Abstract
Multiple Regressive Pattern Recognition Technique (MRPRT) is an adapted approach for improved geologic resource estimation. We developed and tested this approach for the Platinum (Pt) bearing region near Goodnews Bay, Alaska, which presents an example of a complex depositional environment. We applied geospatial and pattern recognition methods to assess the spatial distribution of offshore Pt in the Goodnews Bay area from point data collected by various agencies. We used the coefficient of correlation (r) and the Nash–Sutcliffe efficiency (E) to quantitatively assess the degree of accuracy of the estimated Pt distribution. We split the study area, based on trend analysis, into two regions: inside the Bay and outside the Bay. We could not obtain appreciable estimates from the geospatial and pattern recognition methods. Using MRPRT, we were able to improve r from 0.57 to 0.93 and the E from 28.31 to 92.91 inside the Bay. We achieved improvement in r from 0.55 to 0.61 and E from 28.46 to 34.52 outside the Bay. The reasons for a non-significant improvement outside the Bay have been discussed. The results indicate that the proposed MRPRT has wide application potential in georesource estimation where input data is often scarce.
This is a preview of subscription content, access via your institution.
References
Barker, J. C., 1986, Platinum-group metals, gold and chromium resource potential offshore of Platinum, Alaska Presented at the 17th annual underwater mining conference, Biloxi, Missouri, available upon request from files at Bureau of Mines, Alaska Field Operations Center: Anchorage, Alaska.
Barker, J. C., and Lamal, K., 1989, Offshore extension of platiniferous bedrock and associated sedimentation of the Goodnews Bay ultramafic complex, Alaska: Mar. Min., v. 8, no. 4, p. 65.
Chee, L. P., and Harrison, R. F., 2003, Online pattern classification with multiple neural network systems: an experimental study: IEEE Trans. Syst. Man Cybern., v. 23, no. 2, p. 235–247.
Clark, I., and Harper, W. V., 2000, Practical geostatistics: Ecosse North American LLC, Columbus, OH, 411 p.
Drucker, H., Cortes, C., Jackel, L. D., Lecun, Y., and Vapnik, V., 1994, Boosting and other ensemble methods: Neural Comput., v. 6, no. 6, p. 1289–1301.
Dutta, S., 2006, Predictive performance of machine learning algorithms for ore reserve estimation in sparse and imprecise data: University of Alaska, Fairbanks, p. 189.
Dutta, S., Misra, D., Ganguli, R., Samanta, B., and Bandopadhyay, S., 2006, A hybrid ensemble model of kriging and neural network for ore grade estimation: Int. J. Surf. Min. Reclamat. Environ., v. 20, no. 1, p. 33–45.
Foody, G. M., and Mathur, A., 2004, A relative evaluation of multiclass image classification by support vector machines: IEEE Trans. Geosci. Remote Sens., v. 42, no. 6, p. 1335–1343.
Fumera, G., and Roli, F., 2005, A theoretical and experimental analysis of linear combiners for multiple classifier systems: IEEE Trans. Pattern Anal. Mach. Intell., v. 27, no. 6, p. 942–956.
Gutta, S., Huang, J. R. J., Jonathon, P., and Wechsler, H., 2000, Mixture of experts for classification of gender, ethnic origin, and pose of human faces: IEEE Trans. Neural Netw., v. 11, no. 4, p. 948–960.
Hansen, L. K., and Salamon, P., 1990, Neural network ensembles: IEEE Trans. Pattern Anal. Mach. Intell., v. 12, no. 10, p. 993–1001.
Harrington, G. L., 1919, Mineral resources of the Goodnews Bay region: U.S. Geol. Surv. Bull., v. 714, p. 207–228.
Hastie, T. R. T., and Friedman, J., eds., 2003, The elements of statistical learning: data mining, inference and prediction: Springer-Verlag, New York, p. 533.
Isaaks, E. H., and Srivastava, R. M., 1989, An introduction to applied geostatistics: Oxford University, New York, 561 p.
Jacobs, R. A., 1995, Methods for combining experts probability assessments: Neural Comput., v. 7, no. 5, p. 867–888.
Johnston, K., 2003, Using ArcGIS geostatistical analyst: ESRI Press, 316 p.
Kanevski, M., Pozdnoukhov, A., Canu, S., and Maignan, M., 2002, Advanced spatial data analysis and modeling with support vector machines: Int. J. Fuzzy Syst., v. 4, no. 1, p. 606–616.
Karatzoglou, A., Meyer, D., and Hornik, K., 2006, Support vector machines in R: J. Stat. Softw., v. 15, no. 9, p. 25.
Kittler, J., Hatef, M., Duin, R. P. W., and Matas, J., 1998, On combining classifiers: IEEE Trans. Pattern Anal. Mach. Intell., v. 20, no. 3, p. 226–239.
Kittler, J., and Roli, F., 2001, Lecture notes in computer science, in Proceedings of 2nd International Workshop on Multiple Classifier Systems, Cambridge, UK.
Kuncheva, L. I., 2004, Combining pattern classifiers: methods and algorithms: Wiley–Interscience.
Meher, S. K., Ghosh, A., Shankar, B. U., and Bruzzone, L., 2006, Neuro-fuzzy fusion: a new approach to multiple classifier system, in ICIT 2006: 9th International Conference on Information Technology, Proceedings, p. 209–212.
Meyer, D., 2001, Support vector machines: R News, v. 1/3. http://cran.r-project.org/doc/Rnews/Rnews_2001-3.pdf.
Misra, D., Samanta, B., Dutta, S., and Bandopadhyay, S., 2007, Evaluation of artificial neural network and kriging for the prediction of arsenic in alaskan bedrock derived sediments using gold concentration data: Int. J. Min. Reclamat. Environ., v. 21, no. 4, p. 282–294.
Nash, J. E., and Sutcliffe, J. V., 1970, River flow forecasting through conceptual models. Part I. A discussion of principles: J. Hydrol., v. 10, no. 3, p. 282–290.
Oommen, T., 2006, Geodatabase development and GIS based analysis for resource assessment of placer platinum in the offshore region of Goodnews Bay, Alaska: University of Alaska, Fairbanks, 198 p.
Oommen, T., and Baise, L. G., 2010, Model validation for intelligent data collection in geotechnical earthquake engineering: J. Comput. Civil Eng., v. 24, no. 6, p. 467–477.
Oommen, T., Misra, D., Twarakavi, N. K. C., Prakash, A., Sahoo, B., and Bandopadhyay, S., 2008a, An objective analysis of support vector machine based classification for remote sensing: Math. Geosci., v. 40, no. 4, p. 409–424.
Oommen, T., Prakash, A., Misra, D., Kelley, J. J., Naidu, S. A., and Bandopadhyay, S., 2008b, GIS based marine platinum exploration, Goodnews Bay Region, Southwest Alaska: Mar. Georesour. Geotechnol., v. 26, no. 1, p. 1–18.
Perrone, M., and Cooper, L. N., eds., 1993, Neural Network for Speech and Image. When networks disagree: ensemble methods for hybrid neural networks: Chapman and Hall, London.
Pozdnoukhov, A., 2005, Support vector regression for automated robust spatial mapping of natural radioactivity: J. Appl. GIS, v. 1, no. 2, p. 2101–2110.
Tipping, M. E., 2001, Sparse Bayesian learning and the relevance vector machine: J. Mach. Learn. Res., v. 1, no. 3, p. 211–244.
Twarakavi, N. K. C., Misra, D., and Bandopadhyay, S., 2006, Prediction of arsenic in bedrock derived stream sediments at a gold mine site under conditions of sparse data: Nat. Resour. Res., v. 15, no. 1, p. 15–26.
Vapnik, V., 1995, The nature of statistical learning theory: Springer-Verlag, New York.
Wolpert, D. H., 1992, Stacked generalization: Neural Netw., v. 5, no. 2, p. 241–259.
Acknowledgments
Part of this study was done by the first author when he was a graduate student at the University of Alaska Fairbanks, who acknowledges the financial support that was provided by the Minerals Management Service (MMS) of the US Department of Interior under the cooperative agreement number 1435-01-02-CA-85124. The authors are grateful to all those who helped them to gather data from the various research studies done in this region during the last five decades.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Oommen, T., Misra, D., Prakash, A. et al. Multiple Regressive Pattern Recognition Technique: An Adapted Approach for Improved Georesource Estimation. Nat Resour Res 20, 11–24 (2011). https://doi.org/10.1007/s11053-010-9132-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11053-010-9132-y
Keywords
- Pattern recognition
- geology
- mining industry
- spatial correlation
- support vector machine