Total Organic Carbon Predictions from Lower Barnett Shale Well-log Data Applying an Optimized Data Matching Algorithm at Various Sampling Densities

• Published in: Pure and applied geophysics Vol. 177; no. 11; pp. 5451 - 5468
• Main Author: Wood, David A.
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01.11.2020; Springer Nature B.V
• Subjects: Algorithms; Cores; Correlation; Data; Earth and Environmental Science; Earth Sciences; Evaluation; Geophysics/Geodesy; Learning algorithms; Machine learning; Matching; Methods; Model accuracy; Organic carbon; Predictions; Sampling; Sedimentary rocks; Shale; Shale gas; Shales; Total organic carbon; Well logs; Wells; data-matching machine learning; data record sample densities; Well log TOC estimates; correlation-free feature selections; zoomed-data interpolation; model transparency
• ISSN: 0033-4553; 1420-9136
• DOI: 10.1007/s00024-020-02566-1

Accurately estimating total organic carbon (TOC) from suites of well logs is essential as it is too costly and time consuming to take direct measurements from core samples in many wells. Unfortunately, the several methods developed over recent decades, based on various correlations and correlation-based machine learning methods, do not provide universally reliable, accurate or easily auditable TOC predictions. A method is developed and its viability evaluated exploiting a promising correlation-free, data-matching routine. This is applied to published well-log curves, with supporting mineralogical data and measured TOC, for two wells penetrating the Lower Barnett Shale formation at distinct settings within the Fort Worth Basin (Texas, U.S.). The method combines between 5 and 10 well log features and evaluates, on a supervised learning basis, multiple cases for nine distinct models at data- record-sampling densities ranging from one record for every 0.5 ft to one record for every 0.04 ft. At zoomed-in sampling densities the model achieves TOC prediction accuracies for the models combining data from both wells of (RMSE ≤ 0.3% and R2 ≥ 0.955) for models involving 6 and 10 input variables. It is the models involving six input variables that have the potential to be applied in unsupervised circumstances to predict TOC in surrounding wells lacking measured TOC, but that potential requires confirmation in future multi-well studies.