Machine learning uncovers provenance of source rocks for volcano-sedimentary lithium mineralization in South China
Bibliographic record
Abstract
The Early to Middle Triassic sedimentary units in South China, belonging to the so-called ”Green bean rock” (hereafter ”GBR”), host significant volumes of potentially economic clay-type volcano-sedimentary lithium (Li) mineralization. However, the source material and the processes that led to the enrichment of Li in these clay deposits remain unclear. This is especially true of the uncertain provenance of the igneous material that eventually forms this Li mineralization. In this study we apply machine learning to geochemical data from igneous rocks and GBR samples to determine the nature of the source rock, the type and source of the magma associated with the GBR, and the initial Li contents of these protoliths. The results of this Random Forest (RF) modeling indicate that the GBR protolith was entirely derived from a dacitic magma, whereas the petrology of these samples indicate that the source magma for the GBR protolith was derived from an intermediate to acidic dacite-rhyolite magma. The RF modeling suggests the protolith volcanic ash was primarily derived from the Sanjiang Orogenic Belt and the Shiwandashan Belt in South China. The location and distribution of the GBR relative to the Sanjiang Orogenic Belt and the Shiwandashan Belt indicates that the GBR has a significant directionality with preferential NE-SW and N-S orientations, indicating the likely influence of paleomonsoon conditions during GBR formation. The Li content of the GBR protolith is <50 ppm, with 68.75% of the data generated during this study having a Li concentration of <20 ppm, indicating that the Li within the GBR was primarily derived from water-rock interactions during the deposition period. This study provides new insights into the process involved in the formation of the GBR and the associated lithium enrichments in this region as well as outlining the value in integrating machine learning models with big data in mineral deposit research.
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 | 0.000 | 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 | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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".