Geophysics Research Intern: AI-Driven Seismic Inversion

CGG Services SAS; Massy; Sur place; EUR 10 000 - 13 000; Temps partiel

Avantages offerts par ce poste

Restaurant with subsidized price

50% transport card reimbursement (Île‑

Gym access

Employee assistance program

Résumé du poste

Viridien is seeking a final-year Master’s student for a six-month internship in the subsurface imaging R&D team to develop and test advanced methods for geophysical workflows, including Full-Waveform Inversion (FWI). You will apply signal processing, AI, and numerical optimization to address demanding reservoir imaging challenges.

The role focuses on neural networks to guide FWI with petrophysical data, mapping properties to elastic parameters, and integrating the network into the FWI framework

Qualifications

• Final-year Master’s student in physics, mathematics, computer science or machine learning.
• Solid understanding of machine learning algorithms and neural networks.
• Excellent coding skills in Python, C/C++, CUDA or FORTRAN.
• Fluent English (read, write, and speak).

Responsabilités

• Investigate the potential of using neural networks to incorporate petrophysical information for guiding full-waveform inversion (FWI).
• Develop a neural network model to map petrophysical parameters to elastic parameters (Vp, Vs, density, …).
• Integrate the neural network mapping into the FWI framework to guide inversion with petrophysical information.

Connaissances

Machine learning

Neural networks

Programming: Python

Programming: C/C++

CUDA

FORTRAN

Fluent English

Formation

Master's degree (final year) in Math/Physics/CS/AI/Data Science

Outils

Python

CUDA

FORTRAN

C/C++

Description du poste

Viridien is seeking a final-year Master’s student for a six-month internship in the subsurface imaging R&D team to develop and test advanced methods for geophysical workflows, including Full-Waveform Inversion (FWI). You will apply signal processing, AI, and numerical optimization to address demanding reservoir imaging challenges.

The role focuses on neural networks to guide FWI with petrophysical data, mapping properties to elastic parameters, and integrating the network into the FWI framework