Enhancing Joint Detection and RQD Estimation in Acoustic Televiewer Imaging Through Automated Instance Segmentation and Deep Learning
Bibliographic record
Abstract
ABSTRACT: Under certain ground conditions, obtaining adequate core specimens for logging can be challenging, leading to low recoveries and poor rock quality designation (RQD). Borehole well logging offers a cost-effective alternative to handling expensive core samples for logging purposes, particularly advantageous for projects constrained by limited resources. To construct a secure subsurface structure, it is vital to identify and detect weak planes. Borehole imaging provides a fast and efficient way to characterize fractures. Acoustic televiewer (ATV) imaging is an effective tool in fracture detection and RQD estimation. However, the conventional process of manually detecting and characterizing joints in ATV images is laborious, subjective, and inconsistent. This study introduces an automated method for joint detection and RQD estimation. For the study, 1390 meters of data from 24 boreholes across 5 different mines were collected. A deep learning algorithm called Mask R-CNN was utilized. The model's predictions yielded a mean absolute error of 1.4% for the RQD prediction. This indicates that the model is effective in estimating RQD. By automating joint detection and RQD estimation, the proposed method streamlines and enhances the process of automated subsurface structure analysis. 1. INTRODUCTION Understanding the structural setting of rock mass is crucial for designing safe and efficient geomechanical projects. These characteristics define the rock's behavior during excavation and influence potential failure mechanisms. However, acquiring accurate geotechnical data remains a challenge, often leading to uncertainties and hindering design reliability (Manzoor et al., 2020; Medinac and Esmaeili, 2020). Drill core logging and borehole well logging are prevalent techniques for rock characterization. In core logging, the Rock Quality Designation (RQD) is traditionally assessed through direct measurement or subjective judgment (Hadjigeorgiou, 2012). These methods are time-consuming, prone to inconsistencies between loggers, and impeded by poor core recoveries or low rock quality (Usta and Esmaeili, 2023; Rodgers et al., 2020; Esmaeili, 2019; Bhuiyan and Esmaeili, 2018). In addition, handling core samples can be expensive for the scope of some projects. In these situations, borehole well logging can be a suitable alternative for rock mass characterization.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| 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".