Machine Learning in Oil-base Mud Microresistivity Imager Interpretation

Westside Houston

Speaker:

Seminar Date: Nov 15 2019

Registration Opens: Nov 06 2019 - Nov 14 2019

Time: 11:30 AM - 01:00 PM (US CDT)

Admission/Registration Link: None

Donation Link: None

Meeting/Webinar Link: None

Contact: Bernd Ruehlicke ( Houston, TX, USA, SPWLA Houston Chapter)

Corresponding: vpwestside@spwla-houston.org

Fees:

For Student: $10

For Member: $15

For Non-member: $15

ABSTRACT:

The new-generation oil-base mud (OBM) micro resistivity imagers provide photorealistic high-resolution quantified formation imaging. One of the existing interpretation methods is the inversion-based workflow providing a high-quality resistivity image, button standoff, and formation permittivities at two frequencies. In this presentation, I will present two machine learning approaches based on artificial neural networks (NN) where NNs can either help the inversion or be used as a new workflow for quantitative interpretation of OBM imager data as an alternative to the inversion-based method.

BIOGRAPHY:

Zikri Bayraktar is a senior machine learning research scientist at the Schlumberger-Doll Research Center in Cambridge, MA focusing on artificial intelligence and machine learning-based solutions to engineering problems at various scales ranging from the borehole to seismic. He received his Ph.D. in electrical engineering and a Ph.D. minor in computational science in 2011 from Pennsylvania State University. Dr. Bayraktar is also an alumnus of the Schreyer Honors College Integrated Undergraduates/Graduated program at Penn State with MSc and BSc degrees in electrical engineering. After graduation, he completed a year-long post-doctoral assignment at Penn State and then joined IBM Semiconductor R&D Center in 2012 as an advisory engineer focusing on the production of IBM server microchips. Since 2014, Dr. Bayraktar is with Schlumberger initially in the computational electromagnetic group and currently in the automated geology department. Dr. Bayraktar has published more than 45 journal and conference papers with multiple patent submissions focusing on machine learning applications in the oil and gas industry. He is a member of the Society of Petroleum Engineers (SPE), Society of Petrophysicists and Wirelog Analysts (SPWLA) and IEEE. Dr. Bayraktar is also serving as one of the 2020 Distinguished Speaker of the SPWLA and the lead-guest editor of the IEEE Antennas and Propagation Wireless Letters Special Cluster Issue on “Machine Learning Applications in Electromagnetics, Antennas and Propagation”.


Parking Info: Visitors are requested to reverse park, note their license plate number, and sign in at the main reception.
 
Please register by Nov 12th, 2019 @ 12 pm to reserve lunch and pre-registration
Contact: Jacob Anderson 
Corresponding: Jacob.anderson10@gmail.com // 337 417 1529

After Payment/Registration, you will receive a confirmation email containing information about joining the seminar.

40 / 40