at the LRCS in Amiens with short assignments in the company NanoMegas in Belgium.

We talk about it on Twitter!