Post-doc offer: Machine learning for glacier study from 2D+t seismic data (Grenoble)

When:
30/07/2020 – 31/07/2020 all-day
2020-07-30T02:00:00+02:00
2020-07-31T02:00:00+02:00

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

Laboratoire/Entreprise : ISTerre, Université Grenoble-Alpes, France
Durée : 12 months, possibly
Contact : sophie.giffard@univ-grenoble-alpes.fr
Date limite de publication : 2020-07-30

Contexte :
In the context of the MIAI (AI institute in Grenoble) environment, we have a post-doctoral position opened at ISTerre, an earth science lab. The interdisciplinary team associated with the project primarily consists of 3 permanent researchers: Sophie Giffard-Roisin (CR IRD), Grégory Bièvre (MDC UGA) and Stéphane Garambois (Pr UGA, PI of the project).

He / She will be integrated into the enlarged working group and will make the link between the two disciplines of data science and geophysics in partnership with the themes developed within the MIAI of the UGA.

Sujet :
The mission is mainly to do exploratory research, animation and transfer concerning the methodologies currently developed in the field of data sciences and artificial intelligence towards automated processing of low amplitude seismic signals, from detection to classification. An effort will also be focused on understanding the processes they reveal in connection with other measured observables.

A concrete application using a 2D+t grid of recorded seismic signals on an alpine glacier will be the core of the work, in order to understand the link between basal slide and subglacial hydrology. For this, he/she will explore and develop machine learning methods used in signal processing (including deep scattering) and images (convolutional neural networks).

Finally (if time permits), the work will focus on a second application: the processing of seismological data acquired for many years on a mountain slow-moving landslide. The learning techniques could make it possible to better constrain the evolution of the relationships between seismicity / rainfall / displacements and thus the evolutionary processes controlling this dynamic.

Profil du candidat :
Skills
The profile sought is clearly linked to data sciences and techniques developed in artificial intelligence for signal processing with experience in applied methodological developments. Some support in seismology and Earth sciences, but also in machine learning, will be available within the research team.

Know-how
A strong interest in the application aspects of methodological developments in AI and a curiosity towards important processes in earth sciences will be appreciated. As the work environment is interdisciplinary, communication and facilitation skills will be necessary. A strong link will have to be consolidated with the Gricad data center. A partial supervision of several thesis works on more applicative subjects could be proposed.

Formation et compétences requises :
PhD in machine learning, signal processing or seismology (if accompanied with strong computer science skills) is required.

Adresse d’emploi :
ISTerre Laboratory, Saint Martin D’Hères, Université Grenoble Alpes

Start date between Sept. and Dec. 2020

Document attaché : 202005251446_Fiche de poste post-doc_MIAI.pdf