Annonce en lien avec l’Action/le Réseau : aucun

Laboratoire/Entreprise : LIMOS, UMR 6158 CNRS
Durée : 36 mois
Contact : vincent.barra@isima.fr
Date limite de publication : 2020-06-30

Contexte :
Volcanic hydrothermal systems are poorly-considered, long-fuse environmental time bombs. They involve complex process-response systems with spatially and temporally varying flows of heat and mass from deep volcanic sources to the Earth’s surface.
Across such zones, high concentrations of volcanic gas and extreme heat fluxes act as environmental polluters, killing-off flora and fauna across wide zones. Such systems are extremely common and involve some of the highest, sustained, heat fluxes on the planet.

The scientific context of this work is the ANR funded project DIRE (Data-Integration, Risk and the Environment) leaded by three CNRS labs of Clermont-Ferrand (LMV , LIMOS , LPC ), in collaboration with national (IRD) and international (INGV Italy, Univ. Geneva) partners.

Sujet :
The objective of this research project is to build Deep-Learning data-driven models that will allow to send alerts concerning the timing, location and hazard level of environmental crises at hydrothermal systems. Potential outcomes can then be assessed by examining past crises and their ecosystem impacts.

The heterogeneous big data originate from high-temporal resolution temperature, pression, gas composition, humidity, windspeed and rainfall sensors, seismicity and physical deformation measures, as well as satellite images (IR and NDVI values) and new and exclusive measures developed in this ANR project concerning muography. Measures are collected from Vulcano (Eolian Islands, Italy), a test bench for understanding active hydrothermal systems. The resulting dataset consists of thousands of multiparametric timeseries, from which probabilistic risk assessment and short-term event-scenario prediction is expected.

Once the model will be built and validated, it is expected to track degassing scenario’s and crises at active hydrothermal systems previously identified as possible targets (Indonesia, Vanuatu, Ecuador…)

Profil du candidat :
Candidates with a background of Computer Sciences will be considered seriously for this position. Speaking French is not mandatory but in any case, good English skills are necessary.

Formation et compétences requises :
Computer Science, Machine & Deep Learning, Programming (Python)

Adresse d’emploi :
LIMOS, UMR 6158 CNRS
Campus des Cézeaux
63178 AUBIERE

Document attaché : phD-Deep-DIRE.pdf