Segmenting identified fracture families from 3D fracture networks in Montney rock using a deep learning-based method
Bibliographic record
Abstract
Fractures are critical to subsurface activities such as oil and gas extraction, geothermal energy production, and carbon storage. Hydraulic fracturing, a technique that enhances fluid production, creates complex fracture networks within rock formations containing natural discontinuities. Accurately distinguishing between hydraulically induced fractures and pre-existing discontinuities is essential for understanding hydraulic fracture mechanisms. However, this remains challenging due to the interconnected nature of fractures in three-dimensional (3D) space. Manual segmentation, while adaptive, is both labor-intensive and subjective, making it impractical for large-scale 3D datasets. This study introduces a deep learning-based progressive cross-sectional segmentation method to automate the classification of 3D fracture volumes. The proposed method was applied to a 3D hydraulic fracture network in a Montney cube sample, successfully segmenting natural fractures, parted bedding planes, and hydraulic fractures with minimal user intervention. The automated approach achieves a 99.6% reduction in manual image processing workload while maintaining high segmentation accuracy, with test accuracy exceeding 98% and F 1 -score over 84%. This approach generalizes well to Brazilian disc samples with different fracture patterns, achieving consistently high accuracy in distinguishing between bedding and non-bedding fractures. This automated fracture segmentation method offers an effective tool for enhanced quantitative characterization of fracture networks, which would contribute to a deeper understanding of hydraulic fracturing processes.
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 | 0.001 |
| Bibliometrics | 0.002 | 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) | 0.001 | 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".