An Introduction To Big Data & Machine Learning in Petrophysics

The last technical session  "An Introduction To Big Data & Machine Learning in Petrophysics"

took place on Wednesday 15th of November 2017: 16h00 -19h30
Auditorium Le Palatin - Office Schlumberger
1, cours du Triangle, 92936 La Défense Cedex

Some people followed the presentations via a Web Lync 

This session was dedicated to Hugues Monrose, past president of SAID, who passed away on October 20 , 2017 ( see below ) 



16:00 – 16:20     Welcome, Introduction

16:20 - 16:30    Hommage à Hugues Monrose, past president of SAID in 1998 & 1999, Jacques Delalex,  VP SAID 

16:30 – 17:30     Use and applicability of machine learning to formation evaluation, Emmanuel CAROLI, Total ( Pdf here below ) 

17:30 – 18:00    Coffee break

18:00 – 18:40     Partial log reconstruction using Machine Learning, Valérian GUILLOT, Héloïse BEURDOUCHE, Schlumberger

18:40– 19:15     Marker recognition and validation using Data Analytics and Machine Learning , Héloïse BEURDOUCHE, Schlumberger

19:15 – 19:30     Conclusion and discussions





Use and applicability of machine learning to formation evaluation 
Emmanuel CAROLI, Total

Fast screening of a large number of wells (hundreds or thousands) is always a challenge but remains a real game changer for data rooms or DRO (Discovered Resources Opportunities). Classical deterministic approaches based on physics are generally time consuming and do not ensure that all interpretation scenarios have been envisaged. Deep learning can be a solution: a large data base including raw and processed data over a wide range of geological contexts has been tested with a neural network approach. Results compare well with classical deterministic outputs provided the training phase could mitigate some pitfalls such as database representativeness, minimum required training dataset or processing constrains.

Emmanuel is graduated from Ecole Normale Supérieure, Ecole des Mines and IFP. He joined TOTAL in 2003. Appointed abroad in Netherland, Argentina and Angola, he has been petrophysicist for 13 years and is now senior specialist in formation evaluation, in charge of an R&D project on petrophysics. His domains of interest are log modeling, fluid characterization and new interpretation methods. He is SAID president since June 2017.


Partial log reconstruction using Machine Learning
Valérian GUILLOT, Héloïse BEURDOUCHE, Schlumberger

Logs can be impacted by bad hole or measurement issues on some depths only. The remaining part of the logs, the good values, contains valid information on the geology of the borehole that can be used with Machine Learning to guess what would have been log values in the bad hole areas and correct the logs. Using nearby wells, even more information can be used by the model to learn so that it predicts log values in the bad hole sections.

Valérian is graduated from Institut National Polytechnique de Lorraine and hold a Master’s from Ecole Nationale Supérieure de Géologie de Nancy. He is currently looking after Digital Solutions in Schlumberger –  Software Integrated Solutions.


Marker recognition and validation from machine learning and analytics
Héloïse BEURDOUCHE, Schlumberger

Geologists have often to re-pick markers, either because existing ones are not consistent, partially missing or naming of the same markers are different based on people or company history. Using all existing markers available and data analytics algorithms it is possible to identify markers that are identical but have different names or markers which are supposed to show the same formation but aren’t actually located at the right depth. Then machine learning can be used to guess the depth of the wrong or missing markers in multi-well context

Héloïse is graduated from Ecole et Observatoire des Sciences de la Terre (EOST, previously called IPGS) and Ecole Nationale Superieure de Geologie (ENSG). She joined Schlumberger in 2012. Heloise was hired as a Quality Engineer on Techlog Wellbore Software Platform, more specifically on the link to Petrel E&P Software Platform, the Techlog collaborative solutions and workflow engine. After almost 4 years, she is appointed Business Analyst for Wellbore Analytics solutions, working with end users and development teams on analytics solutions for wellbore data and processing.