基于地质空间数据挖掘的区域成矿预测方法

doi:10.11867/j.issn.1001-8166.2011.06.0615

以多源地质空间数据库和空间数据挖掘技术为基础，顾及地质数据的空间特征和不确定性，提出一种基于地质空间数据挖掘的区域成矿预测方法，主要包括：连续型地质空间数据离散化、成矿空间关系提取及属性化、成矿关联规则提取及质量评价、成矿关联规则综合评价与潜力制图。最后，以青海省东昆仑地区铁矿资源潜力预测为例进行实验，并将地质空间数据挖掘预测结果与传统的证据权模型预测结果进行对比。实验对比结果表明，基于地质空间数据挖掘的预测结果较传统的证据权模型方法预测精度更高，该方法用于区域成矿预测效果良好。

关键词: 地质空间数据挖掘, 区域成矿预测, 云模型, Apriori算法, 层次分析

Spatial data mining (SDM) refers to extracting and “mining” the hidden, implicit, valid, novel and interesting spatial or non-spatial patterns or rules from a large amount of, incomplete, noisy, fuzzy, random, and practical spatial databases. At present, SDM mainly concentrates on the efficiency of mining algorithm itself. Another important issue-application in SDMhas not been paid much attention to. Geological data are typical spatial data, which include geological, geophysical, geochemical, and remote sensing data. Regional metallogenic prediction and quantitative resource assessment have been recognized as important when integrating multisource geological spatial data in recent years. The statistical and mathematical approaches that have developed recently for multi-resources geological spatial data integration include weights-of -evidence modelling, and the logistic regression modeling. The fuzzy logic model, artificial neural networks model and the fractal method have been applied in the prediction and assessment of mineral resources potential. These methods promote the effectiveness of mineral resource prospecting. However, under the shortage of mineral resources and the leap cost of prospecting and exploring, how to make full use of the existing multi-sources geo-spatial data to find deep mining information through massive uncertain multi-source geology spatial database and establish a rapid, efficient, intelligent method of mineral prediction to reduce the cost of mineral exploration and improve the efficiency and accuracy of mineral prediction is particularly important and urgent. These traditional statistical mathematical approaches and GIS spatial analysis technology is lack of intelligence and reasoning mechanism. In this paper, a geoglogy spatial data mining method for regional metallogenic prediction is proposed. The geology spatial data mining method for regional metallogenic prediction mainly includes continuous geological spatial data discretization, spatial relationship abstracting and attribute transforming, mining metallogenic association rules and quality assessment, comprehensive evaluation of association rules and mineral potential mapping. Firstly, the best ore-controlling variable and threshold were determined using proximity analysis of the weights-of-evidence model. On the basis of a correlation analysis among evidence variables, the authors selected vector ore-controlling data of stratum, unconformity, fault, regional geochemical data, remote-sensing mineralization information, bouguer gravity data, aeromagnetic data, and mineral occurrence for this experiment. Secondly, the cloud model was used to execute the uncertainty translation between continuous geology data and discrete geology data. Meanwhile, on the basis of apriori algorithm, the metallogenic association rules were abstracted and six uncertainty indexesconfidence, support, lift, coverage, leverage and interesting-were adopted to assess the quality of metallogenic association rules. Finally, the experiment of regional metallogenic prediction for iron deposits was performed in Eastern Kunlun, Qinghai province, China, using geoglogy spatial data mining method and weights-of-evidence model, respectively. All the data sets were derived from a multi-source geology spatial database (MGSDB) established by the Institute of Geo-Spatial Information Science and Technology, University of Electronic Science and Technology of China in 2009, which contains geological, geophysical, geochemical and remote sensing data. The algorithm is implemented with C# programming language. The study areas were divided into three parts to assist the interpreting of the potential distribution of iron deposits. We defined the three target zones as high potential areas, moderate potential areas and low potential areas, respectively. Using the weights-of-evidence model, low potential areas contain 32% of the total gold deposits, covering 75% of the total area; the high potential areas contain 48% of the total gold deposits, covering 10% of the total area; and the moderate potential areas contain 20% of the gold deposits, covering 15% of the total area; about 68% of known deposits are located in the moderate and high potential areas. Using the geology spatial data mining method in this paper, Low potential areas contain 8% of the total gold deposits, covering 75% of the total area; the high potential areas contain 72% of the total gold deposits, covering 10% of the total area; and the moderate potential areas contain 20% of the gold deposits, covering 15% of the total area. About 92% of known deposits are located in the moderate and high potential areas. The results indicate that the prediction accuracy of geology spatial data mining was obvious higher than that of weights-of-evidence model’s, the method is suitable for mineral resources potential assessment and its effectiveness is good.

Key words: Geology spatial data mining, Regional metallogenic prediction, Cloud model, Apriori algorithm, Analytic hierarchy process.

中图分类号:

TD851

[1]Zhao Pengda. “Three-Component” quantitative resource prediction and assessments: Theory and practice of digital mineral prospecting[J].Earth Science—Journal of China University of Geosciences,2002, 27(5): 482-489.[赵鹏大．“三联式”资源定量预测与评价——数字找矿理论与实践探讨[J].地球科学——中国地质大学学报，2002，27（5）：482-489.]
[2]Zhao Pengda, Chen Jianping, Zhang Shouting. The new development of “Three Components” quantitative mineral prediction[J].Earth Science Frontiers, 2003,10(2): 455-462.[赵鹏大，陈建平，张寿庭．“三联式”成矿预测新进展[J]．地学前缘，2003，10（2）：455-462]
[3]Wang Shicheng, Chen Yongliang, Xia Lixian. Comprehensive Information and Method of Mineral Prediction[M]. Beijing: Science Press,2000.[王世称,陈永良,夏立显.综合信息矿产预测理论与方法[M]．北京：科学出版社，2000.]
[4]Cheng Qiuming. Singularity-generalized self-similarityfractal spectrum (3S) models[J].Earth Science—Journal of China University of Geosciences,2006, 31(3):337-348.[成秋明．非线性成矿预测理论：多重分形奇异性—广义自相似性—分形谱系模型与方法[J]．地球科学——中国地质大学学报，2006，31（3）：337-348．]
[5]Singer D A. Basic concepts in three part quantitative assessments of undiscovered mineral resources[J]. Nonrenewable Resources,1993, 2(2): 69-81.[6]Singer D A. Some suggested future directions of quantitative resources assessment[J].Journal of China University of Geosciences,2001, 12(1): 40-44.[7]Agterberg F P, BonhamCarter G F, Wright D F. Statistical pattern integration for mineral exploration[M]∥Gaál G, Merriam D F, eds. Computer Applications in Resource Estimation Prediction and Assessment for Metals and Petroleum.Oxford: Pergamon Press, 1990:1-21.
[8]Agterberg F P. Combining indicator patterns in weights of evidence modeling for resource evaluation[J]. Nonrenewable Resources1992, 1(1):39-50.
[9]Agterberg F P, Cheng Q. Conditional independence test of weights-of-evidence modeling[J].Natural Resources Research,2002, 11(4) :249-255.
[10]Carranza E J M. Weights of evidence modeling of mineral potential: A case study using small number of prospects, Abra, Philippines
[J].Natural Resources Research,2004, 13 (3): 173-187.
[11]Porwal A, González Alvarez I, Markwitz V,et al. Weights of evidence and logistic regression modeling of magmatic nickel sulfide prospectivity in the Yilgarn Craton, Western Australia[J].Ore Geology Reviews,2010, 38 (3):184-196.
[12]He Binbin, Chen Cuihua, Liu Yue. Gold resources potential assessment in eastern Kunlun Mountains of China combining weights-of-evidence model with GIS spatial analysis technique[J].Chinese Geographical Science,2010, 20(5):461-470.
[13]Carranza E J M, Hale M. Logistic regression for geologically constrained mapping of gold potential, Baguio district, Philippines[J].Exploration and Mining Geology,2001, 10(3): 165-175. 
[14]Luo X, Dimitrakopoulos R. Datadriven fuzzy analysis in quantitative mineral resource assessment[J]. Computers & Geosciences,2003, 29(1): 3-13.[15]Rigol-Sanchez J P, Chica-Olmo M, Abarca-Hernandez F. Artificial neural networks as a tool for mineral potential mapping with GIS[J].International Journal of Remote Sensing,2003, 24(5): 1 151-1 156. 
[16]Gumiel P, Sanderson D J, Arias M, et al. Analysis of the fractal clustering of ore deposits in the Spanish Iberian Pyrite Belt[J].Ore Geology Reviews,2010, 38(4): 307-318.
[17]Di Kaichang.Spatial Data Mining and Knowledge Discovery[M]. Wuhan: Wuhan University Press,2001.[邸凯昌．空间数据发掘与知识发现[M]．武汉：武汉大学出版社，2001.]
[18]Miller H, Han J. Geographic Data Mining and Knowledge Discovery[M]. London: Taylor & Francis, 2001.
[19]Li Deren, Wang Shuliang, Li Deyi, et al. Theories and technologies of spatial data mining and knowledge discovery[J].Geomatics and Information Science of Wuhan University,2002, 27(3): 221-233.[李德仁，王树良，李德毅,等．论空间数据挖掘与知识发现的理论与方法[J]．武汉大学学报:信息科学版，2002，27（3）：221-233.]
[20]Li Deren, Wang Shuliang, Li Deyi. Theory and Application of Spatial Data Mining[M]. Beijing: Science Press,2006.[李德仁，王树良，李德毅．空间数据挖掘理论与应用[M]．北京：科学出版社，2006．]
[21]He Binbin. Uncertainty Theory and Application of Spatial Data Mining[M]. Xuzhou: China University of Mining,2007.[何彬彬．空间数据挖掘不确定性理论及应用[M]．徐州：中国矿业大学出版社，2007．]
[22]Li Deyi, Du Yi. Uncertainty Artificial Intelligence[M]. Beijing: National Defence Industry Press,2005.[李德毅，杜鹢．不确定性人工智能[M]．北京：国防工业出版社，2005.]
[23]Di Kaichang, Li Deyi, Li Deren. Cloud theory and its applications in spatial data ming and knowledge disvoery[J].Journal of Image and Graphics,1999,4A(11):930-935.[邸凯昌，李德毅，李德仁．云理论及其在空间数据发掘和知识发现中的应用[J]．中国图象图形学报，1999，4A(11)：930-935．]
[24]Li Xingsheng, Li Deyi. A new method based on cloud model for discretization of continuous attributes in rough sets[J].PATTERN Recognition and Artificial Intelligence,2003,16(1):33-38.[李兴生，李德毅．一种基于云模型的决策表连续属性离散化方法[J]．模式识别与人工智能，2003，16(1)：33-38.][25]Agrawal R, Imielinski T, Swami A. Mining association rules between sets of items in large database[C]∥Proceedings of 1993’ACM-SIGMOD International Conference of Management of Data, 1993: 207-216.
[26]Agrawal R,Srikant R. Fast algorithms for mining association rules[C]∥Proceedings of the 20th International Conference on Very Large Data Bases, 1994:487-499.
[27]He Binbin, Chen Cuihua, Fang Tao, et al. Uncertainty processing and measurement of spatial data association rules mining[J].Geography and Geo-information Science,2006,22(6):5-8.[何彬彬，陈翠华，方涛,等.空间数据关联规则挖掘的不确定性处理及度量[J]．地理与地理信息科学，2006，22(6)：5-8．]
[28]Gray B, Orlowska M E. CCAIIA: Clustering categorical attributes into interesting association rules[C]∥Proceedings of the Second Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD98), Lecture Notes in ArtificialIntelligence 1394,1998: 132-143.
[29]Saaty Thomas L, Vargas Luis G. Uncertainty and rank order in the analytic hierarchy process[J]. European Journal of Operational Research,1987, 32(1):107-117.
[30]Kemp L D, BonhamCarter G F, Raines G L. Arc-WofE: ArcView extension for weights of evidence mapping[EB/OL]. http:∥gis.nrcan.gc.ca/software/arcview/ wofe, 1999.
[31]Bian Qiantao, Zhao Dasheng, Ye Zhengren, et al. A preliminary study of the Kunlun-Qiliian-Qinling suture system[J].Acta Geoscientia Sinica,2002, 23(6):501-508.[边千韬，赵大升，叶正仁,等.初论昆祁秦缝合系[J]．地球学报，2002，23(6)：501-508．]
[32]Qian Zhuangzhi, Hu Zhengguo, Liu Jiqing. Active continental margin and regional metallogenesis of the palaeo-tethys in the east kunlun mountains
[J].Geotectonica and Metallogenia,2000,24(2):134-139.[钱壮志，胡正国，刘继庆．古特提斯东昆仑活动陆缘及其区域成矿[J]．大地构造与成矿学，2000，24(2)：134-139．]

[1]	徐春亮,陈彦,贾明权,刘增灿,卢海平,童玲. 典型地物后向散射特性的测量与分析[J]. 地球科学进展, 2009, 24(7): 810-816.

阅读次数

全文

摘要

Geology Spatial Data Mining Method for Regional Metallogenic Prediction