Application of UMAP to identify refined gold sources using chemical composition analysis
Bibliographic record
Abstract
A substantial fraction of global gold production originates from unregulated or illegal operators, which generates severe environmental damage, threatens human rights, and could destabilize local and even national economies. Demonstrating the true origin of gold, with a geochemical fingerprint, remains a major challenge, particularly when similar sources are mixed. To address this issue, we apply the Uniform Manifold Approximation and Projection (UMAP), a nonlinear dimensionality-reduction method designed for analyzing high-dimensional datasets. In this study, gold compositional data were expressed as probability vectors and compared using Hellinger distance, enabling the visualization and clustering of samples across different stages of the production chain. Our analysis demonstrates that while beneficiation processes alter the absolute concentrations of certain elements, distinctive geochemical signatures are retained between natural gold samples and manufactured products. This persistence allows UMAP to reveal meaningful patterns of similarity and distinction, even when traditional methods fail to differentiate mixed or transformed materials. The results demonstrate that UMAP is a robust, powerful tool to support traceability and enhance measures against illegal gold mining. By strengthening the scientific basis for source attribution, this approach provides an innovative workflow to support regulatory frameworks and judicial actions aimed at disrupting illicit gold trade and promoting responsible resource management.
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 | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".