A Data-Driven Approach for Exploring Unconventional Lithium Resources in Devonian Sedimentary Brines, Alberta, Canada
Bibliographic record
Abstract
Abstract Lithium-rich (Li-rich) sedimentary brine has emerged as a valuable unconventional resource, driven by the blooming global market, advancements in direct extraction technologies, and a lower environmental impact compared to traditional mining methods. However, resource delineation and estimation remain challenging due to inefficient field sampling and unreliable correlations between Li concentration ([Li]) and environment-sensitive geochemical indicators. Supported by public data and newly acquired measurements of water chemistry for Alberta Devonian brines, we developed a cutoff-based data-driven approach to extract Li-rich environmental characteristics in the probability domain to predict [Li] levels at locations with water chemistry data but without [Li] measurements. The approach relies solely on commonly available geospatial (coordinates, stratigraphic position) and geochemical features, including contents of total dissolved solids (TDS) and cations of Na, K, Mg, and Ca. Validated against about one hundred Li-labeled samples measured after May 2022, the approach achieved a minimum precision and accuracy of 97% and 84%, respectively, for predicting three [Li] cutoff levels (i.e., > 35 mg/L, > 50 mg/L, and > 75 mg/L). It was subsequently applied to predict [Li] levels of formation water from 897 different locations with legacy water chemistry data. The results align spatially with observed trends of Li-rich brines in Alberta Devonian formations and expand resource delineation and estimation capabilities to areas and formations with limited [Li] data availability.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 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".