Data driven deep learning method for quantifying groundwater flux in deep fractured aquifers with the fractured rock passive flux meter
Bibliographic record
Abstract
• Groundwater fluxes in fractured aquifers were measured using the Fractured Rock Passive Flux Meter (FRPFM). • A deep learning model (YOLOv8) was applied to identify dye marks on fabric and quantify flux parameters from laboratory experiments. • YOLOv8 achieved high accuracy with precision (P) = 0.99 and recall (R) = 0.75 for object detection and mask predictions. • Groundwater fluxes were estimated with relative errors of ±23 % ( Δ z d y e ) and ±16 % ( A d y e ), yielding an overall ±20 % error. • The Precision-Recall curve analysis suggests that model accuracy can be further improved with a larger training dataset. Movement of groundwater in fractured aquifers is highly variable and depends on many factors besides fracture apertures. Hence, downhole techniques that directly map fracture locations, orientations, apertures, and measure groundwater fluxes are valuable tools. Here, we explored the possibility of using the Fractured Rock Passive Flux Meter (FRPFM) with visible dye component to measure groundwater fluxes and identify geometric fracture parameters through laboratory experiments. For this purpose, we used the deep learning model YOLOv8 to accurately identify the dye marks and to measure their areas A d y e and widths Δ z d y e from images of the dyed fabric. Results showed that groundwater fluxes were measured with relative errors of ±23 % and ±16 % based on Δ z d y e and A d y e , respectively, with an overall relative error of ±20 %. The YOLOv8 model showed very good accuracy by achieving high precision P = 0.99 and recall R = 0.75 for both object detection and mask predictions. The P - R -curve showed that accuracy can be improved by using more images to train the model.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".