Abstract

Oman Drilling Project was conducted as a part of the International Continental scientific Drilling Program (ICDP) from 2017 to 2018 and several boreholes including four across the crust-mantle transition zone were drilled in the program. A full suite of slim and conventional wireline log data included the high-resolution resistivity borehole images was acquired nearby the coring borehole. The full core samples were acquired from the coring boreholes and various core analysis were conducted to create detailed core description manually with significant time and effort. Identification of geological facies is crucial to understand the complicated crust-mantle transition zone. If this facies recognition is achieved using a more automated way from available logging data, it enables to optimize the operation cost and analysis time, which will be useful for future scientific ultradeep ocean drilling Mohole To Mantle (M2M) project planned by the International Ocean Discovery Program (IODP).

We propose unsupervised AI-boosted geological facies analysis(FaciesSpect) method using borehole images and other petrophysical log data on the Oman Drilling Project. Among the available logging data, borehole images(resistivity type with dynamic color scaling) and two log curves (Fe and Ca) from geochemical spectroscopy log data were selected for the automatic facies analysis. Fifteen clusters were classified from the selected log data with the proposed approach. The clusters’ distribution trend was consistent with cuttings and core lithologies which composed of the three major lithology zones: Dunite, Gabbro, and Harzburgite.

Another two automatic facies analysis methods were also attempted which are Class-Based Machine Learning (CBML)and Heterogeneous Rock Analysis (HRA)to compare the result with FaciesSpect. These methods have already used commercially and well-established methods which can validate newer FaciesSpect method result. The three different methods’ class results were compared. They are matched at major lithology change boundaries. Furthermore, FaciesSpect class result makes easier to compare with core lithologies and gave a positive impression due to the advantage of using borehole image data as input data.

In this case study, we applied the automatic facies analysis to complicated crust-mantle transition zone at the first time. We validated FaciesSpect method is useful to quickly understand the overall lithology trend. It also saved analysis time and provides a fit-for-purpose result which does not relied on the individual interpreter’s experiences. The high-resolution borehole image and geochemical spectroscopy logs are crucial inputs for automatic facies analysis in this study.

This content is only available via PDF.
You can access this article if you purchase or spend a download.