Convolutional neural network and transfer learning based mineral prospectivity modeling for geochemical exploration of Au mineralization within the Guandian–Zhangbaling area, Anhui Province, China
作者： He Li , Xiaohui Li , Feng Yuan , Simon M. Jowitt , Mingming Zhang
DOI: 10.1016/J.APGEOCHEM.2020.104747
关键词: Geology 、 Prospectivity mapping 、 Earth science 、 Convolutional neural network 、 Mineral exploration 、 Transfer of learning 、 Multivariate statistics 、 Mineralization (geology)
摘要: Abstract The Zhangbaling–Guandian area is located in the eastern part of Anhui Province, China, and contains several small Au-Cu deposits occurrences that highlight prospectivity this for future mineral exploration. Recent research has determined machine learning can identify potentially mineralization-related geochemical anomalies represent targets However, majority previous focused on identifying based individual sample points but not incorporated associated data such as spatial characteristics shape, overlap, zonation within multivariate haloes. Here, we present a convolutional neural network algorithm approach to areas prospective Au exploration multielement maps. This considers various employs transfer method reduce influence limited number known area, accelerating convergence rates improving accuracy model. training results indicate each model >99 cross-entropy loss values are
sci-hub.st 参考文章(40)
Qiuming Cheng, Yaguang Xu, Eric Grunsky, Integrated Spatial and Spectrum Method for Geochemical Anomaly Separation Natural resources research. ,vol. 9, pp. 43- 52 ,(2000) , 10.1023/A:1010109829861
Jiangnan Zhao, Shouyu Chen, Renguang Zuo, Identifying geochemical anomalies associated with Au–Cu mineralization using multifractal and artificial neural network models in the Ningqiang district, Shaanxi, China Journal of Geochemical Exploration. ,vol. 164, pp. 54- 64 ,(2016) , 10.1016/J.GEXPLO.2015.06.018
Pierre Sermanet, Yann LeCun, David Eigen, Rob Fergus, Michael Mathieu, Xiang Zhang, OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks arXiv: Computer Vision and Pattern Recognition. ,(2013)
Qiuming Cheng, Spatial and scaling modelling for geochemical anomaly separation Journal of Geochemical Exploration. ,vol. 65, pp. 175- 194 ,(1999) , 10.1016/S0375-6742(99)00028-X
Renguang Zuo, Qinglin Xia, Daojun Zhang, A comparison study of the C–A and S–A models with singularity analysis to identify geochemical anomalies in covered areas Applied Geochemistry. ,vol. 33, pp. 165- 172 ,(2013) , 10.1016/J.APGEOCHEM.2013.02.009
Qiuming Cheng, Mapping singularities with stream sediment geochemical data for prediction of undiscovered mineral deposits in Gejiu, Yunnan Province, China Ore Geology Reviews. ,vol. 32, pp. 314- 324 ,(2007) , 10.1016/J.OREGEOREV.2006.10.002
Feng Yuan, Xiaohui Li, Simon M. Jowitt, Mingming Zhang, Cai Jia, Xiaoyu Bai, Taofa Zhou, Anomaly identification in soil geochemistry using multifractal interpolation: A case study using the distribution of Cu and Au in soils from the Tongling mining district, Yangtze metallogenic belt, Anhui province, China Journal of Geochemical Exploration. ,vol. 116, pp. 28- 39 ,(2012) , 10.1016/J.GEXPLO.2012.03.003
Richard J. Goldfarb, David L. Leach, William J. Pickthorn, Colin J. Paterson, Origin of lode-gold deposits of the Juneau gold belt, southeastern Alaska Geology. ,vol. 16, pp. 440- 443 ,(1988) , 10.1130/0091-7613(1988)016<0440:OOLGDO>2.3.CO;2
Mansour Ziaii, Faramarz Doulati Ardejani, Mahdi Ziaei, Ali A. Soleymani, Neuro-fuzzy modeling based genetic algorithms for identification of geochemical anomalies in mining geochemistry Applied Geochemistry. ,vol. 27, pp. 663- 676 ,(2012) , 10.1016/J.APGEOCHEM.2011.12.020
Richard J. Goldfarb, M. Santosh, The dilemma of the Jiaodong gold deposits: Are they unique? Geoscience frontiers. ,vol. 5, pp. 139- 153 ,(2014) , 10.1016/J.GSF.2013.11.001