From Rocks to Pixels: A Protocol for Reproducible Mineral Imaging and its Applications in Machine Learning
Bibliographic record
Abstract
Identifying minerals is essential for geology, mineral exploration, engineering, and environmental sciences. Recent advances in machine learning have illustrated its potential as a fast, cost-effective, and reliable tool for identifying minerals from photographs or photomicrographs. However, in the recent literature, few studies have been dedicated to image acquisition. Machine learning generally requires reproducible, high-quality data to perform complicated tasks such as mineral identification to avoid common pitfalls. In this paper, we propose a practical image acquisition protocol for optical microscopes. This protocol focuses on ensuring reproducibility and enhancing image quality. To favor reproducibility, we detail dealing with camera errors, using reference color gauges, and establishing experimental parameters such as the external light source and temperature. For image enhancement, we explain the importance of lighting and its impact on machine learning precision, selection of the objective, and white balance calibration. In addition, we trialed the protocol on heavy mineral concentrate from till samples (20 species) with a typical deep learning model and it revealed that minor lighting modification (<5% difference in one channel) significantly increased misclassification rates: kyanite from 6.4% to 24.9% and monazite from 6.5% to 42.9%.
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 | 0.004 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.014 | 0.008 |
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".