A comparative study of fuzzy weights of evidence and random forests for mapping mineral prospectivity for skarn-type Fe deposits in the southwestern Fujian metallogenic belt, China

详细信息    查看全文

• 作者：ZhenJie Zhang ; RenGuang Zuo ; YiHui Xiong
• 关键词：mineral prospectivity mapping ; fuzzy weights of evidence ; random forest ; skarn ; type Fe ; Makeng deposit
• 刊名：Science China Earth Sciences
• 出版年：2016
• 出版时间：March 2016
• 年：2016
• 卷：59
• 期：3
• 页码：556-572
• 全文大小：8,391 KB
• 参考文献：Agterberg F P. 1989. Computer programs for mineral exploration. Science, 245: 76–81CrossRef
  Agterberg F P, Bonham-Carter G F. 1990. Statistical Applications in the Earth Sciences: Energy, Mines and Resources Canada. Geological Survey of Canada
  Agterberg F P, Bonham-Carter G F, Cheng Q M, Wright D F. 1993. Weights of evidence modeling and weighted logistic regression for mineral potential mapping. Comput Geol, 25: 13–32
  Agterberg F P, Bonham-Carter G F, Wright D F. 1990. Statistical pattern integration for mineral exploration. In: Gaál G, Merriam D F, eds. Computer Applications in Resource Estimation: Prediction and Assessment for Metals and Petroleum. Oxford: Pergamon Press. 1–21CrossRef
  An P, Moon W M, Bonham-Carter G F. 1992. On knowledge-based approach of integrating remote sensing, geophysical and geological information. Geoscience and Remote Sensing Symposium, 1992 IGARSS’92 International: IEEE. 34–38
  An P, Moon W M, Rencz A. 1991. Application of fuzzy set theory for integration of geological, geophysical and remote sensing data. Can J Explor Geoph, 27: 1–11
  Bonham-Carter G. 1994. Geographic Information Systems for Geoscientists: Modelling with GIS. New York: Elsevier. 398
  Breiman L. 1996. Bagging predictors. Mach Learn, 24: 123–140
  Breiman L. 2001. Random forests. Mach Learn, 45: 5–32CrossRef
  Breiman L, Friedman J, Stone C J, Olshen R A. 1984. Classification and Regression Trees. Boca Raton: CRC Press
  Carranza E J M. 2004. Weights of evidence modeling of mineral potential: A case study using small number of prospects, Abra, Philippines. Nat Resour Res, 13: 173–187CrossRef
  Carranza E J M, Laborte A G. 2015a. Data-driven predictive mapping of gold prospectivity, Baguio district, Philippines: Application of random forests algorithm. Ore Geol Rev, 71: 777–787CrossRef
  Carranza E J M, Laborte A G. 2015b. Random forest predictive modeling of mineral prospectivity with small number of prospects and data with missing values in Abra (Philippines). Comput Geosci, 74: 60–70CrossRef
  Carranza E J M, Woldai T, Chikambwe E M. 2005. Application of data- driven evidential belief functions to prospectivity mapping for aquamarine- bearing pegmatites, Lundazi district, Zambia. Nat Resour Res, 14: 47–63CrossRef
  Chen S R, Xie J H, Xu C N, Guo W W. 1985. The origin of Makeng iron deposit, Fujian (in Chinese). Geochimica, 4: 350–357
  Chen Y S. 2002. New knowledge of the information cause of ore deposit during the exploitation process of Makeng iron mine (in Chinese with English abstract). Met Mine, 317: 50–52
  Chen Y S. 2010. New understanding of ore-control structure feature of Fujian Makeng Iron Mine (in Chinese with English abstract). Met Mine, 404: 96–99
  Cheng Q M. 2000. GeoData Analysis System (GeoDAS) for mineral exploration: User’s guide and exercise manual. In: Material for the Training Workshop on GeoDAS Held. Toronto: York University
  Cheng Q M. 2007. Mapping singularities with stream sediment geochemical data for prediction of undiscovered mineral deposits in Gejiu, Yunnan province, China. Ore Geol Rev, 32: 314–324CrossRef
  Cheng Q M. 2012. Ideas and methods for mineral resources integrated prediction in covered areas (in Chinese with English abstract). Earth Sci-J China Univ Geosci, 37: 1109–1123
  Cheng Q M, Agterberg F P. 1999. Fuzzy weights of evidence method and its application in mineral potential mapping. Nat Resour Res, 8: 27–35CrossRef
  Cheng Q M, Chen Z J, Khaled A. 2007. Application of fuzzy weights of evidence method in mineral resource assessment for gold in Zhenyuan district, Yunnan province, China (in Chinese with English abstract). Earth Sci-J China Univ Geosci, 32: 175–184
  Chung C F, Agterberg F P. 1980. Regression models for estimating mineral resources from geological map data. J Inter Assoc Math Geol, 12: 473–488CrossRef
  Ford A, Blenkinsop T G. 2008. Combining fractal analysis of mineral deposit clustering with weights of evidence to evaluate patterns of mineralization: application to copper deposits of the Mount Isa Inlier, NW Queensland, Australia. Ore Geol Rev, 33: 435–450CrossRef
  Franca-Rocha W, Bonham-Carter G, Misi A. 2003. GIS modeling for mineral potential mapping of carbonate-hosted Pb-Zn deposits. Braz J Geol, 33: 191–196
  Ge C H, Han F, Zhou T R, Chen D Q. 1981. Geological characteristics of the Makeng iron deposit of marine volcano-sedimentary origin (in Chinese with English abstract). Acta Geol Sin, 3: 47–69
  Han F, Ge C H. 1983. Geological and geochemical features of submarine volcanic hydrothermal-sedimentary mineralization of Makeng iron deposit, Fujian province (in Chinese with English abstract). Bull Inst Miner Depos Chin Acad Geol Sci, 7: 1–118
  Harris D, Pan G C. 1999. Mineral favorability mapping: A comparison of artificial neural networks, logistic regression, and discriminant analysis. Nat Resour Res, 8: 93–109CrossRef
  Harris J R, Grunsky E, Behnia P, Corrigan D. 2015. Data-and Knowledge driven mineral prospectivity maps for Canada’s North. Ore Geol Rev, 71: 788–803CrossRef
  Harris J R, Wilkinson L, Heather K, Fumerton S, Bernier M A, Ayer J, Dahn R. 2001. Application of GIS processing techniques for producing mineral prospectivity maps—A case study: Mesothermal Au in the Swayze Greenstone Belt, Ontario, Canada. Nat Resour Res, 10: 91–124CrossRef
  Jiang Y F. 2009. Analysis of metallogenic geological features in Makeng iron deposit (in Chinese). Mod Min, 8: 89–91
  Lai S H, Chen R Y, Zhang D, Di Y J, Gong Y, Yuan Y, Chen L. 2014. Petrogeochemical features and zircon LA-ICP-MS U-Pb ages of granite in the Pantian iron ore deposit, Fujian province and their relationship with mineralization (in Chinese with English abstract). Acta Petrol Sin, 30: 1780–1792
  Liaw A, Wiener M. 2002. Classification and regression by random forest. R News, 2: 18–22
  Lin D Y. 2011. Research on late Paleozoic-Triassic tectonic evolution and metallogenetic regularities of iron-polymetalic deposits in the southwestern Fujian province. Doctoral Dissertation. Beijing: China University of Geosciences
  Lin Z X. 2008. Discussion on geological features and prospecting direction of Makeng iron deposit (in Chinese). Express Inf Min Ind, 10: 84–86
  Meinert L, Dipple G, Nicolescu S. 2005. World skarn deposits. Econ Geol 100th Anniv Vol. 299–336
  Ripley B D. 2001. The R project in statistical computing. MSOR Connections, 1: 23–25CrossRef
  Rodriguez-Galiano V F, Chica-Olmo M, Chica-Rivas M. 2014. Predictive modelling of gold potential with the integration of multisource information based on random forest: a case study on the Rodalquilar area, Southern Spain. Int J Geogr Inf Sci, 28: 1336–1354CrossRef
  Rodriguez-Galiano V F, Sanchez-Castillo M, Chica-Olmo M, Chica- Rivasd M. 2015. Machine learning predictive models for mineral prospectivity: An evaluation of neural networks, random forest, regression trees and support vector machines. Ore Geol Rev, 71: 804–818CrossRef
  Singer D A, Kouda R. 1996. Application of a feedforward neural network in the search for Kuroko deposits in the Hokuroku district, Japan. Math Geosci, 28: 1017–1023
  Wang H M, Cai G R, Cheng Q M. 2002. Data integration using weights of evidence model: Applications in mapping mineral resource potentials. Int Arch Photogramm. Remote Sens Spat Inf Sci, 34: 48–53
  Wang W B, Ji S X, Xing W C, Wang R H. 1981. A discussion on genesis of Makeng type iron deposit in Southwestern Fujian (in Chinese with English abstract). Bull Nanjing Inst Geol Miner Resour Chin Acad Geol Sci, 2: 1–28
  Wang Z J, Cheng Q M. 2006. GIS-Based (W+/W-) weight of evidence model and its application to gold resources assessment in Abitibi, Canada. J China Univ Geosci, 17: 71–78CrossRef
  Xie X J, Mu X Z, Ren T X. 1997. Geochemical mapping in China. J Geochem Explor, 60: 99–113CrossRef
  Yang Z L, Zhang D Q, Feng C Y, She H Q, Li J W. 2008. SHRIMP zircon U-Pb dating of quartz porphyry from Zhongjia Tin-polymetallic deposit in Longyan area, Fujian province, and its geological significance (in Chinese with English abstract). Miner Deposit, 27: 329–335
  Yuan Y, Feng H B, Zhang D, Di Y J, Wang C M, Ni J H. 2013. Geochronology of Dapai ironpolymetallic deposit in Yongding city, Fujian Province and its geological significance (in Chinese). Acta Mineral Sin, 33: 73–75
  Zhang C S. 2012. Geology and geochemistry of Makeng Fe-Mo deposit, Fujian. Doctoral Dissertation. Beijing: China University of Geosciences
  Zhang C S, Mao J W, Xie G Q, Zhao C S, Yu M, Wang J X, Liu W G. 2012a. Geology and molybdenite Re-Os ages of Makeng skarn-type Fe-Mo deposit in Fujian province (in Chinese with English abstract). J Jilin Univ-Earth Sci Ed, 42: 224–236
  Zhang C S, Su H M, Yu M, Hu C G. 2012b. Zircon U-Pb age and Nd-Sr-Pb isotopic characteristics of Dayang-Juzhou granite in Longyan, Fujian province and its geological significance (in Chinese with English abstract). Acta Petrol Sin, 28: 225–242
  Zhang D, Wu G G, Di Y J, Wang C M, Yao J M, Zhang Y Y, Lv L Y, Yuan Y, Shi J J. 2012c. Geochronology of diagenesis and mineralization of the Luoyang iron deposit in Zhangping city, Fujian province and its geological significance (in Chinese with English abstract). Earth Sci-J China Univ Geosci, 37: 1217–1231
  Zhang D J, Agterberg F P, Cheng Q M, Zuo R G. 2014. A comparison of modified fuzzy weights of evidence, fuzzy weights of evidence, and logistic regression for mapping mineral prospectivity. Math Geosci, 46: 869–885CrossRef
  Zhang Z J, Zuo R G. 2013. Iron isotope systematics of magnetite: Implications for the genesis of Makeng iron deposit, southern China. Acta Geol Sin-Engl Ed, 87: 840–843
  Zhang Z J, Zuo R G. 2014. Sr-Nd-Pb isotope systematics of magnetite: Implications for the genesis of Makeng Fe deposit, southern China. Ore Geol Rev, 57: 53–60CrossRef
  Zhang Z J, Zuo R G. 2015. Tectonic evolution of southwestern Fujian Province and spatial-temporal distribution regularity of mineral deposits (in Chinese with English abstract). Acta Petrol Sin, 31: 217–229
  Zhang Z J, Zuo R G, Cheng Q M. 2015a. Geological features and formation processes of the Makeng Fe deposit, China. Resour Geol, 65: 266–284CrossRef
  Zhang Z J, Zuo R G, Cheng Q M. 2015b. The mineralization age of the Makeng Fe deposit, South China: Implications from U-Pb and Sm-Nd geochronology. Int J Earth Sci, 104: 663–682CrossRef
  Zhao Y M, Tan H J, Xu Z N, Yuan R G, Bi C S, Zheng R L, Li D X, Sun J H. 1983. The calcic-skarn iron ore deposit of Makeng type in southwestern Fujian (in Chinese). Bull Inst Miner Depos Chin Acad Geol Sci, 7: 1–141
  Zhu L X, Zhu J Z, Xue J Y, Xu Q Q, Liu J X. 1982. Discussion on the mineralization of Makeng iron deposit, Fujian (in Chinese). Shanghai Geol, 2: 21
  Ziaii M, Carranza E J M, Ziaei M. 2011. Application of geochemical zonality coefficients in mineral prospectivity mapping. Comput Geosci, 37: 1935–1945CrossRef
  Zuo R G, Carranza E J M. 2011. Support vector machine: A tool for mapping mineral prospectivity. Comput Geosci, 37: 1967–1975CrossRef
  Zuo R G, Zhang Z J, Zhang D J, Carranza E J M, Wang H C. 2015. Evaluation of uncertainty in mineral prospectivity mapping due to missing evidence: A case study with skarn-type Fe deposits in Southwestern Fujian Province, China. Ore Geol Rev, 71: 502–515CrossRef
  
• 作者单位：ZhenJie Zhang (1)
  RenGuang Zuo (2)
  YiHui Xiong (2)
  
  1. School of Earth Sciences and Resources, China University of Geosciences, Beijing, 100083, China
  2. State Key Laboratory of Geological Processes and Mineral Resources, China University of Geosciences, Wuhan, 430074, China
  
• 刊物主题：Earth Sciences, general;
• 出版者：Springer Berlin Heidelberg
• ISSN：1869-1897

文摘

Recent studies have pointed out that the widespread iron deposits in southwestern Fujian metallogenic belt (SFMB) (China) are skarn-type deposits associated with the Yanshanian granites. There is still excellent potential for mineral exploration because large areas in this belt are covered by forest. A new predictive model for mapping skarn-type Fe deposit prospectivity in this belt was developed and focused on in this study, using five criteria as evidence: (1) the contact zones of Yanshanian granites (GRANITE); (2) the contact zones within the late Paleozoic marine sedimentary rocks and the carbonate formations (FORMATION); (3) the NE-NNE-trending faults (FAULT); (4) the zones of skarn alterations (SKARN); and (5) the aeromagnetic anomaly (AEROMAGNETIC). The fuzzy weights of evidence (FWofE) method, developed from the classical weights of evidence (WofE) and based on fuzzy sets and fuzzy probabilities, could provide smaller variances and more accurate posterior probabilities and could effectively minimize the uncertainty caused by omitted or wrongly assigned data and be more flexible than the WofE. It is an efficient and widely used method for mineral potential mapping. Random forests (RF) is a new and useful method for data-driven predictive mapping of mineral prospectivity method, and needs further scrutiny. Both prospectivity results respectively using the FWofE and RF methods reveal that the prediction model for the skarn-type Fe deposits in the SFMB is successful and efficient. Both methods suggested that the GRANITE and FORMATION are the most valuable evidence maps, followed by SKARN, AEROMAGNETIC, and FAULT. This is coincident with the skarn-type Fe deposit mineral model in the SFMB. The unstable performance experienced when FORMATION was omitted might indicate that the highest uncertainty and risk in follow-up exploration is related to the sequences. In addition, the performance of the RF method for the skarn-type Fe deposits prospectivity in the SFMB is better than the FWofE; therefore, it could be used to guide further exploration of skarn-type Fe prospects in the SFMB.