Abstract
Mineral-potential mapping is the process of combining a set of input maps, each representing a distinct geo-scientific variable, to produce a single map which ranks areas according to their potential to host mineral deposits of a particular type. The maps are combined using a mapping function that must be either provided by an expert (knowledge-driven approach), or induced from sample data (data-driven approach). Current data-driven approaches using multilayer perceptrons (MLPs) to represent the mapping function have several inherent problems: they are highly sensitive to the selection of training data; they do not utilize the contextual information provided by nondeposit data; and there is no objective interpretation of the values output by the MLP. This paper presents a new approach by which MLPs can be trained to output values that can be interpreted strictly as representing posterior probabilities. Other advantages of the approach are that it utilizes all data in the construction of the model, and thus eliminates any dependence on a particular selection of training data. The technique is applied to mapping gold mineralization potential in the Castlemaine region of Victoria, Australia, and results are compared with a method based on estimating probability density functions.
Article PDF
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
References
Baum, E. B., and Wilczek, F., 1988, Supervised learning of probability distributions by neural networks, in Anderson, D. Z., ed., Neural Information Processing Systems: Am. Ins. Physics, New York, p. 52–61.
Bishop, C. M., 1995, Neural networks for pattern recognition: Oxford Univ. Press, Oxford, 482 p.
Bonham-Carter, G. F., 1994, Geographic information systems for geoscientists: modeling with GIS: Pergamom Press, Oxford, 398 p.
Brown, W. M., Gedeon, T. D., and Groves, D. I., 2003, Use of noise to augment training data: a neural network method of mineral–potential mapping in regions of limited known deposit examples: Natural Resources Research, v. 12, no. 2, p. 141–152.
Brown, W. M., Gedeon, T. D., Groves, D. I., and Barnes, R. G., 2000, Artificial neural networks: a new method for mineral prospectivity mapping: Jour. Australian Earth Sciences, v. 47, no. 4, p. 757–770.
Clark, I., and Cook, B., eds., 1988, Victorian geology excursion guide: Australian Acad. Science, Canberra, Australia, 489 p.
Cochrane, G. W., Quick, G., and Spencer-Jones, D., eds., 1995, Introducing Victorian geology (2nd edn,): Geol. Soc. Australia Incorporated (Victorian Division), Melbourne, Australia, 304 p.
Cybenko, G., 1989, Approximation by superpositions of a sigmoidal function: Math. Control, Signals, and Systems, v. 2, p. 303–314.
Dempster, A. P., Laird, N. M., and Rubin, D. B., 1977, Maximum likelihood from incomplete data via the EM algorithm: Jour. Roy. Statist. Soc. Series B, v. 39, p. 1–38.
Duda, R. O., and Hart, P. E., 1973, Pattern recognition and scene analysis: John Wiley & Sons, New York, 482 p.
Harris, D., and Pan, G., 1999, Mineral favorability mapping: a comparison of artificial neural networks, logistic regression, and discriminant analysis: Natural Resources Research, v. 8, no. 2, p. 93–109.
Harris, D., Zurcher, L, Stanley, M., Marlow, J., and Pan, G., 2003, A comparative analysis of favorability mappings by weights of evidence, probabilistic neural networks, discriminant analysis, and logistic regression: Natural Resources Research, v. 12, no. 4, p. 241–256.
Hopfield, J. J., 1987, Learning algorithms and probability distributions in feed-forward and feed-back networks: Proc. Nat. Acad. Sciences, v. 84, p. 8428–8433.
Hornick, K., Stinchcombe, M., and White, H., 1989, Multilayer feed-forward networks are universal approximators: Neural Networks, v. 2, no. 5, p. 359–66.
Møller, M., 1993, A scaled conjugate gradient algorithm for fast supervised learning: Neural Networks, v. 6, no. 4, p. 523–533.
Parzen, E., 1962, On estimation of a probability density function and mode: Ann. Math. Statistics, v. 33, no. 3, p. 1065–1076.
Porwal, A., Carranza, E. J., and Hale, M. 2003, Artificial neural networks for mineral-potential mapping: a case study from the Aravalli Provence’ Western India: Natural Resources Research, v. 12, no. 3, p 155–171.
Rumelhart, D. E., and McClelland, J. L., 1986, Parallel distributed processing: exploration in the microstructure of cognition (Vols. 1 & 2), MIT Press, Cambridge, MA, 611 p. and 547 p.
Schumacher, M., Rossner, R., and Vach, W., 1996, Neural networks and logistic regression: part 1 & 2: Computational Statistics & Data Analysis, v. 21, p. 661–701.
Singer, D. A., and Kouda, R., 1996, Application of a feed-forward neural network in the search for Kuroko deposits in the Hokoruko District, Japan: Math. Geology, v. 28, no. 8, p. 1017–1023.
Singer, D. A., and Kouda, R., 1997, 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., 1999, A comparison of the weights-of-evidence method and probabilistic neural networks: Natural Resources Research, v. 8, no., 4, p. 287–298.
Skabar, A., 2000, Inductive learning techniques for mineral potential mapping: unpubl. docforal dissertation, School Electrical and Electronic Systems Engineering, Queensland Univ. Technology, Australia, 225 p.
Specht, D. F., 1990, Probabilistic neural networks: Neural Networks, v. 3, no. 1, p. 109–118.
Titterington, D. M., Smith, A. F. M., and Makov, U. E., 1985, Statistical analysis of finite mixture distributions: John Wiley & Sons, New York, 243 p.
Willman, C. E. 1995, Castlemaine Goldfield: Castlemaine-Chewton, Fryers Creek 1:10 000 Maps: Victoria Energy and Minerals, Geol. Survey Rept. 106.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Skabar, A.A. Mapping Mineralization Probabilities using Multilayer Perceptrons. Nat Resour Res 14, 109–123 (2005). https://doi.org/10.1007/s11053-005-6955-z
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/s11053-005-6955-z