Insights on formation damage associated with hydraulic fracturing using image analysis and machine learning
Bibliographic record
Abstract
Abstract Hydraulic fracturing is a well‐recognized technique used to produce as much as possible from unconventional resources. Yet, the communication between the main fracture and the fracture process zone (FPZ) around the primary fracture is still a mystery. Some research was conducted on actual samples to statistically examine the behaviour of these parameters along and parallel to the main fracture and the degree of damage/enhancement induced in the FPZ. Therefore, to understand the formation damage near the hydraulic fracture and its relation to the induced fractures, I am introducing a comprehensive analysis to shed light on some of the observations that I drew through the investigation throughout the previous years. Image analysis was performed on tight core samples under the triaxial compression test in addition to other sources of data and image analysis using data mining and machine learning. The number, length, and aspect ratios of the microcracks were measured. The drainage distance from the main fracture and the development of the microcracks were analyzed. A periodic cycle distribution was apparent around the main fracture and was related to the orientation of the microcracks and the surface roughness of the main hydraulic fracture. These results will help differentiate between the natural and induced microcracks. Additionally, a clear understanding of the relation between the primary fracture and the microcracks, the direction of the microcracks relative to the primary fracture, and the effectiveness of hydraulic fractures in the real world is presented. This work helps find the relation between the natural fractures and the induced fractures in a more realistic way, which helps in the design of the hydraulic fracture implementation and production increase.
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 | 0.004 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 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".