A machine-learning workflow to integrate high-resolution core-based facies into basin-scale stratigraphic models for the Wolfcamp and Third Bone Spring Sand, Delaware Basin
Bibliographic record
Abstract
Abstract The characterization of subsurface reservoirs that are dominated by mudrock facies is hindered by the inherent heterogeneity and high degree of spatial variability typical of mudrock depositional systems. Subsurface reservoir properties that include porosity and permeability, fluid saturations, stratigraphic thicknesses of reservoir units, and source rock potential are ultimately controlled by the spatial distribution of sedimentary rock facies, which supports efforts to improve subsurface characterization workflows. Although core-based data provide direct measurements of rock attributes that are used to inform static reservoir models, capturing high-resolution core-based rock facies and downscaling these observations to tie to lower-resolution wireline logs remains a challenge. The effort to integrate core-based facies to reservoir-scale models is especially difficult when trying to capture thin-bedded heterogeneity that is common to mudrock systems. Herein, a workflow is developed and applied to visualize and integrate multivariate and spatially complex core-based data sets with wireline logs. Formation-specific core-based chemofacies training data sets are developed by integrating core descriptions with chemofacies clusters developed from high-resolution X-ray fluorescence core scanning. Core-based rock attribute data (e.g., XRD mineralogy, total porosity, and total organic matter content) are used to describe the chemofacies, providing a means to upscale low-resolution rock attribute measurements to high-resolution core-based chemofacies. Supervised core-based chemofacies training data sets are then used with neural network multiclass classification machine-learning tools to train triple combo wireline logs (gamma ray, deep resistivity, bulk density, and neutron porosity) to predict rock facies from wireline logs, providing a new approach to apply core-based facies classifications to wireline log studies. A basin-scale case study that applies this workflow is described for the Third Bone Spring Sand and units of the Wolfcamp Formation in the Delaware Basin of West Texas, United States.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.007 | 0.003 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".