3D metallogenic prediction based on machine learning: A case study of the Lala copper deposit in Sichuan Province
-
摘要:
在大数据蓬勃发展的时代背景下，矿产资源定量预测作为地质大数据的核心部分，其综合分析挖掘多元信息的基本思路与大数据的理念不谋而合。以四川拉拉铜矿为例，开展基于机器学习的三维矿产资源定量预测。通过建立三维地质模型，提取成矿有利信息，构建研究区定量预测模型；基于"立方块预测模型"找矿方法，采用机器学习随机森林算法，计算出研究区成矿概率分布，以此圈定出5个找矿远景区。结果表明，随机森林具有更高的预测准确度与稳定性，且能够对控矿要素重要性做出定量评价。该研究成功地将机器学习应用于三维矿产定量预测，为今后的矿产资源预测评价做出了积极的探索。
Abstract:Under the background of the vigorous development of big data, the quantitative prediction of mineral resources is the core part of geological big data. The basic idea of comprehensive analysis and mining of multi-information coincides with the concept of big data. With the Lala copper deposit as the study area, the authors carried out 3D mineral resources prediction based on machine learning. In this paper, 3D geological model was established to extract useful information of mineralization and build the quantitative prediction model of the study area. By using the "cube prediction model" prospecting method, the authors adopted the random forest algorithm of machine learning to calculate the probability distribution of mineralization in the study area. In this way, five prospecting prospective areas were delineated. The results show that the random forest has higher prediction accuracy and stability and can make quantitative evaluation on the importance of ore controlling factors. This study has successfully applied machine learning to the 3D mineral resources prediction and made a positive exploration for the prediction and evaluation of mineral resources in the future.
-
Key words:
- mineral prediction /
- 3D modelling /
- machine learning /
- random forest /
- Lala copper deposit
-
-
表 1 三维地质建模数据基础
Table 1. The database of 3D geological modelling
资料名称 比例尺 数量 探测深度/m 地形地质图 1:5000 1 地表 基岩地质图 1:5000 1 地表 矿层柱状对比图 1:5000 2 1000 钻孔柱状图 1:200 147 70~1030 地质勘探剖面 1:2000 21 1000~1200 CSAMT综合解译剖面图 1:1万 12 2000 CSAMT综合解译中段图 1:1万 3 500, 1000, 1500 
下载: 导出CSV
表 2 拉拉铜矿定量预测模型
Table 2. Quantitative prediction model of the Lala copper deposit
矿床类型 控矿要素 要素类型 特征变量 特征值 火山沉积变质型铜(铁)矿 地层 赋矿地层 天生坝组 天生坝组 新桥组 新桥组 落凼组 落凼组 构造 控矿断裂 基底断裂 断裂 断裂破碎带 断裂缓冲区 100m缓冲区 构造发育部位 方位异常度 （0，0.1） 构造等密度 （1.045，1.492） 中心对称度 （0.001，0.210） 构造频数 （0，1.375） 岩体 有利成矿岩体 辉长岩 辉长岩 岩体接触带 岩体缓冲区 缓冲区50m 有利岩体特征 岩体分异度 （0.07，3.04） 地球物理 视电阻率异常 CSAMT异常 低阻异常体 CSAMT异常缓冲 缓冲区50m
下载: 导出CSV
-
[1] 肖克炎, 张晓华, 李景朝, 等.全国重要矿产总量预测方法[J].地学前缘, 2007, 14(5):20-26. doi: 10.3321/j.issn:1005-2321.2007.05.003
[2] 赵鹏大, 李紫金, 胡光道.重点成矿区三维立体矿床统计预测——以安徽月山地区为例[M].武汉:中国地质大学出版社, 1992.
[3] 陈建平, 吕鹏, 吴文, 等.基于三维可视化技术的隐伏矿体预测[J].地学前缘, 2007, 4(5):54-61. doi: 10.3321/j.issn:1005-2321.2007.05.006
[4] 陈建平, 于萍萍, 史蕊, 等.区域隐伏矿体三维定量预测评价方法研究[J].地学前缘, 2014, 21(5):211-220. http://d.old.wanfangdata.com.cn/Periodical/dxqy201405016
[5] Wang G W, Li R X, Emmanuel J M, et al. 3D geological modeling for prediction of subsurface Motargets in the Luanchuan district, China[J]. Ore Geology Reviews, 2015, 71:592-610. doi: 10.1016/j.oregeorev.2015.03.002
[6] Wang G W, Zhang S, Yan C, et al. Mineral potential targeting and resource assessment based on 3D geological modeling in Luanchuan region, China[J]. Computers & Geosciences, 2011, 37(12):1976-1988. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=2ebe97b6bb61befb0348b7d8b43727f0
[7] 肖克炎, 李楠, 孙莉, 等.基于三维信息技术大比例尺三维立体矿产预测方法及途径[J].地质学刊, 2012, 36(3):229-236. doi: 10.3969/j.issn.1674-3636.2012.03.229
[8] Xiao K Y, Li N, Porwal A, et al. GIS-based 3D prospectivity mapping:A case study of Jiama copper-polymetallic deposit in Tibet, China[J]. Ore Geology Reviews, 2015, 71:611-632. doi: 10.1016/j.oregeorev.2015.03.001
[9] 毛先成, 戴塔根, 吴湘滨, 等.危机矿山深边部隐伏矿体立体定量预测研究——以广西大厂锡多金属矿床为例[J].中国地质, 2009, 36(2):424-435. doi: 10.3969/j.issn.1000-3657.2009.02.016
[10] 毛先成, 邹艳红, 陈进, 等.隐伏矿体三维可视化预测[M].长沙:中南大学出版社, 2011.
[11] Mao X C, Chen J, Deng H, et al. 3D Quantitative Predictivity of Concealed Ore Bodies in Fenghuangshan Copper Deposit, Tongling District, China[J]. Acta Geologica Sinica, 2015, 88(2s):454-456. http://cn.bing.com/academic/profile?id=3e90949d883fcf75d723f4ae031552c3&encoded=0&v=paper_preview&mkt=zh-cn
[12] 袁峰, 李晓辉, 张明明, 等.隐伏矿体三维综合信息成矿预测方法[J].地质学报, 2014, 88(4):630-643. http://d.old.wanfangdata.com.cn/Periodical/dizhixb201404015
[13] Li X H, Yuan F, Zhang M M, et al. Three-dimensional mineral prospectivity modeling for targeting of concealed mineralization within the Zhonggu iron orefield, Ningwu Basin, China[J]. Ore Geology Reviews, 2015, 71:633-654. doi: 10.1016/j.oregeorev.2015.06.001
[14] Rodriguez G V, Sanchez C M, Chica O M, et al. Machine learning predictive models for mineral prospectively:An evaluation of neural networks, random forest, regression trees and support vector machines[J]. Ore Geology Reviews, 2015, 71:804-818. doi: 10.1016/j.oregeorev.2015.01.001
[15] Zhang S, Xiao K, Carranza E J M, et al. Maximum entropy and random forest modeling of mineral potential:Analysis of gold prospectivity in the Hezuo-Meiwu district, west Qinling Orogen, China[J]. Natural Resources Research, 2019, 28(3):645-664. doi: 10.1007/s11053-018-9425-0
[16] Zuo R, Xiong Y. Big Data Analytics of Identifying Geochemical Anomalies Supported by Machine Learning Methods[J]. Natural Resources Research, 2017:1-9. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=02dc1df3ade6b785872cbae156006d07
[17] O'Brien J J, Spry P G, Dan N, et al. Using Random Forests to distinguishgahnite compositions as an exploration guide to Broken Hill-type Pb-Zn-Agdeposits in the Broken Hill domain, Australia[J]. Journal of GeochemicalExploration, 2015, 149(149):74-86.
[18] Carranza E J M, Laborte A G. Random forest predictive modeling of mineral prospectivity with small number of prospects and data with missing values inAbra (Philippines)[J]. Computers & Geosciences, 2015, 74:60-70. http://cn.bing.com/academic/profile?id=a275abd6609e1d0e9e43c7757829f5b3&encoded=0&v=paper_preview&mkt=zh-cn
[19] 周家云, 陈家彪, 沈冰, 等.四川拉拉铜矿构造成矿动力学机制[J].大地构造与成矿学, 2008, 32(1):98-104. doi: 10.3969/j.issn.1001-1552.2008.01.013
[20] 孙燕, 李承德.四川拉拉铜矿床成矿机制研究[J].成都地质学院学报, 1990, 4:1-9. http://www.cnki.com.cn/Article/CJFDTotal-CDLG199004000.htm
[21] Zhou J Y, Zheng R C, Zhu Z M, et al. Geochemistry and Sm-Nd Dating of the Gabbro in the LalaCopper Ore District, Sichuan Province, China[J]. Bulletin of Mineralogy Petrology & Geochemistry, 2009, 28(2):111-122. http://en.cnki.com.cn/Article_en/CJFDTotal-KYDH200902002.htm
[22] 申屠保涌.四川会理拉拉厂铜矿床地质地球化学特征及成矿模式[J].沉积与特提斯地质, 1997, (21):115-130. http://www.cnki.com.cn/Article/CJFDTotal-TTSD721.008.htm
[23] 陈根文, 夏斌.四川拉拉铜矿床成因研究[J].矿物岩石地球化学通报, 2001, 20(1):42-44. doi: 10.3969/j.issn.1007-2802.2001.01.009
[24] 朱志敏, 曾令熙, 周家云, 等.四川拉拉铁氧化物铜金矿床(IOCG)形成的矿相学证据[J].高校地质学报, 2009, 15(4):485-495. doi: 10.3969/j.issn.1006-7493.2009.04.007
[25] 张武鹏, 余璨, 李峰, 等.四川拉拉会理红泥坡铜矿地质特征及找矿标志[J].有色金属工程, 2016, 6(2):80-84. doi: 10.3969/j.issn.2095-1744.2016.02.017
[26] Breiman L. Classification and Regression Trees[M]. New York:Routledge, 1984.
[27] Breiman L. Bagging predictors[J]. Machine Learning, 1996, 24:123-140. http://d.old.wanfangdata.com.cn/NSTLQK/NSTL_QKJJ0224054512/
[28] Breiman L. Random forests[J]. Machine Learning, 2001, 45:5-32. doi: 10.1023/A:1010933404324
[29] 向杰, 陈建平, 胡桥, 等.基于矿床成矿系列的三维成矿预测——以安徽铜陵矿集区为例[J].现代地质, 2016, 30(1):230-238. doi: 10.3969/j.issn.1000-8527.2016.01.026
[30] 董庆吉, 肖克炎, 陈建平, 等.西南"三江"成矿带北段区域成矿断裂信息定量化分析[J].地质通报, 2010, 29(10):1479-1485. doi: 10.3969/j.issn.1671-2552.2010.10.010 http://dzhtb.cgs.cn/gbc/ch/reader/view_abstract.aspx?file_no=20101009&flag=1
[31] 向杰, 陈建平, 胡彬, 等.基于三维地质-地球物理模型的三维成矿预测-以安徽铜陵矿集区为例[J].地球科学进展, 2016, 31:603-614. doi: 10.11867/j.issn.1001-8166.2016.06.0603.
-
图(9)
表(2)
计量
- 文章访问数: 1923
- PDF下载数: 24
- 施引文献: 0