Applied Mathematics Engineer Intern Build automatically realistic implicit structural models for deep leaning (5-6 months)
Detail de l'annonce :
APPLIED MATHEMATICS ENGINEER INTERN - BUILD AUTOMATICALLY REALISTIC
IMPLICIT STRUCTURAL MODELS FOR DEEP LEANING (5-6 MONTHS)
Montpellier - France
JOB TITLE:
Applied Mathematics Engineer Intern - Build automatically realistic
implicit structural models for deep leaning (5-6 months)
LOCATION:
Montpellier, France
ABOUT SCHLUMBERGER:
We are Schlumberger, the leading provider of technology and services
to the energy industry. Throughout much of the oil and gas lifecycle
in over 120 countries; we design, develop, and deliver technology and
services that transforms how work is done.
We define the boundaries of the industry by unleashing our talented
people’s energy. We’re looking for innovators to join our diverse
community of colleagues and develop new solutions and push the limits
of what’s possible. If you share our passion for discovery and want
to find out what you could really do, then here is the place to do it.
JOB SUMMARY:
Our Subsurface Structural Modeling team has for mission the
elaboration of industrial numerical code for building structural
models of the underground. Those models are essential to understand
the history of the underground and its structure, enabling to search
for subsurface resources (ore, geothermal, oil and gas, water).
Our current technology is based on the well known implicit technic
representing each conformal horizon as an iso-value of a function to
be computed. This interpolation problem is formulated as a
least-square minimization problem which is numerically costly to
solve.
Meanwhile, artificial intelligence (AI) has spread over a wide range
of domains in particular geoscience world. AI has proven to be an
outstanding approach for solving problems that until now were
requiring massive computational efforts. The idea proposed herein aims
to explore the application of the deep learning to the implicit
structural modeling. The aim of this internship is to develop a tool
to automatically build realistic synthetic structural models in 2D and
3D for training a neural network. The algorithm should be able to
generate diverse structures with realistic folding and faulting
features depending on a set of parameters randomly selected.
ESSENTIAL RESPONSIBILITIES AND DUTIES:
The theme of this internship is twofold:
* Design and develop an algorithm to automatically build diverse
structural models with realistic folding and faulting features
(C++/python)
* Interact with data scientists for ML part.
QUALIFICATION:
* Penultimate or final year
COMPETENCIES:
* Bibliographical research and Mathematical formulation
* Implementation of a prototype (C++ or python)
* Report and Technical discussions
Schlumberger is an equal employment opportunity employer. Qualified
applicants are considered without regard to race, color, religion,
sex, sexual orientation, gender identity, national origin, age,
disability, or other characteristics protected by law.