Machine Learning in Geometallurgy: A Review of Advances and Case Studies from Peru's Mining Sector
Bibliographic record
Abstract
The integration of artificial intelligence (AI), particularly machine learning (ML), into geometallurgy provides an important opportunity to optimize mineral processing and mine planning.This study synthesizes recent research on ML-based geometallurgical applications and examines advances and challenges within the Peruvian mining sector.A non-experimental, descriptive methodology was employed through a systematic literature review in Scopus, ScienceDirect, and Web of Science (2013-2023).The search identified 312 records, reduced to 238 after removing duplicates.Following title and abstract screening, 170 studies were excluded, and 33 publications met the inclusion criteria, all reporting ML models incorporated into geometallurgical workflows.The selected studies were classified into six application categories, and two Peruvian case studies were examined: Sociedad Minera Cerro Verde, focused on copper concentration improvement, and the Minsur-Pucamarca Unit, centered on gold leaching optimization.Internationally, research is dominated by supervised classification algorithms for mineralogical prediction, while in Peru successful implementations are mainly associated with computer-assisted decision-making in operational contexts.At Cerro Verde, the use of Random Forest and Gradient Boosting models led to a 6.5% increase in copper production and a 0.8% rise in recovery.At Minsur, the Optimus Leach system improved gold recovery prediction accuracy (R² = 0.81) and generated USD 1.4 million in economic benefits during its first year.Overall, the findings indicate that ML-enabled geometallurgy can enhance efficiency, profitability, and sustainability when supported by high-quality data, adequate instrumentation, and multidisciplinary teams, contributing to the digital transformation of Peruvian mining.
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 | 0.005 | 0.015 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.011 | 0.016 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".