Society: SPE, November 12, 2020
In this paper, collaborative teams from Schlumberger and ADNOC, present a solution to automatically perform data QC, bad data identification and log reconstruction (correcting for borehole effects, missing data, despiking, etc.) of well data.
The standard approach has been to manually correct logs for various anomalies and normalize them at the field scale, a very time-consuming and often very subjective approach. The workload is even more time-consuming for mature fields where log data has been collected across multiple vintages of logging tools and from multiple vendors, for decades.
The study targets quad-combo logs acquired since the 1960s in a giant Lower Cretaceous carbonate onshore field in Abu Dhabi. The solution consists of several advanced algorithms guided by domain knowledge and physics based well logs correlation, all orchestrated via an AI platform. The machine-learning (ML) based solution demonstrated its effectiveness while correcting logs for depth-shifts, removing outliers, identifying erroneous readings and reconstructing missing curves.
The full cycle of ML training, logs editing, and results review was accelerated from 15 days of manual well by well log editing down to two days for the new automated process.
AI for petrophysical data conditioning and reconstruction
Petrophysical data engineering
Download the PDF to read the full article.
Authors: Maniesh Singh, ADNOC Onshore; Gennady Makarychev and Hussein Mustapha, Schlumberger; Deepak Voleti, ADNOC Onshore; Ridvan Akkurt, Schlumberger; Khadija Al Daghar, Arwa Ahmed Mawlod, Khalid Al Marzouqi, and Sami Shehab, ADNOC Onshore; Alaa Maarouf, Obeida El Jundi, and Ali Razouki, Schlumberger