Toward a Semisupervised Machine Learning Application to Seismic Facies Classification
Bibliographic record
Abstract
Summary Seismic facies classification is a machine learning task that maps seismic attributes to classes. The training data for these problems are commonly governed by wells, which are characteristically sparse. Most seismic facies classification problems utilize supervised machine learning algorithms, but supervised algorithms are prone to overfitting in the presence of minimal training data. However, semisupervised algorithms are designed for problems with small training sets because they incorporate both the labelled and the unlabelled data during training. Semisupervised algorithms are largely unexplored in geoscience applications, and we explore their potential here on a study using the 2D SEAM model. We provide a workflow for performing seismic classification of this synthetic model that consists of four stages. The earlier stages synthesize the seismic data from the model and build the classes for the labelled data using unsupervised learning. A latter stage involves estimating a ground-truth facies model using machine learning where the training data amount to roughly 0.2% of the full dataset. We show that our semisupervised algorithm can capture more detail compared to a popular supervised algorithm, XGBoost, and this supports the hypothesis that semisupervised algorithms can recover better predictions than supervised methods in the context of minimal training data.
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 | 0.003 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 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".