Artificial Intelligence / Machine Learning Internship (5 - 6 months) - Hybrid model (AI – Physics) with uncertainty estimation for drilling applications | Schlumberger

Job Details

Artificial Intelligence / Machine Learning Internship (5 - 6 months) - Hybrid model (AI – Physics) with uncertainty estimation for drilling applications

Clamart - France

Job Description

Schlumberger is developing and providing advanced technologies for downhole safety and oil & gas applications. It enables for customers (mainly oilfield companies) reliable and high-performance equipment and measurements to characterize, monitor and optimize their reservoir production.

Drilling technologies have been evolving in recent years, providing our customers high performant systems. One of the challenges of the drilling domain is modeling the Rate of Penetration (ROP) or the speed of the tool. Building a model that predicts the ROP with high accuracy will enable the optimization of drilling time and the reduction of drilling costs. Multiple sensors provide real time field-data stream to Google Cloud Platform. The main objective is to consolidate and improve Machine Learning/Deep Learning algorithms by incorporating physics-based models and measuring the uncertainty of the predictions. The benefit of a hybrid model is to combine the strengths of data science algorithms and physics knowledge. Furthermore, quantifying the uncertainty around the predictions plays a critical role in the process since it gives more confidence to the model.

The purpose of the internship is to focus on  achine learning and deep learning algorithms in order to build a hybrid model with uncertainty estimation of the ROP. The design methodology shall consider application-specific requirements and internal tools. It shall be based on current internal expertise from Schlumberger data scientist, project team and a consolidated bibliography. Proposed machine learning algorithms would be applied and benchmarked on simulated and experimental data. The intern will have the opportunity to contribute to the new product development for ROP prediction and work with the application and project experts located in Beijing (China), Stonehouse (England), Houston (USA) and with data scientists from the AI Lab located on Clamart Campus.

The intern will be in charge of defining the best strategy and methodology to provide a new answer product based on data science technologies (statistics and machine learning algorithms). The intern will have the ability to use available experimental equipment and numerical tools (large  possibilities within Schlumberger with research and engineering centers). Expected outcome from the internship would be a prototype algorithm for a specific drilling equipment.

Essential Responsibilities and Duties:

  • The responsibilities will be to research the state of the art in this domain which could be applied or pushed to deviler the required outcome.
  • The candidate will learn the latest and greatest in the context of our described challenge. Research, Model, Solution and Report will be part of the deliveries for this project.
  • Additional opportunities to produce recorded webinars and marketing 2min recording pitches will most likely occure during the internship.

Qualifications:  

  • End studies internship

Competencies and skills

  • Applied mathematics, Probability & statistics, Bayesian statistics, embedded software and physics/electronics (general)
  • Cloud computing services: Google Cloud Platform
  • Programming language: Python, PyTorch or Keras/Tensorflow

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.

Artificial Intelligence / Machine Learning Internship (5 - 6 months) - Hybrid model (AI – Physics) with uncertainty estimation for drilling applications
Log in to apply for this position today.
Apply Now

Share This