Mineralisation predictive targeting using TensorFlow (Google) deep neural networks

Karl Kwan; Ian Johnson; Jean M Legault; Kanita Khaled

doi:10.1080/22020586.2019.12072983

2nd Australasian Exploration Geoscience Conference: Data to Discovery

ISSN: 2202-0586
E-ISSN:

oa Mineralisation predictive targeting using TensorFlow (Google) deep neural networks
Authors Karl Kwan^a, Ian Johnson^b, Jean M Legault^c and Kanita Khaled^d
View Affiliations Hide Affiliations

^a Geotech Ltd. Aurora, , CAN, [email protected] ^b Consultant Toronto, , CAN, [email protected] ^c Geotech Ltd. Aurora, , CAN, [email protected] ^d Geotech Ltd. Aurora, , CAN, [email protected]
Publisher: Australian Society of Exploration Geophysicists
Source: ASEG Extended Abstracts, Volume 2019, Issue 2nd Australasian Exploration Geoscience Conference: Data to Discovery, Dec 2019, p. 1 - 5
DOI: https://doi.org/10.1080/22020586.2019.12072983
- Published online: 01 Dec 2019

Abstract

Summary

Simple two-layer feedforward supervised neural network (NN) has been described and used for mineral predictive targeting. However, the simple NN has some limitations. For instance, it requires the geophysical responses of over the target be positively high relative to non-target areas.

The release of Google’s TensorFlow (TF) for Python (https://www.tensorflow.org/) in 2015 has made it possible to apply the more powerful and robust Deep Neural Network (DNN) to geoscience data for mineral predictive targeting.

We test the TF DNN using the magnetic data over a kimberlite in the Canadian Shield and compare the results with those from the simple two-layer NN. The DNN results are better.

DNNs are applied to the helicopter TDEM data from Nuqrah, western Arabian Shield and the TDEM from Kabinakagami Lake greenstone belt in Superior craton in Ontario to illustrate the utility of predictive targeting of DNN..

Article metrics loading...

/content/journals/10.1080/22020586.2019.12072983

2019-12-01

2026-01-17

From This Site

/content/journals/10.1080/22020586.2019.12072983

dcterms_title,dcterms_subject,pub_keyword

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

10

5

Full text loading...

References

Goodfellow, I., Bengio, Y. and Courville, A., 2016: Deep Learning, MIT Press Book; http://www.deeplearningbook.org.
Ontario Geological Survey, 2015, Ontario airborne geophysical surveys, magnetic and electromagnetic data, Kabinakagami Lake area: Ministry of Northern Development and Mines.
Kwan, K., Legault, J.M., Johnson, I., Prikhodko, A. and Plastow, G., 2018, Interpretation of Cole-Cole parameters derived from helicopter TDEM data – Case studies: SEG, Expanded Abstracts, 5 pp.
Kwan, K., Reford, S., Djiba, M., Pitcher, D.H., Bournas, N., Prikhodko, A., Plastow, G. and Legault, J.M., 2015, Supervised Neural Network Targeting and Classification Analysis of Airborne EM, Magnetic and Gamma-ray Spectrometry Data for Mineral Exploration: ASEG-PESA 24th International Geophysical Conference and Exhibition, Extended Abstracts, 4 pp.
Legault, J.M., Izarra, C., Prikhodko, A., Zhao, S. and Saadawi, E.M., 2014, Helicopter EM (ZTEM-VTEM) survey results over the Nuqrah copper-lead-zinc-gold SEDEX massive sulphide deposit in the Western Arabian Shield, Kingdom of Saudi Arabia: Exploration Geophysics, 46 (1), 36-48.
Mir, R., Perrouty, S., Thibaut A., Bérubé, C.L. and Smith, R.S., 2019, Structural complexity inferred from anisotropic resistivity: example from airborne EM and compilation of historical Resistivity/IP data from the gold-rich Canadian Malartic district, Québec, Canada, Geophysics (in press): 1-52, https://doi.org/10.1190/geo2018-0444.1.
Reford, S., Lipton, G. and Ugalde H., 2004, Predictive ore deposit targeting using Neural Network analysis: SEG Expanded Abstracts, 1198-1201.
Wilson, A.C. 1993, Geology of the Kabinakagami Lake greenstone belt: Ontario Geological Survey, Open File Report 5787, 80 pp.
Witherly, K., R. Irvine, and E. B. Morrison, 2004, The Geotech VTEM time domain electromagnetic system: 74th Annual International Meeting, SEG, Expanded Abstracts, 1217–1221.

/content/journals/10.1080/22020586.2019.12072983

Article Type: Research Article

Keyword(s): Targeting

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 Mineralisation predictive targeting using TensorFlow (Google) deep neural networks

Abstract

Most Read This Month

Most Cited This Month Most Cited RSS feed