Artificial intelligence and machine learning to enhance critical mineral deposit discovery
Bibliographic record
Abstract
• ML in mineral exploration struggles with low-quality data and interdisciplinary gaps. • Statistical model and data prep can improve exploration dataset consistency. • Specific focus on ML is limiting, a broader data science approach would be beneficial. • Exploration needs blending ML with geoscientific expertise. The application of machine learning (ML) in mineral exploration has garnered significant attention and investment, yet greenfield mineral deposit discovery rates remain unchanged. This limited success stems from challenges such as low data quality outside existing mines, inconsistent sampling, limited interdisciplinary collaboration, and the unique complexity of geoscientific problems. Unlike traditional ML applications, mineral exploration demands a focus on subtle variations within finite search spaces, requiring an exploratory rather than accuracy-driven approach. Effective implementation necessitates collaboration between data scientists and geoscientists, leveraging ML as a tool to test hypotheses and analyse diverse datasets. However, reliance solely on ML overlooks the critical role of human creativity in generating and evaluating novel search strategies. Broader adoption of statistical methods, integrated spatial models, and innovative data preparation techniques can address the inconsistencies in exploration datasets. Furthermore, subjective modelling approaches, such as Delphi methods, can complement ML by incorporating expert judgment to overcome predictive limitations. By combining technological advancements with human expertise, the mineral exploration industry can enhance discovery success and achieve long-term sustainability. There is an important short-term requirement to secure the supply of critical metal resources, as their supply from existing mines and brownfield exploration is finite and commercial recycling of critical metals is still in its infancy.
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 | 0.006 | 0.024 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.004 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.006 | 0.002 |
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".