Pitfalls and insights from a machine learning contest on log facies classification
Bibliographic record
Abstract
FORCE: Machine Predicted Lithology was a challenging facies classification contest using well logs from the North Sea’s Norwegian coast. As we built different machine learning workflows to predict the lithofacies best, we encountered a few interesting challenges. The first involved merging different lithofacies to one single class and balancing the predictions accordingly with the class frequencies. The second was related to the contest metric. It did not consider the imbalanced classes. In fact, the most sampled classes, like the shale, which corresponded to 62% of the observations, were more critical. Our initial workflow focused on balancing the classes, and our balanced accuracy metric score was 0.56, while the contest metric was −1.35. In the second approach, we threw off the imbalanced classes consideration, and by doing so, we could improve the contest metric to −0.58, but with a trade-off on the balance accuracy score, which decreased to 0.41.
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 | 0.065 | 0.136 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.004 | 0.004 |
| Science and technology studies | 0.004 | 0.005 |
| Scholarly communication | 0.010 | 0.008 |
| Open science | 0.003 | 0.006 |
| Research integrity | 0.003 | 0.007 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
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".