3D Mineral Prospectivity Mapping of Zaozigou Gold Deposit, West Qinling, China: Deep Learning-Based Mineral Prediction

Zhengbo Yu, Bingli Liu, Miao Xie, Yixiao Wu, Yunhui Kong, Cheng Li, Guodong Chen, Yaxin Gao et al.

Minerals 2022 article cited by 24

Source Open-access PDF More in Science & Research

importance 4/10 partially solved Geochemistry and Geologic Mapping mining exploration stage: research

Problem

Quantitative prediction of gold mineralization at large depth in the Zaozigou gold deposit, west Qinling, China, to guide future exploration.

Why it matters

Delineating buried gold targets determines where costly exploration is focused next.

What the AI did

The STOAD model, built on knowledge distillation combined with a Deep Auto-encoder, performed 3D mineral prospectivity mapping using five geological and geochemical indicators.

Results

AUC 0.97; three main mineral exploration targets delineated

Impact

Model identified three exploration targets for further investigation at the deposit.

Record

Venue	Minerals
Published	2022
Work type	article
Authors	Zhengbo Yu, Bingli Liu, Miao Xie, Yixiao Wu, Yunhui Kong, Cheng Li, Guodong Chen, Yaxin Gao et al.
Citations	24 (OpenAlex, at import time)
References	48
Model or method	STOAD (Deep Auto-encoder, knowledge distillation)
Organization	not stated in source
Primary source	https://doi.org/10.3390/min12111382
Open access	gold
Keywords	mineral prospectivity, deep learning, STOAD, knowledge distillation, gold deposit, 3D mapping

Importance rating

4 / 10

real but narrower advance

Improves exploration targeting at a single gold deposit; useful for mining but narrow geographic and industry scope.

Basis: inferred. Judged from the source text, which gives no explicit scale. Stated scale: not stated in source. Method and limits.

More in Science & Research

#	Paper	Year	Citations	Importance
1	Neural‐Symbolic Machine Learning for Retrosynthesis and Reaction Prediction Marwin Segler, Mark P. Waller	2017	549	7
2	Learning interpretable network dynamics via universal neural symbolic regression Jiao Hu, Jiaxu Cui, Bo Xiong Yang	2025	13	7
3	Data-driven Chemical Reaction Prediction and Retrosynthesis Vishnu H Nair, Philippe Schwaller, Teodoro Laino	2019	32	7
4	Incorporating the image formation process into deep learning improves network performance Yue Li, Yijun P. Su, Min Yi Guo, Xiaofei Han, Jiamin Liu, Harshad D. V...	2022	123	6
5	Generative and reinforcement learning approaches for the automated de novo design of bioactive compounds Maria V. Korshunova, Niles Huang, Stephen J. Capuzzi, Dmytro S. Radche...	2022	101	6