Deterministic versus unsupervised machine learning approach for facies modeling within the Late Devonian Duvernay Formation, Western Canada Sedimentary Basin, Alberta
Bibliographic record
Abstract
ABSTRACT Facies interpretation from wire-line logs has traditionally been performed through comparison of core-observed facies distributions and associated log response, from which log-based, deterministic algorithms are developed for facies prediction in wells lacking core control. In contrast, stochastic unsupervised learning analyzes and automatically clusters recurring well log data associations without calibration to core observations. Using petrophysical and core description data collected from the Late Duvernay Formation of Alberta, Canada, this study investigates whether unsupervised machine learning detects lithologic attributes at higher resolution than the traditional deterministic approach. The unsupervised machine learning methodology nonnegative matrix factorization with k-means clustering (NMFk) is applied to identify recurring petrophysical groups independent of core observations. The NMFk groups are compared to four depositional facies associations independently predicted through deterministic assignment of well log cutoffs established by comparing log response to core-observed facies association distributions. Depositional facies associations include the undifferentiated Ireton Shale that overlies the Duvernay and the open to transitional basin, restricted basin, and allochthonous basinal carbonates of the Duvernay. Four NMFk groups are identified; three groups coincide with varying shale lithologies and one group with carbonate lithologies. All of the groups are similar to the depositional facies associations recognized by the deterministic approach. In addition, NMFk partitions the deterministic restricted basin facies association into subdivisions that are likely distinguished by unique petrophysical responses related to variations in organic richness and associated matrix pore fluid.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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".