Innovative AI-Driven Core Image Analysis for Reservoir Characterization
Bibliographic record
Abstract
Abstract This study introduces an AI-driven workflow designed to predict oil saturation along with geological facies from core images, addressing the limitations associated with traditional wireline logging and the inherent subjectivity of visual core analyses. Specifically, the method targets operational scenarios where logging is unavailable or limited due to operational and HSE restrictions, and where core or cutting samples represent primary datasets. The method systematically classifies color variations from core images captured under both ambient white light and ultraviolet (UV) illumination using (1) Photoshop’s color-detection tools and (2) unsupervised machine learning techniques (e.g., Principal Component Analysis and K-means clustering). A custom-developed application converts these classified color features into quantitative saturation logs, automating workflows traditionally performed visually or semi-quantitatively by geologists. Validation against conventional saturation logs demonstrated a strong quantitative agreement, ensuring reliability. Notably, the method proved highly adaptable, and hence can be demonstrating utility for analyzing cutting samples in the absence of core data or wireline logs. The significant novelty lies in transforming previously unused qualitative image data into actionable quantitative insights, effectively bridging qualitative visual assessment with quantitative reservoir characterization. This advancement offers scalable and practical solutions, significantly enhancing subsurface evaluation capabilities and reservoir characterization accuracy, particularly in challenging operational contexts.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".