The S3 orogenic gold targeting algorithm: A case study from the Timmins gold camp, Ontario, Canada
Bibliographic record
Abstract
ABSTRACT Mineral exploration targeting of orogenic gold deposits is challenging, especially in concealed terrains. To meet this challenge, a practical orogenic gold targeting method using structural complexity (SC), a self-organizing map (SOM), and a supervised deep neural network (SDNN) is developed. Because orogenic gold deposits are structurally controlled, the use of high-resolution aeromagnetic data to delineate concealed structures is routinely performed by mineral explorationists. SC is defined as the intersection density or the orientation diversity of linear structures, which can be derived from magnetic data or acquired by geologic structural mapping. Common features from the SC and the magnetic data can be grouped together into one class by the SOM, essentially an unsupervised neural network classification method. A small percentage of the data also can be designated as anomalous classes by the SOM. The SOM results can support gold exploration targeting in areas lacking any known gold deposits or occurrences. However, the predictive targeting of orogenic gold mineralization also can be achieved with the support of an SDNN using the SC results. The SDNN can be trained by the SC data over known gold deposits or occurrences. The top few percentiles of the target probabilities are used for target generation. Because the orogenic gold targeting process involves SC, SOM, and SDNN, it may be called the S3 method. Our S3 method is tested using public domain high-resolution aeromagnetic data covering the world-class Timmins gold camp in the Abitibi greenstone belt, Superior Province, Ontario, Canada. The results document that the S3 algorithm is an effective and robust artificial intelligence-supported method to target concealed orogenic gold mineralization.
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 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".