Mineral Favorability Mapping: A Comparison of Artificial Neural Networks, Logistic Regression, and Discriminant Analysis
Tóm tắt
A Probabilistic Neural Network (PNN) was trained to classify mineralized and nonmineralized cells using eight geological, geochemical, and geophysical variables. When applied to a second (validation) set of well-explored cells that had been excluded from the training set, the trained PNN generalized well, giving true positive percentages of 86.7 and 93.8 for the mineralized and nonmineralized cells, respectively. All artifical neural networks and statistical models were analyzed and compared by the percentages of mineralized cells and barren cells that would be retained and rejected correctly respectively, for specified cutoff probabilities for mineralization. For example, a cutoff probability for mineralization of 0.5 applied to the PNN probabilities would have retained correctly 87.66% of the mineralized cells and correctly rejected 93.25% of the barren cells of the validation set. Nonparametric discriminant analysis, based upon the Epanechnikov Kernel performed better than logistic regression or parametric discriminant analysis. Moreover, it generalized well to the validation set of well-explored cells, particularly to those cells that were mineralized. However, PNN performed better overall than nonparametric discriminant analysis in that it achieved higher percentages of correct retention and correct rejection of mineralized and barren cells, respectively. Although the generalized regression neural network (GRNN) is not designed for a binary—presence or absence of mineralization— dependent variable, it also performed well in mapping favorability by an index valued on the interval [0, 1]. However, PNN outperformed GRNN in correctly retaining mineralized cells and rejecting barren cells of the validation set.
Tài liệu tham khảo
citation_journal_title=Computers & Geosciences; citation_title=LOGDIA-FORTRAN 77 program for logistic regression with diagnostics; citation_author=F. P. Agterberg; citation_volume=15; citation_issue=4; citation_publication_date=1989; citation_pages=599-614; citation_id=CR1
citation_journal_title=Nonrenewable Resources; citation_title=Combining indicator patterns in weights of evidence modeling for resource evaluation; citation_author=F. P. Agterberg; citation_volume=1; citation_issue=1; citation_publication_date=1992; citation_pages=39-50; citation_id=CR2
citation_title=Deriving weights of evidence from geoscience contour maps for the prediction of discrete events; citation_inbook_title=Proc. 22nd APCOM Symp. (Berlin); citation_publication_date=1990; citation_pages=381-396; citation_id=CR3; citation_author=F. P. Agterberg; citation_author=G. Bonham-Carter; citation_publisher=Technical Univ.
citation_journal_title=Computers & Geosciences; citation_title=Integration of mineral resource data for Kasmere Lake area, northwest Manitoba, with emphasis on uranium; citation_author=G. F. Bonham-Carter, C. F. Chung; citation_volume=15; citation_issue=1; citation_publication_date=1983; citation_pages=25-45; citation_id=CR4
citation_journal_title=Ann. Inst. Statistical Mathematics (Tokyo); citation_title=Estimation of a multivariate density; citation_author=T. Cacoullos; citation_volume=18; citation_issue=2; citation_publication_date=1966; citation_pages=179-189; citation_id=CR5
citation_journal_title=Math. Geology; citation_title=Regression models for estimating mineral resources from geological map data; citation_author=C. F. Chung, F. P. Agterberg; citation_volume=12; citation_issue=5; citation_publication_date=1980; citation_pages=473-488; citation_id=CR6
Cox, D. P., and Singer, D. A., 1986, Mineral deposit models: U.S. Geol. Survey Bull. 1693, 379 p.
citation_journal_title=Producers Monthly; citation_title=Differentiation of oil-bearing from barren sediments by quantitative petrographic analysis; citation_author=J. C. Griffiths; citation_volume=19; citation_issue=2; citation_publication_date=1957; citation_pages=33-37; citation_id=CR8
Harris, D. P., 1965, An application of multivariate statistical analysis to mineral exploration: unpubl. doctoral dissertation, Pennsylvania State Univ., University Park, 261 p.
citation_title=Mineral resources appraisal; citation_publication_date=1984; citation_id=CR10; citation_author=D. P. Harris; citation_publisher=Oxford Univ. Press
citation_title=Mineral exploration decisions: a guide to economic analysis and modeling; citation_publication_date=1990; citation_id=CR11; citation_author=D. P. Harris; citation_publisher=John Wiley & Sons
citation_journal_title=Econ. Geology; citation_title=Consistent geological areas for epithermal gold-silver deposits in the Walker Lake Quadrangle of Nevada and California delineated by quantitative methods; citation_author=D. P. Harris, G. Pan; citation_volume=86; citation_issue=1; citation_publication_date=1991; citation_pages=142-165; citation_id=CR12
Harris, D. P., and Rieber, M., 1993, Evaluation of the United States Geological Survey's three-step assessment methodology: U.S. Geol. Survey Open-File Rept. 93–258, 673 p.
citation_title=Neural networks, a comprehensive foundation; citation_publication_date=1994; citation_id=CR14; citation_author=S. Haykin; citation_publisher=Macmillan College Publ. Co. or Maxwell Macmillan Intern.
citation_journal_title=Math. Geology; citation_title=An empirical discriminant method applied to sedimentary rock classification from major element geochemistry; citation_author=R. J. Howarth; citation_volume=3; citation_issue=1; citation_publication_date=1971; citation_pages=51-60; citation_id=CR15
Link, A. J., 1964, A Phsico-chemical and textural study of carbonate sedimentation in a lagoonal environment: unpubl. masters thesis, Northwestern Univ., 125 p.
citation_journal_title=Ann. Mathematical Statistics; citation_title=Estimation of probability density; citation_author=V. K. Murthy; citation_volume=36; citation_issue=3; citation_publication_date=1965; citation_pages=1027-1031; citation_id=CR17
citation_title=Nonparametric estimation of multivariate densities with applications; citation_inbook_title=Multivariate analysis; citation_publication_date=1966; citation_pages=43-58; citation_id=CR18; citation_author=V. K. Murthy; citation_publisher=Academic Press
Orris, Greta Jean, 1997, An investigation of two methodologies for estimating boron in lacustrine settings: unpubl. doctoral dissertation, Dept. Mining and Geological Engineering, Univ. Arizona, 281 p.
Pan, G. C., 1989, Concepts and methods of multivariate information synthesis for mineral resources estimation: unpubl. doctoral dissertation, Dept. of Mining and Geol. Eng., Univ. Arizona, Tucson, 302 p.
citation_journal_title=Computers & Geoscience; citation_title=Canonical favorability model for data integration and mineral potential mapping; citation_author=G. C. Pan; citation_volume=19; citation_issue=8; citation_publication_date=1993; citation_pages=1077-1100; citation_id=CR21
citation_journal_title=Nonrenewable Resources; citation_title=Extended weights of evidence modeling for the pyseudo-estimation of metal grades; citation_author=G. C. Pan; citation_volume=5; citation_issue=1; citation_publication_date=1996; citation_pages=53-76; citation_id=CR22
citation_journal_title=Math. Geology; citation_title=Estimating a favorability function for the integration of geodata and selection of mineral exploration targets; citation_author=G. C. Pan, D. P. Harris; citation_volume=24; citation_issue=2; citation_publication_date=1992; citation_pages=177-202; citation_id=CR23
citation_journal_title=Ann. Mathematical Statistics; citation_title=On estimation of a probability density function and mode; citation_author=E. Parzen; citation_volume=33; citation_issue=3; citation_publication_date=1962; citation_pages=1065-1076; citation_id=CR24
citation_journal_title=Math. Geology; citation_title=Discriminant analysis as a method of predicting mineral occurrence potentials in central Norway; citation_author=A. E. Prelat; citation_volume=9; citation_issue=4; citation_publication_date=1977; citation_pages=343-367; citation_id=CR25
citation_title=Linear statistical inference and its applications; citation_publication_date=1973; citation_id=CR26; citation_author=C. R. Rao; citation_publisher=John Wiley & Sons, Inc.
Reddy, R. K., Agterberg, F. P., and Bonham-Carter, G. F., 1991, Application of GIS-based logistic models to base-metal potential mapping in Snow Lake area, Manitoba: Proc. Canadian Conference on GIS, Ottawa, p. 607–618.
citation_journal_title=Jour. Sed. Pet.; citation_title=Depositional mechanisms from the size analysis of clastic sediments; citation_author=B. K. Sahu; citation_volume=34; citation_issue=1; citation_publication_date=1964; citation_pages=73-83; citation_id=CR28
citation_title=SAS/STAT User's Guide; citation_publication_date=1990; citation_id=CR29; citation_publisher=SAS Institute, Inc., Sas Campus Drive
citation_journal_title=Math. Geology; citation_title=Application of a feedforward neural network in the search for Kuroko deposits in the Hokuroku District, Japan; citation_author=D. A. Singer, R. Kouda; citation_volume=28; citation_issue=8; citation_publication_date=1996; citation_pages=1017-1023; citation_id=CR30
citation_journal_title=Nonrenewable Resources; citation_title=Classification of mineral deposits into types using mineralogy with a probabilistic neural network; citation_author=D. A. Singer, R. Kouda; citation_volume=6; citation_issue=1; citation_publication_date=1997; citation_pages=27-32; citation_id=CR31
Singer, D. A., and Kouda, R., 1997b, Use of neural network to integrate geoscience information in the classification of mineral deposits and occurrences, in Gubins, A. G., ed., Proc. Exploration 97: Fourth Decennial Intern. Conf. Mineral Exploration, p. 127–134.
citation_journal_title=Econ. Geology; citation_title=Integrating spatial and frequency information in the search for kuroko deposits of the Hokuroku District, Japan; citation_author=D. A. Singer, K Ryoichi; citation_volume=83; citation_issue=1; citation_publication_date=1988; citation_pages=18-29; citation_id=CR33
citation_journal_title=Neural Networks; citation_title=Probabilistic neural networks; citation_author=D. F. Specht; citation_volume=3; citation_issue=1; citation_publication_date=1990; citation_pages=109-118; citation_id=CR34
citation_journal_title=IEEE Trans. Neural Networks; citation_title=A general regression neural network; citation_author=D. F. Specht; citation_volume=2; citation_issue=6; citation_publication_date=1991; citation_pages=568-576; citation_id=CR35
citation_journal_title=Proc. Intern. Joint Conference On Neural Networks; citation_title=Generalization accuracy of probabilistic neural networks compared with back-propagation networks; citation_author=D. F. Specht, P. D. Shapiro; citation_volume=1; citation_publication_date=1991; citation_pages=887-892; citation_id=CR36
citation_title=NeuroShell 2; citation_publication_date=1996; citation_id=CR37; citation_publisher=Ward Systems Group, Inc.
citation_journal_title=Jour. Sed. Pet.; citation_title=Discriminating between refractory and nonrefractory quartzite by quantitative petrography; citation_author=G. V. Wood; citation_volume=31; citation_issue=4; citation_publication_date=1961; citation_pages=530-533; citation_id=CR38