期刊
MINERALS
卷 12, 期 11, 页码 -出版社
MDPI
DOI: 10.3390/min12111382
关键词
3D mineral prospectivity mapping; geological and geochemical quantitative prediction model at depth; Deep auto-encoder network; Student Teacher Ore-induced Anomaly Detection; Zaozigou gold deposit
资金
- National Key Research and Development Program of China [2017YFC0601505]
- National Natural Science Foundation of China [41602334, 42072322]
- Key Laboratory of Geochemical Exploration, Ministry of Natural Resources [AS2019P02-01]
- Sichuan Science and Technology Program [2022NSFSC0510]
- Opening Fund of the Geomathematics Key Laboratory of Sichuan Province [scsxdz2020yb06, scsxdz2021zd04]
This paper focuses on the scientific problem of quantitative mineralization prediction at large depth in the Zaozigou gold deposit, west Qinling, China. Machine learning and Deep learning algorithms are employed for 3D Mineral Prospectivity Mapping (MPM) with a proposed STOAD model, which shows good performance in mineral resources prediction.
This paper focuses on the scientific problem of quantitative mineralization prediction at large depth in the Zaozigou gold deposit, west Qinling, China. Five geological and geochemical indicators are used to establish geological and geochemical quantitative prediction model. Machine learning and Deep learning algorithms are employed for 3D Mineral Prospectivity Mapping (MPM). Especially, the Student Teacher Ore-induced Anomaly Detection (STOAD) model is proposed based on the knowledge distillation (KD) idea combined with Deep Auto-encoder (DAE) network model. Compared to DAE, STOAD uses three outputs for anomaly detection and can make full use of information from multiple levels of data for greater overall robustness. The results show that the quantitative mineral resources prediction by applying the STOAD model has a good performance, where the value of Area Under Curve (AUC) is 0.97. Finally, three main mineral exploration targets are delineated for further investigation.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据