Building a machine learning classifier for iron ore prospectivity in the Yilgarn Craton

Andrew S. Merdith; Thomas C.W. Landgrebe; R. Dietmar Muller

doi:10.1071/ASEG2015ab282

24th International Geophysical Conference and Exhibition – Geophysics and Geology Together for Discovery

ISSN: 2202-0586
E-ISSN:

oa Building a machine learning classifier for iron ore prospectivity in the Yilgarn Craton
Authors Andrew S. Merdith^a, Thomas C.W. Landgrebe^b and R. Dietmar Muller^c
View Affiliations Hide Affiliations

^a Earthbyte Group, School of GeosciencesUniversity of Sydney, , 2006 [email protected] ^b Earthbyte Group, School of GeosciencesUniversity of Sydney, , 2006 [email protected] ^c Earthbyte Group, School of GeosciencesUniversity of Sydney, , 2006 [email protected]
Publisher: Australian Society of Exploration Geophysicists
Source: ASEG Extended Abstracts, Volume 2015, Issue 24th International Geophysical Conference and Exhibition – Geophysics and Geology Together for Discovery, Dec 2015, p. 1 - 4
DOI: https://doi.org/10.1071/ASEG2015ab282
- Published online: 01 Dec 2015

Abstract

High resolution, large-scale geophysical data have recently become readily and freely available for the majority of the Australian continent; yet there have been few efforts to create a synthesis of these datasets for mineral exploration. Considering the rising cost of finding new deposits and the recent economic downturn, there is a focus on using low expenditure, large-scale explorative techniques to assist in finding deposits. Using sophisticated machine learning algorithms coupled with increases in computational power, we present a methodology that tests and trains a classifier using six geophysical datasets in conjunction with 37 iron ore locations in the Pilbara Craton that accurately predicts the locations of iron ore deposits throughout the Yilgarn Craton. Our selected classifier uses principal component analysis and mixture of Gaussian classification with reject option, and it successfully identifies 88% of iron ore locations. We use cross-validation (10 fold, 70% testing 30% training) to ensure the generalisation of our classifier. We apply our classifier to the Yilgarn Craton, an area not used for the training and testing phase, and compare the predictive confidence map to previously published locations of iron ore occurrences. We find that our classifier correctly locates key known Yilgarn iron ore deposits, in addition to highlighting other areas that could potentially be prospective for iron ore.

Article metrics loading...

/content/journals/10.1071/ASEG2015ab282

2015-12-01

2026-01-13

From This Site

/content/journals/10.1071/ASEG2015ab282

dcterms_title,dcterms_subject,pub_keyword

-contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution

10

5

Full text loading...

References

Alpaydin, E. (2010). Introduction to machine learning. Methods in Molecular Biology (2nd ed., Vol. 1107, pp. 1579). Cambridge: Massachusetts Institute of Technology. doi: 10.1007/978-1-62703-748-8-7
Britt, A., Barber, J., Carson, L., Penney, K., Skirrow, R., Shael, T., ... Barnicoat, A. (2013). Australia’s Mineral Resource Assessment 2013. Canberra, Australia.
Brown, W. M., Gedeon, T. B., Groves, B. I., & Barnes, R. G. (2000). Artificial neural networks : A new method for mineral prospectivity mapping. Australian Journal of Earth Sciences, 47(4), 37-41. doi:10.1046/j.1440-0952.2000.00807.x
Carranza, E. J. M. (2011). From Predictive Mapping of Mineral Prospectivity to Quantitative Estimation of Number of Undiscovered Prospects. Resource Geology, 61(1), 30-51. doi: 10.1111751-3928.2010.00146.x
Cooper, R. (2013). Iron Ore Deposits of the Yilgarn Craton -2013. Geological Survey of Western Australia.
Cracknell, M. J., Reading, a. M., & McNeill, a. W. (2013). Mapping geology and volcanic-hosted massive sulfide alteration in the Hellyer-Mt Charter region, Tasmania, using Random Forests™ and Self-Organising Maps. Australian Journal of Earth Sciences, 61 (August 2014), 287-304. doi:10.1080/08120099.2014.858081
Buda, R., Hart, P., & Stork, B. (2000). Pattern Classification (2nd ed., p. 680). New York: Wiley.
Buuring, P., & Hagemann, S. (2013). Genesis of superimposed hypogene and supergene Fe orebodies in BIF at the Madoonga deposit, Yilgarn Craton, Western Australia. Mineralium Deposita, 48, 371-395. doi:10.1007/s00126-012-0429-0
Ewers, G., Evans, N., Hazell, M., & Kilgour, B. (2002). OZMIN Mineral Beposits Batabase. Canberra: Geoscience Australia.
Gross, G. A. (1980). On Classification of Iron Formations based on Bepositional Environments. Canadian Mineralogist, 18, 215-222.
Groves, B. I., Goldfarb, R. J., Knox-Robinson, C. M., Ojala, J., Gardoll, S., Yun, G. Y., & Holyland, P. (2000). Late-kinematic timing of orogenic gold deposits and significance for computer-based exploration techniques with emphasis on the Yilgarn Block, Western Australia. Ore Geology Reviews, 17, 1-38. doi:10.1016/S0169-1368(00)00002-0
Holden, E.-J., Bentith, M., & Kovesi, P. (2008). Towards the Automated Analysis of Regional Aeromagnetic Bata to Identify Regions Prospective for Gold Beposits. Computers & Geosciences, 34, 1505-1513.
Holden, E.-J., Wong, J. C., Kovesi, P., Wedge, B., Bentith, M., & Bagas, L. (2012). Identifying structural complexity in aeromagnetic data: An image analysis approach to greenfields gold exploration. Ore Geology Reviews, 46, 47-59. doi: 10.1016/j.oregeorev.2011.11.002
Hronsky, J. M. A., & Groves, B. I. (2008). Science of targeting: definition, strategies, targeting and performance measurement. Australian Journal of Earth Sciences, 55(1), 312.
Huston, B. L., & Logan, G. a. (2004). Barite, BIFs and bugs: Evidence for the evolution of the Earth’s early hydrosphere. Earth and Planetary Science Letters, 220, 41 -55. doi:10.1016/S0012-821X(04)00034-2
Jolliffe, I. (2002). Principal Component Analysis. In Springer Series in Statistics (2nd ed.). New York: Springer-Verlag.
Landgrebe, T. C. W., Merdith, A., Butkiewicz, A., & Muller, R. B. (2013). Relationships between palaeogeography and opal occurrence in Australia: A data-mining approach. Computers & Geosciences, 56, 76-82. doi:10.1016/j.cageo.2013.02.002
Landgrebe, T. W., Tax, B., & Buin, R. (2006). The interaction between classification and reject performance for distance-based reject-option classifiers. Pattern Recognition Letters, 27(8), 908-917. doi:10.1016/j.patrec.2005.10.015
Merdith, A. S., Landgrebe, T. C. W., Butkiewicz, A., & Muller, R. B. (2013). Towards a predictive model for opal exploration using a spatio-temporal data mining approach. Australian Journal of Earth Sciences, 60(2), 217-229. doi: 10.1080/08120099.2012.754793
Tax, B. (2014). BBtools, the Bata Bescription Toolbox for Matlab. Retrieved from http://prlab.tudelft.nl/david-tax/dd_tools.html

/content/journals/10.1071/ASEG2015ab282

Article Type: Research Article

Keyword(s): big data; iron ore; Machine Learning; mineral exploration; Pilbara Craton; Yilgarn Craton

Most Cited This Month Most Cited RSS feed

- Inversion of data from electrical imaging surveys in water-covered areas
  
  Authors M. H. Loke and J. W. Lane
- Inversion of Magnetic Data from Remanent and Induced Sources
  
  Authors Robert G. Elllis, Barrry de Wet and Ian N. Macleod
- A comparison of smooth and blocky inversion methods in 2-D electrical imaging surveys
  
  Authors M. H. Loke, Ian Acworth and Torleif Dahlin
- Designing matched bandpass and azimuthal filters for the separation of potential-field anomalies by source region and source type
  
  Authors Jeffrey D. Phillips
- Bad Colour Maps Hide Big Features and Create False Anomalies
  
  Authors Peter Kovesi
- Practical 3D EM inversion – the P223F software suite
  
  Authors Art Raiche, Fred Sugeng and Glenn Wilson
- Estimating Noise Levels in AEM Data
  
  Authors Andy Green and Richard Lane
- Target delineation using Full Tensor Gravity Gradiometry data
  
  Authors Colm A. Murphy and James Brewster
- Transdimensional Monte Carlo Inversion of AEM Data
  
  Authors Ross C Brodie and Malcolm Sambridge
- The geotech VTEM time domain helicopter em system
  
  Authors Ken Witherly, Richard Irvine and Edward Morrison
More Less

oa Building a machine learning classifier for iron ore prospectivity in the Yilgarn Craton

Abstract

Most Read This Month

Most Cited This Month Most Cited RSS feed