Application of discriminant analysis and generalized distance measures to uranium exploration

  • J. J. Beauchamp
  • C. L. Begovich
  • V. E. Kane
  • D. A. Wolf
Article

Abstract

The National Uranium Resource Evaluation (NURE) Program has as its goal the estimation of the nation's uranium resources. It is possible to use discriminant analysis methods on hydrogeochemical data collected in the NURE Program to aid in formulating geochemical models that can be used to identify the anomalous areas used in resource estimation. Discriminant analysis methods have been applied to data from the Plainview, Texas Quadrangle which has approximately 850 groundwater samples with more than 40 quantitative measurements per sample. Discriminant analysis topics involving estimation of misclassification probabilities, variable selection, and robust discrimination are applied. A method using generalized distance measures is given which enables the assignment of samples to a background population or a mineralized population whose parameters were estimated from separate studies. Each topic is related to its relevance in identifying areas of possible interest to uranium exploration. However, the methodology presented here is applicable to the identification of regions associated with other types of resources.

Key words

discriminant analysis variable selection uranium favorability generalized distance measures regional variables geochemical fingerprint 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Agterberg, F. P., 1974. Geomathematics: Elsevier Scientific Publishing Co., New York.Google Scholar
  2. Amaral, E. J., 1979, NURE Plainview quadrangle, Texas: Bendix Field Engineering Corporation, Grand Junction Operations, Grand Junction, Colorado, GJQ-001.Google Scholar
  3. Anderson, T. W., 1958, An introduction to multivariate statistical analysis: John Wiley & Sons, New York.Google Scholar
  4. Arendt, J. W., Butz, T. R., Cagle, G. W., Kane, V. E., and Nichols, C. E., 1979, Hydrogeochemical and stream sediment reconnaissance procedures of the uranium resource evaluation project: Union Carbide Corporation, Nuclear Division, Oak Ridge Gaseous Diffusion Plant, Oak Ridge, Tennessee, K/UR-100.Google Scholar
  5. Barr, A. J., Goodnight, J. H., Sall, J. P., and Helwig, J. T., 1976, A user's guide to SAS76: SAS Institute, Inc., Raleigh, North Carolina.Google Scholar
  6. Beauchamp, J. J., Begovich, C. L., Kane, V. E., and Wolf, D. A., 1979, Application of discriminant analysis and generalized distance measures to uranium exploration: Union Carbide Corporation, Nuclear Division, Oak Ridge Gaseous Diffusion Plant, Oak Ridge, Tennessee, K/UR-28.Google Scholar
  7. Dixon, W. J. and Brown, M. B., BMDP-77, 1977, Biomedical computer programs P-series: University of California Press, Berkeley, California.Google Scholar
  8. Gnanadesikan, R., 1977, Methods for statistical data analysis of multivariate observations, John Wiley & Sons, New York.Google Scholar
  9. Habbema, J. D. F. and Hermans, J., 1977, Selection of variables in discriminant analysis by F-statistic and error rate: Technometrics, v. 19, p. 487–493.Google Scholar
  10. Huber, P. J., 1977, Robust covariances, statistical decision theory and related topics II: Academic Press, New York.Google Scholar
  11. Lachenbruch, P. A., 1975, Discriminant analysis: Hafner, New York.Google Scholar
  12. Lachenbruch, P. A. and Goldstein, M., 1979, Discriminant analysis: Biometrics, v. 35, p. 69–85.Google Scholar
  13. McCabe, G. P., Jr., 1975, Computations for variable selection in discriminant analysis: Technometrics, v. 17, p. 103–109.Google Scholar
  14. McCabe, G. P., Jr., 1979, Personal communication.Google Scholar
  15. Randles, R. H., Broffitt, J. D., Ramberg, J. S., and Hogg, R. V., 1978a, Discriminant analysis based on ranks: J. Amer. Stat. Ass., v. 73, p. 379–384.Google Scholar
  16. Randles, R. H., Broffitt, J. D., Ramberg, J. S., and Hogg, R. V., 1978b, Generalized linear and quadratic discriminant functions using robust estimates: J. Amer. Stat. Ass., v. 73, p. 564–568.Google Scholar
  17. Rao, C. R., 1965, Linear statistical inference and its applications: John Wiley & Sons, Inc., New York, p. 435–513.Google Scholar
  18. Uranium Resource Evaluation Project, 1978, Hydrogeochemical and stream sediment reconnaissance basic data for Plainview NTMS quadrangle, Texas: Union Carbide Corporation, Nuclear Division, Oak Ridge Gaseous Diffusion Plant, Oak Ridge, Tennessee, K/UR-101. United States Department of Energy, Grand Junction, Colorado [GJBX-92(78)].Google Scholar
  19. Uranium Resource Evaluation Project, 1978, Procedures manual for groundwater reconnaissance sampling: Union Carbide Corporation, Nuclear Division, Oak Ridge Gaseous Diffusion Plant, Oak Ridge, Tennessee, K/UR-12. United States Department of Energy, Grand Junction, Colorado [GJBX-62(78)].Google Scholar

Copyright information

© Plenum Publishing Corporation 1980

Authors and Affiliations

  • J. J. Beauchamp
    • 1
  • C. L. Begovich
    • 1
  • V. E. Kane
    • 1
  • D. A. Wolf
    • 1
  1. 1.Computer Sciences DivisionUnion Carbide Corporation, Nuclear DivisionOak RidgeUSA

Personalised recommendations