3D Mineral Prospectivity Mapping of Zaozigou Gold Deposit, West Qinling, China: Deep Learning-Based Mineral Prediction
نویسندگان
چکیده
This paper focuses on the scientific problem of quantitative mineralization prediction at large depth in Zaozigou gold deposit, west Qinling, China. Five geological and geochemical indicators are used to establish model. Machine learning Deep algorithms employed for 3D Mineral Prospectivity Mapping (MPM). Especially, Student Teacher Ore-induced Anomaly Detection (STOAD) model is proposed based knowledge distillation (KD) idea combined with Auto-encoder (DAE) network Compared DAE, STOAD uses three outputs anomaly detection can make full use information from multiple levels data greater overall robustness. The results show that mineral resources by applying has a good performance, where value Area Under Curve (AUC) 0.97. Finally, main exploration targets delineated further investigation.
منابع مشابه
Fuzzification of continuous-value spatial evidence for mineral prospectivity mapping
Complexities of geological processes portrayed as certain feature in a map (e.g., faults) are natural sources of uncertainties in decision-making for exploration of mineral deposits. Besides natural sources of uncertainties, knowledge-driven (e.g., fuzzy logic) mineral prospectivity mapping (MPM) is also plagued and incurs further uncertainty in subjective judgment of analyst when there is no r...
متن کاملMineral Prospectivity Mapping Method Integrating Multi-Sources Geology Spatial Data Sets and Case-Based Reasoning
Extracting and synthesizing information from existing and massive amounts of geology spatial data sets is of great scientific significance and has considerable value in its applications. To make mineral exploration less expensive, more efficient, and more accurate, it is important to move beyond traditional concepts and establish a rapid, efficient, and intelligent method of predicting the exis...
متن کاملA GIS-based weights-of-evidence model for mineral potential mapping of hydrothermal gold deposits in Torbat-e-Heydarieh area
The method of weights of evidence is one of the most important data driven methods for mineral potential mapping in GIS. In this method, considering the characteristics of known mineralized locations, we can prospect new mineralized areas. In this research work, the method of weights of evidence has been used for hydrothermal gold potential mapping in Torbat-e-Heydarieh area, east of Iran. As a...
متن کاملA clustering approach for mineral potential mapping: A deposit-scale porphyry copper exploration targeting
This work describes a knowledge-guided clustering approach for mineral potential mapping (MPM), by which the optimum number of clusters is derived form a knowledge-driven methodology through a concentration-area (C-A) multifractal analysis. To implement the proposed approach, a case study at the North Narbaghi region in the Saveh, Markazi province of Iran, was investigated to discover porphyry ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Minerals
سال: 2022
ISSN: ['2075-163X']
DOI: https://doi.org/10.3390/min12111382