Statistical techniques for leveraging geochemical data in ore and non-ore characterization for mining and environmental stewardship
Bibliographic record
Abstract
The timeline from exploration through to extraction of a mineral deposit often spans decades, resulting in multi-generational geochemical data collected utilizing a variety of digestion and analytical methods. To extract value from these diverse datasets is challenging. This is due to lack of comparability in elemental concentrations produced by different digestion and analysis methods. Relationships between these multi-generational, variable digest geochemical datasets are typically non-linear, requiring a more sophisticated approach to data integration. Two case studies are presented to address this integration problem using simple machine learning workflows. Case study 1 outlines a workflow to derive a common molar element ratio used in porphyry deposit exploration and alteration quantification (2Ca+K+Na)/Al from four-acid digestion data as a proxy for the degree of feldspar destruction caused by hydrothermal metasomatism. It further illustrates the prediction of this ratio (derived from four-acid digestion geochemistry) using aqua regia digestion geochemical data as an input. Case study 2 illustrates the use of aqua regia derived Ca as a proxy for neutralization potential in mineralogical systems dominated by carbonate dissolution in aqua regia digestion, and presents a workflow to predict neutralization potential from four-acid data, trained to aqua regia Ca. Both case studies showcase the integration of aqua regia and four-acid datasets via non-linear machine learning algorithms, which exploit the mineralogical and elemental controls governing differences between digestion methods.
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 | 0.020 | 0.052 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.007 | 0.008 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.003 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.002 | 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".