Postdoc M/F MACHINE LEARNING AND AUTOMATED INTERPRETATION OF GEOLOGICAL STRUCTURES

Updated: about 1 month ago
Location: Orleans, CENTRE
Job Type: FullTime
Deadline: 10 Apr 2024

21 Mar 2024
Job Information
Organisation/Company

CNRS
Department

Institut des Sciences de la Terre d'Orléans
Research Field

Geosciences
Astronomy
Environmental science
Researcher Profile

First Stage Researcher (R1)
Country

France
Application Deadline

10 Apr 2024 - 23:59 (UTC)
Type of Contract

Temporary
Job Status

Full-time
Hours Per Week

35
Offer Starting Date

1 Jun 2024
Is the job funded through the EU Research Framework Programme?

Not funded by an EU programme
Is the Job related to staff position within a Research Infrastructure?

No

Offer Description

Artificial intelligence innovations open new horizons for modelling sub-surface Earth structures. However, the high level of epistemic uncertainty generally attached to such systems explains why this domain still faces several scientific and technical issues. This job offer comes in the framework of the MaLISSiA project that explores a geocognitive approach to geomdelling based on the formalisation of geological knowledge and interpretation.
This new paradigm for geomodelling relies on three principal components that are (1) a formalisation of geological concepts in the form of an ontology, (2) an algorithm for iterative interpretation based on a Spatial-Agent-based approach and framed as a continuous improvement process, and (3) on machine learning algorithms guided by theory and analogues from natural objects and simulations.
The proposed position will cover four missions in collaboration with the other team members:
Mission 1 – Numerical Development of the research code: the first and main mission will consist n taking part in the implementation of the interpretation algorithm. These developments will be made in Python programming language and possibly with some compiled pieces of code in C++. Documentation, management, and publication of the code will be particularly important in this task.
Mission 2 – Research on machine learning integration: several key stages of the proposed algorithm could benefit from interactions with algorithms based on machine learning. This second task will consist in a bibliography study and analysis of the current approach to integrate existing machine learning and artificial intelligence strategies into the proposed approach.
Mission 3 – Participating in a geological corpus construction: machine learning as well as testing and developing the proposed interpretation process call for a large database of reference geological models. This task will consist in improving the corpus under construction and for example in co-supervising Master research students in running numerical simulations and in digital acquisition of rock samples.
Mission 4 – Publication and Communication : results and methodological developments will be presented in conferences and published in scientific journals.

The research activities related to the aforementioned tasks will consist in: (1) numerical development in python and possibly c++; (2) documenting and illustrating code usage, creating examples, and promoting the code accessibility; (3) bibliographic research on machine learning approaches and integration into the developed approach; (4) supervision of M.Sc. Students with possibilities for teaching; (5) scientific valorisation and publication.

This position is in the framework of the MaLISSiA project funded by the French research agency (ANR-JCJC : ANR-22-CE56-0001-01). It will take place at ISTO (Institut des Sciences de la Terre d'Orléans) in the Metallogenic Systems research team. This team is developing a research topic on modelling of geological structures, in particular with applications to metal deposit characterization. The MaLISSiA project is also applied in the context of the Observatory of the Non-Saturated Zone (O-ZNS) to study subsurface water transfers above the phreatic nappes in the Beauce region. This project is in strong interaction with the French geological survey (BRGM) and will if needed benefit from access to the regional mesocenter for High Performance Computing CaSciModOT.


Requirements
Research Field
Geosciences
Education Level
PhD or equivalent

Research Field
Astronomy
Education Level
PhD or equivalent

Research Field
Environmental science
Education Level
PhD or equivalent

Languages
FRENCH
Level
Basic

Research Field
Geosciences
Years of Research Experience
None

Research Field
Astronomy
Years of Research Experience
None

Research Field
Environmental science
Years of Research Experience
None

Additional Information
Eligibility criteria

We are looking for candidates with a Ph.D. in science:
 The recruited profile should be either a numerical geologist with experience in formalizing and implementing new numerical techniques or a scientist specialized in informatics with an open mind for natural objects and/or spatial applications.
 A strong formation and/or first experience about some of the key aspects of the proposed position will be appreciated: artificial intelligence, machine learning, computer vision, web semantic, 3D structural modelling, photogrammetry.
 Programming skills are expected, both technical language skills (Python) and knowledge of development tools and methods (documentation, versionning, environnement, code publication, project management).
 Above all, and as for all research job, enthusiasm and skills for team work, synthesis, and oral and written communication (at least in English but some French skills will be appreciated even though not compulsory).


Website for additional job details

https://emploi.cnrs.fr/Offres/CDD/UMR7327-MARROU0-039/Default.aspx

Work Location(s)
Number of offers available
1
Company/Institute
Institut des Sciences de la Terre d'Orléans
Country
France
City
ORLEANS
Geofield


Where to apply
Website

https://emploi.cnrs.fr/Candidat/Offre/UMR7327-MARROU0-039/Candidater.aspx

Contact
City

ORLEANS
Website

https://www.isto-orleans.fr/

STATUS: EXPIRED