A study of faults in the Superior province of Ontario and Quebec using the random forest machine learning algorithm: Spatial relationship to gold mines
Bibliographic record
Abstract
This paper uses the random forest (RF) algorithm to produce two maps of orogenic gold prospectivity (MPM) across the entire Superior geologic province of Ontario and Quebec, Canada. One MPM of this entire study area is based on a compilation of mapped faults while the other is based on a manual interpretation of lineaments from airborne magnetic data. In addition, we have created four MPMs over the Abitibi region as the MPM map of the entire Superior is characterized by a mapping bias due to more intense mapping of faults over the Abitibi portion of the study area with respect to the rest of the Superior province. There are three RF maps generated over the Abitibi region based on faults, fault density and fault intersection density, faults + magnetic data and faults + gravity + magnetic data. To reduce the effect of the fault mapping bias, we developed a fourth map based on a knowledge driven (weighted sum technique). Statistically the best MPM is based on the faults, gravity and magnetic data. The major predictors of gold are NW-SE, NE-SW, EW trending faults, fault intersection density between EW and NW trending faults and to a lesser extent fault density and a magnetic vertical gradient image. In addition, we compare two greenstone belts in three dimensions with respect to their potential for gold exploration. We conclude that the Larder Lake greenstone belt is more fertile with respect to gold mineralization than the Swayze greenstone belt due to deeper penetrating faults which have greater potential for tapping gold mineralized fluid from the mantle or lower crust. Our final MPM map has identified prospective areas that contain known gold mines as well as areas that do not contain any known gold mines. These prospective areas may be prime for orogenic gold exploration.
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 | 0.002 | 0.001 |
| 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 | 0.000 |
| Open science | 0.000 | 0.000 |
| 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".