Machine Learning Methods Application in Gold Mineralization Prediction Based on Gold Unit Data

被引：0
|
作者：
Zhang Y. [1 ]
Li M. [1 ]
Han S. [1 ]
Ren Q. [1 ]
Zhu Y. [2 ,3 ]
机构：
[1] State Key Laboratory of Hydraulic Engineering Simulation and Safety, Tianjin University, Tianjin
[2] Development Research Center of China Geological Survey, Beijing
[3] Key Laboratory of Geological Information Technology, Ministry of Natural Resources, Beijing
来源：
Li, Mingchao (lmc@tju.edu.cn) | 1600年 / Science Press卷 / 44期
关键词：
Classification boundary; Gold mineralization prediction; Precision; Random forest; Recall; Resample;
D O I：
10.16539/j.ddgzyckx.2020.02.002
中图分类号：
学科分类号：
摘要：
It is significant to integrate geochemical and geological survey to search deep gold orebody in modern gold mineralization prospecting. However, geological survey is laborious and expensive. Therefore, it is beneficial to study the results of the previous geological survey and find the regular pattern in the massive and complex gold deposit data. In this research, Logistic regression, Random forest and Decision tree are applied to train the model using raw data and resampling data. Recall, precision and accuracy are also used to evaluate model performance. The confusion matrix is selected to visualize the performance of different models. After comparison, it is found that the gold mineralization data cannot be identified because of the huge imbalance between the two groups of data. The test data are going to be predicted into the group with huge data. Random Forest has a good performance on the resampling data, recall and accuracy are 90.63% and 70.78%, respectively. The influence of the different classification boundaries is also discussed. According to the different requirements, the values of the different classification boundaries can be chosen. Evaluating with different measures may improve the adequacy of the model for gold mineralization prediction and improve the efficiency of the gold survey. © 2020, Science Press. All right reserved.
引用
收藏
页码：183 / 191
页数：8
相关论文
共 8 条
  • [1] Geranian H., Tabatabaei S.H., Asadi H.H., Carranza E.J.M., Application of discriminant analysis and support vector machine in mapping gold potential areas for further drilling in the Sari-Gunay gold deposit, NW Iran, Natural Resources Research, 25, 2, pp. 145-159, (2015)
  • [2] Goldie M., Self-potentials associated with the Yanacocha high-sulfidation gold deposit in Peru, Geophysics, 67, 3, pp. 684-689, (2002)
  • [3] Goldie M., A comparison between conventional and distributed acquisition induced polarization surveys for gold exploration in Nevada, The Leading Edge, 26, 2, pp. 180-183, (2007)
  • [4] Hariharan S., Tirodkar S., Porwal A., Bhattacharya A., Joly A., Random forest-based prospectivity modelling of greenfield terrains using sparse deposit data: An example from the Tanami region, Western Australia, Natural Resources Research, 26, 4, pp. 489-507, (2017)
  • [5] Hoschke T., Sexton M., Geophysical exploration for epithermal gold deposits at Pajingo, North Queensland, Australia, Exploration Geophysics, 36, 4, pp. 401-406, (2005)
  • [6] Meyers J.B., Cantwell N., Nguyen P., Donaldson M., Sub-audio magnetic survey experiments for high-resolution, subsurface mapping of regolith and mineralisation over the Songvang Gold Mine near Agnew, Western Australia, Exploration Geophysics, 36, 2, pp. 125-132, (2005)
  • [7] Wallace Y., 3D Modelling of banded iron formation incorporating demagnetization - A case study at the Musselwhite Mine, Ontario, Canada, Exploration Geophysics, 38, 4, pp. 254-259, (2008)
  • [8] Zuo R., Machine learning of mineralization-related geochemical anomalies: A review of potential methods, Natural Resources Research, 26, 4, pp. 457-464, (2017)
1