Abstract
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.
Similar content being viewed by others
REFERENCES
Agterberg, F. P., 1989, LOGDIA-FORTRAN 77 program for logistic regression with diagnostics: Computers & Geosciences, v. 15,no. 4, p. 599–614.
Agterberg, F. P., 1992, Combining indicator patterns in weights of evidence modeling for resource evaluation: Nonrenewable Resources, v. 1,no. 1, p. 39–50.
Agterberg, F. P., and Bonham-Carter, G., 1990, Deriving weights of evidence from geoscience contour maps for the prediction of discrete events: Proc. 22nd APCOM Symp. (Berlin), Technical Univ., Berlin, v. 2, p. 381–396.
Bonham-Carter, G. F., and Chung, C. F., 1983, Integration of mineral resource data for Kasmere Lake area, northwest Manitoba, with emphasis on uranium: Computers & Geosciences, v. 15,no. 1, p. 25–45.
Cacoullos, T., 1966, Estimation of a multivariate density: Ann. Inst. Statistical Mathematics (Tokyo), v. 18,no. 2, p. 179–189.
Chung, C. F., and Agterberg, F. P., 1980, Regression models for estimating mineral resources from geological map data: Math. Geology, v. 12,no. 5, p. 473–488.
Cox, D. P., and Singer, D. A., 1986, Mineral deposit models: U.S. Geol. Survey Bull. 1693, 379 p.
Griffiths, J. C., 1957, Differentiation of oil-bearing from barren sediments by quantitative petrographic analysis: Producers Monthly, v. 19,no. 2, p. 33–37.
Harris, D. P., 1965, An application of multivariate statistical analysis to mineral exploration: unpubl. doctoral dissertation, Pennsylvania State Univ., University Park, 261 p.
Harris, D. P., 1984, Mineral resources appraisal: Oxford Univ. Press, New York, 445 p.
Harris, D. P., 1990, Mineral exploration decisions: a guide to economic analysis and modeling: John Wiley & Sons, New York, 436 p.
Harris, D. P., and Pan, G., 1991, Consistent geological areas for epithermal gold-silver deposits in the Walker Lake Quadrangle of Nevada and California delineated by quantitative methods: Econ. Geology, v. 86,no. 1, p. 142–165.
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.
Haykin, S., 1994, Neural networks, a comprehensive foundation: Macmillan College Publ. Co. or Maxwell Macmillan Intern., New York, 696 p.
Howarth, R. J., 1971, An empirical discriminant method applied to sedimentary rock classification from major element geochemistry: Math. Geology, v. 3,no. 1, p. 51–60.
Link, A. J., 1964, A Phsico-chemical and textural study of carbonate sedimentation in a lagoonal environment: unpubl. masters thesis, Northwestern Univ., 125 p.
Murthy, V. K., 1965, Estimation of probability density: Ann. Mathematical Statistics, v. 36,no. 3, p. 1027–1031.
Murthy, V. K., 1966, Nonparametric estimation of multivariate densities with applications, in Krishnaiah, P. R., ed., Multivariate analysis: Academic Press, New York, p. 43–58.
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.
Pan, G. C., 1993, Canonical favorability model for data integration and mineral potential mapping: Computers & Geoscience, v. 19,no. 8, p. 1077–1100.
Pan, G. C., 1996, Extended weights of evidence modeling for the pyseudo-estimation of metal grades: Nonrenewable Resources, v. 5,no. 1, p. 53–76.
Pan, G. C., and Harris, D. P., 1992, Estimating a favorability function for the integration of geodata and selection of mineral exploration targets: Math. Geology, v. 24,no. 2, p. 177–202.
Parzen, E., 1962, On estimation of a probability density function and mode: Ann. Mathematical Statistics, v. 33,no. 3, p. 1065–1076.
Prelat, A. E., 1977, Discriminant analysis as a method of predicting mineral occurrence potentials in central Norway: Math. Geology, v. 9,no. 4, p. 343–367.
Rao, C. R., 1973, Linear statistical inference and its applications (2nd ed.): John Wiley & Sons, Inc., New York, 625 p.
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.
Sahu, B. K., 1964, Depositional mechanisms from the size analysis of clastic sediments: Jour. Sed. Pet., v. 34,no. 1, p. 73–83.
SAS, 1990, SAS/STAT User's Guide, v. 1 and v. 2, (4th ed.): SAS Institute, Inc., Sas Campus Drive, Gary, NC 27513.
Singer, D. A., and Kouda, R., 1996, Application of a feedforward neural network in the search for Kuroko deposits in the Hokuroku District, Japan: Math. Geology, v. 28,no. 8, p. 1017–1023.
Singer, D. A., and Kouda, R., 1997a, Classification of mineral deposits into types using mineralogy with a probabilistic neural network: Nonrenewable Resources, v. 6,no. 1, p. 27–32.
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.
Singer, D. A., and Ryoichi, K, 1988, Integrating spatial and frequency information in the search for kuroko deposits of the Hokuroku District, Japan: Econ. Geology, v. 83,no. 1, p. 18–29.
Specht, D. F., 1990, Probabilistic neural networks: Neural Networks, v. 3,no. 1, p. 109–118.
Specht, D. F., 1991, A general regression neural network: IEEE Trans. Neural Networks, v. 2,no. 6, p. 568–576.
Specht, D. F., and Shapiro, P. D, 1991, Generalization accuracy of probabilistic neural networks compared with back-propagation networks, in Proc. Intern. Joint Conference On Neural Networks, v. 1, p. 887–892.
Ward Systems Group, Inc., 1996, NeuroShell 2: Ward Systems Group, Inc., Executive Park West, 5 Hillcrest Drive, Frederick, MD 21702, 298 p.
Wood, G. V., 1961, Discriminating between refractory and nonrefractory quartzite by quantitative petrography: Jour. Sed. Pet., v. 31,no. 4, p. 530–533.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Harris, D., Pan, G. Mineral Favorability Mapping: A Comparison of Artificial Neural Networks, Logistic Regression, and Discriminant Analysis. Natural Resources Research 8, 93–109 (1999). https://doi.org/10.1023/A:1021886501912
Issue Date:
DOI: https://doi.org/10.1023/A:1021886501912