The abstract is read at the publisher; the summary is JClub's.
In 155 surface-soil samples from an arid, high-altitude mining area in Wuqia County, Xinjiang, China, Cd–Pb–Zn co-enrichment localized near waste-rock and processing facilities.
- Why it matters: Mining inputs are hard to separate from heterogeneous geology in arid mining regions, limiting reliable, source-oriented environmental assessment.
- What they did: A staged workflow used a self-organizing map plus APCS-MLR, LightGBM, and SHAP to resolve multielement patterns and estimate potential-source contributions, with Huber regression on 105 robust samples.
- The result: Huber regression identified F1 and F4 as mean contributors of 29.7% and 27.5%, respectively, and LightGBM OOF evaluation showed F1 was most stable (pooled OOF R² = 0.36) with decreasing contribution away from the mining area.
The findingWhy it mattersWhat they didThe result
AI summary of the abstract · may contain errors · not medical advice · read the paper.