Accelerating and Enhancing Petrophysical Analysis with Machine Learning | Schlumberger
Tech Paper

Rıdvan Akkurt, Schlumberger

Tim T. Conroy, Woodside

David Psaila, AnalyticSignal

Andrea Paxton, Schlumberger

Jacob Low, Woodside

Paul Spaans, Woodside

Paper Number
Presentation Date

Accelerating and Enhancing Petrophysical Analysis with Machine Learning

A Case Study of an Automated System for Well Log Outlier Detection and Reconstruction


Recent advances in data science and machine learning (ML) have brought the benefits of these technologies closer to the main stream of petrophysics. ML systems, where decisions and self-checks are made by carefully designed algorithms, in addition to executing typical tasks such as classification and regression, offer efficient and liberating solutions to the modern petrophysicist. The outline of such a system and its application in the form of a multilevel workflow to a 59-well multifield study are presented in this paper.

overflow image
Quad combo logs from wells 13 to 15 (left to right). Neutron, density and DTC logs in well 13 look different from their counterparts in the other two wells, despite very good borehole conditions in well 13. NEUTRON and DENSITY logs track one another in Well 13, while separation is observed in Wells 14 and 15. Also note the noisy nature of the DTC log in Well 13, with very anomalous high readings, when compared to other two wells.

Share This