Log-Derived Permeability in a Heterogeneous Carbonate Reservoir of Middle East, Abu Dhabi, Using Artificial Neural Network
Bibliographic record
Abstract
Abstract Estimation of permeability in carbonates has been a challenge for many years. Well logs, particularly high-resolution logs, are influenced by rock properties. Therefore, when there is limited core coverage and scarce high-resolution log data, permeability estimation using the standard suite of logs (resistivity, density, neutron, caliper, gamma ray) is crucial for populating and constraining a 3D geological permeability model. Two new traces, the deep and micro resistivity activity traces, are derived from the corresponding resistivity logs. The activity traces are not affected by fluid effects and, thus, preserve better the formation characteristics. Permeability estimation using an artificial neural network approach is made through a two-step process. In the first step, probabilities of log-derived rock types are estimated from a trained neural network using the micro and deep resistivity activity traces, and the standard suite of logs as input. In the second step, a separately trained neural network uses rock type probabilities from step 1, along with a suite of logs to predict permeability. Two examples are provided to illustrate the validity of the method in predicting permeability in a heterogeneous carbonate reservoir located in Abu Dhabi, UAE. This reservoir exhibits permeability ranging from half a milli-Darcy to more than 20 Darcies. The first example represents a blind test where the estimated permeability shows good agreement with core permeability data. The second example demonstrates the predictive capability of the method in a non-cored well that is located in the vicinity of cored wells. The estimation technique is robust and was found valuable to supplement core data in the construction of geo-cellular permeability models.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".