AI-DRIVEN ROCK PHYSIC TO LEVERAGE THE SEISMIC CHARACTERIZATION IN EXPLORATION CONTEXT

Beicip-Franlab

Rueil-Malmaison

Sur place

EUR 8 928 - 13 392

Plein temps

14 jours+

Recevez plus de réponses des employeurs

Envoyez un CV adapté au poste en quelques minutes.

Résumé du poste

A consulting firm in geoscience in France is offering an entry-level internship focused on AI-driven rock physics and seismic characterization. Interns will work under senior supervision, engaging in tasks like catalog building, optimization using AI, and developing models to analyze seismic data. This position is ideal for final year master's students in geosciences with skills in programming and rigor in technical software usage.

Qualifications

Candidates should be final year master students in geosciences.
Eager to master technical software and methodologies.

Responsabilités

Build catalogs of rock physics templates and constants.
Optimize parameters using AI techniques.
Develop models and validate results with real datasets.
Create interactive visuals of seismic data.

Connaissances

Knowledge of rock physics

Programming (Python, C++, Java)

Fast learner

Rigor

Formation

Final year master in geosciences

Outils

Anaconda

Visual Studio

NetBeans

InterWell

Description du poste

AI-DRIVEN ROCK PHYSIC TO LEVERAGE THE SEISMIC CHARACTERIZATION IN EXPLORATION CONTEXT

Beicip-Franlab, a leading consulting firm in geoscience, is exploring the potential of AI throughout its value chain. Historically data‑driven and utilizing machine learning, the seismic characterization group is now investigating an innovative approach to re‑introduce rock physics into industrial workflows, leveraging recent breakthroughs in AI.

During this internship, you will work on tasks that combine rock physics, seismic interpretation, and AI techniques, supervised by a senior geophysicist and software engineer.

Catalog building of rock physics templates, mineral and fluid constants.
Testing AI (MCDA, PINNS…) to automatically optimize parameters and select the best model(s). Discussion about uncertainties.
Application to build missing logs and detect anomalous values in raw data.
Synthetic AVO, synthetic gathers and angle‑stacks. Comparison with real dataset.
Validation of inversion results and petro‑elastic models. Population of training samples for facies prediction and application to real project data.
Development of an interactive view (plots vs seismic) into InterWell.

Software used includes IDEs (Anaconda, Visual Studio, NetBeans) and specialist software InterWell. Candidates should be final year master students in geosciences, fast learners, rigorous, eager to master technical software, with knowledge of rock physics and programming (Python, C++, Java).

Seniority level