The Interpretation of Pyrite Laser Ablation-Inductively Coupled Plasma-Mass Spectrometry Maps Using Machine Learning: A Case Study of the Colosseum Au Deposit, Southern California
Bibliographic record
Abstract
Abstract This study explores the application of machine learning techniques for an enhanced interpretation of pyrite laser ablation-inductively coupled plasma-mass spectrometry (LA-ICP-MS) maps. The Colosseum Au deposit, in southern California, was considered as a case study. Colosseum is genetically related to a rhyolitic breccia-pipe complex, where Au mineralization is associated with two main pyrite generations—early pyrite and late pyrite. Our machine learning workflow involves the detection of distinct compositional zones in individual maps through unsupervised clustering, and a second clustering step where these zones are grouped by compositional similarity, enabling the direct comparison between different maps and providing a compositional overview of pyrite representative of the various styles of mineralization present in the deposit. Clustering of individual maps correctly differentiated between distinct growth zones in early pyrite, fractures that crosscut early pyrite growth, and zones of late pyrite growth, matching petrographic observation. All the zones detected by this first step, in turn, were classified into two compositionally distinct groups and a third transitional group, enabling the direct comparison between maps while keeping petrographic consistency. For Colosseum, our approach revealed that (1) Au is more abundant in late pyrite than early pyrite, but significant amounts can be found in both generations and in both Colosseum mineralized breccia pipes; (2) the transition from early to late pyrite is represented by a change from a Co-Ni-Te–rich end member to a Cu-Ag-Zn-Sb-Tl–rich end member; and (3) Au is directly correlated with As in both pyrite generations.
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 | 0.000 |
| Open science | 0.001 | 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".