1887
Volume 72, Issue 9
  • E-ISSN: 1365-2478
PDF

Abstract

Abstract

We apply a machine learning approach to automatically infer two key attributes – the location of fault or shear zone structures and the thickness of the overburden – in an 18 km2 study area within and surrounding the Archean Fenelon gold deposit in Quebec, Canada. Our approach involves the inversion of carefully curated borehole lithological and structural observations truncated at 480 m below the surface, combined with magnetic and Light Detection and Ranging survey data. We take a computationally low‐cost approach in which no underlying model for geological consistency is imposed. We investigated three contrasting approaches: (1) an inferred fault model, in which the borehole observations represent a direct evaluation of the presence of fault or shear zones; (2) an inferred overburden model, using borehole observations on the overburden‐bedrock contact; (3) a model with three classes – overburden, faulted bedrock and unfaulted bedrock, which combines aspects of (1) and (2). In every case, we applied all 32 standard machine learning algorithms. We found that Bagged Trees, fine ‐nearest neighbours and weighted ‐nearest neighbour were the most successful, producing similar accuracy, sensitivity and specificity metrics. The Bagged Trees algorithm predicted fault locations with approximately 80% accuracy, 70% sensitivity and 73% specificity. Overburden thickness was predicted with 99% accuracy, 77% sensitivity and 93% specificity. Qualitatively, fault location predictions compared well to independently construct geological interpretations. Similar methods might be applicable in other areas with good borehole coverage, providing that criteria used in borehole logging are closely followed in devising classifications for the machine learning training set and might be usefully supplemented with a variety of geophysical survey data types.

© 2024 European Association of Geoscientists & Engineers. © 2024 The Author(s). Geophysical Prospecting published by John Wiley & Sons Ltd on behalf of European Association of Geoscientists & Engineers.
Loading

Article metrics loading...

/content/journals/10.1111/1365-2478.13589
2024-10-11
2026-02-15

  • From This Site

    /content/journals/10.1111/1365-2478.13589
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

/deliver/fulltext/gpr/72/9/gpr13589.html?itemId=/content/journals/10.1111/1365-2478.13589&mimeType=html&fmt=ahah

References

  1. Alary, C. & Demougeot‐Renard, H. (2010) Factorial kriging analysis as a tool for explaining the complex spatial distribution of metals in sediments. Environmental Science & Technology, 44, 593–599. Available from: https://doi.org/10.1021/es9022305
     [Google Scholar]
  2. Bateman, R., Ayer, J.A. & Dubé, B. (2008) The Timmins‐Porcupine gold camp, Ontario: anatomy of an Archean greenstone belt and ontogeny of gold mineralization. Economic Geology, 103, 1285–1308. Available from: https://doi.org/10.2113/gsecongeo.103.6.1285
     [Google Scholar]
  3. Bedeaux, P., Pilote, P., Daigneault, R. & Rafini, S. (2016) Synthesis of the structural evolution and associated gold mineralization of the Cadillac Fault, Abitibi, Canada. Ore Geology Reviews, 82, 49–69. Available from: https://doi.org/10.1016/j.oregeorev.2016.11.029
     [Google Scholar]
  4. Bellefleur, G., Cheraghi, S. & Malehmir, A. (2019) Reprocessing legacy three‐dimensional seismic data from the Halfmile Lake and Brunswick no. 6 volcanogenic massive sulphide deposits, New Brunswick, Canada. Canadian Journal of Earth Sciences, 56, 569–583. Available from: https://doi.org/10.1139/cjes‐2018‐0103
     [Google Scholar]
  5. Bemis, S.P., Micklethwaite, S., Turner, D., James, M.R., Akciz, S., Thiele, S.T. et al. (2014) Ground‐based and UAV‐based photogrammetry: a multi‐scale, high‐resolution mapping tool for structural geology and paleoseismology. Journal of Structural Geology, 69, 163–178. Available from: https://doi.org/10.1016/j.jsg.2014.10.007
     [Google Scholar]
  6. Bleeker, W. (2015) Synorogenic gold mineralization in granite‐greenstone terranes: the deep connection between extension, major faults, synorogenic clastic basins, magmatism, thrust inversion, and long‐term preservation. Targeted Geoscience Initiative: Contributions to the Understanding of Precambrian Lode Gold Deposits and Implications for Exploration, 4, 25–47. Available from: https://doi.org/10.4095/296626
     [Google Scholar]
  7. Bording, T.S., Asif, M.R., Barfod, A.S., Larsen, J.J., Zhang, B., Grombacher, D.J. et al. (2021) Machine learning based fast forward modelling of ground‐based time‐domain electromagnetic data. Journal of Applied Geophysics, 187, 104290. Available from: https://doi.org/10.1016/j.jappgeo.2021.104290
     [Google Scholar]
  8. Brazell, S., Bayeh, A., Ashby, M. & Burton, D. (2019) A machine‐learning‐based approach to assistive well‐log correlation. Petrophysics—The SPWLA Journal of Formation Evaluation and Reservoir Description, 60, 469–479. Available from: https://doi.org/10.30632/PJV60N4‐2019a1
     [Google Scholar]
  9. Bressan, T.S., Kehl De Souza, M., Girelli, T.J. & Junior, F.C. (2020) Evaluation of machine learning methods for lithology classification using geophysical data. Computers & Geosciences, 139, 104475. Available from: https://doi.org/10.1016/j.cageo.2020.104475
     [Google Scholar]
  10. Carter, J., Gregory, D. & Genna, D. (2022) Pyrite trace element chemistry of the Fenelon Gold deposit, Québec. Master of Science, Toronto: University of Toronto.
  11. Castonguay, S., Dubé, B., Wodicka, N. & Mercier‐Langevin, P. (2020) Geological setting and gold mineralization associated with the Sunday Lake and Lower Detour deformation zones, northwestern Abitibi greenstone belt, Ontario and Quebec. Geological Survey of Canada. Report number: Open file 8712. Available from: https://doi.org/10.4095/323670
  12. Chukwu, C., Betts, P., Moore, D., Munukutla, R., Armit, R., Mclean, M. et al. (2024) Unsupervised machine learning and depth clusters of Euler deconvolution of magnetic data: a new approach to imaging geological structures. Exploration Geophysics, 55, 1–23. Available from: https://doi.org/10.1080/08123985.2023.2299475
     [Google Scholar]
  13. Côrte, G., Dramsch, J., Amini, H. & Macbeth, C. (2020) Deep neural network application for 4D seismic inversion to changes in pressure and saturation: optimizing the use of synthetic training datasets. Geophysical Prospecting, 68, 2164–2185. Available from: https://doi.org/10.1111/1365‐2478.12982
     [Google Scholar]
  14. Cowan, E.J. (2020) Deposit‐scale structural architecture of the Sigma‐Lamaque gold deposit, Canada—insights from a newly proposed 3D method for assessing structural controls from drill hole data. Mineralium Deposita, 55, 217–240. Available from: https://doi.org/10.1007/s00126‐019‐00949‐6
     [Google Scholar]
  15. Cracknell, M.J. & Reading, A.M. (2014) Geological mapping using remote sensing data: a comparison of five machine learning algorithms, their response to variations in the spatial distribution of training data and the use of explicit spatial information. Computers & Geosciences, 63, 22–33. Available from: https://doi.org/10.1016/j.cageo.2013.10.008
     [Google Scholar]
  16. Daigneault, R., Mueller, W. & Chown, E. (2002) Oblique Archean subduction: accretion and exhumation of an oceanic arc during dextral transpression, Southern Volcanic Zone, Abitibi Subprovince Canada. Precambrian Research, 115, 261–290. Available from: https://doi.org/10.1016/S0301‐9268(02)00012‐8
     [Google Scholar]
  17. Daigneault, R., Mueller, W. & Chown, E. (2004) Abitibi greenstone belt plate tectonics: the diachronous history of arc development, accretion and collision. Developments in Precambrian Geology, 12, 88–103. Available from: https://doi.org/10.1130/0091‐7613(1995)023<0471:FOTAGB>2.3.CO;2
     [Google Scholar]
  18. Dentith, M.C. & Mudge, S. (2014) Geophysics for the mineral exploration geoscientist. Cambridge: Cambridge University Press. Available from: https://doi.org/10.1017/CBO9781139024358
     [Google Scholar]
  19. Dubé, B., Mercier‐Langervin, P. & Castonguay, S. (2015) Precambrian lode gold deposits—a summary of TGI‐4 contributions to the understanding of lode gold deposits, with an emphasis on implications for exploration. Geological Survey of Canada. Report number: Open File 7852. Available from: https://doi.org/10.4095/296624
  20. Dubosq, R., Schneider, D.A., Camacho, A. & Lawley, C.J.M. (2019) Geochemical and geochronological discrimination of biotite types at the Detour Lake gold deposit, Canada. Minerals, 9, 596. Available from: https://doi.org/10.3390/min9100596
     [Google Scholar]
  21. Dumakor‐Dupey, N.K. & Arya, S. (2021) Machine learning—a review of applications in mineral resource estimation. Energies, 14, 4079. Available from: https://doi.org/10.17159/2411‐9717/1250/2022
     [Google Scholar]
  22. Guo, J., Li, Y., Jessell, M.W., Giraud, J., Li, C., Wu, L., Li, F. & Liu, S. (2021) 3D geological structure inversion from Noddy‐generated magnetic data using deep learning methods. Computers & Geosciences, 149, 104701. Available from: https://doi.org/10.1016/j.cageo.2021.104701
     [Google Scholar]
  23. Haest, M., Cudahy, T., Laukamp, C. & Gregory, S. (2012a) Quantitative mineralogy from infrared spectroscopic data. I. Validation of mineral abundance and composition scripts at the Rocklea channel iron deposit in Western Australia. Economic Geology, 107, 209–228. Available from: https://doi.org/10.2113/econgeo.107.2.209
     [Google Scholar]
  24. Haest, M., Cudahy, T., Laukamp, C. & Gregory, S. (2012b) Quantitative mineralogy from infrared spectroscopic data. II. Three‐dimensional mineralogical characterization of the Rocklea channel iron deposit, Western Australia. Economic Geology, 107, 229–249. Available from: https://doi.org/10.2113/econgeo.107.2.229
     [Google Scholar]
  25. Holden, E.‐J., Fu, S.C., Kovesi, P., Dentith, M., Bourne, B. & Hope, M. (2011) Automatic identification of responses from porphyry intrusive systems within magnetic data using image analysis. Journal of Applied Geophysics, 74, 255–262. Available from: https://doi.org/10.1016/j.jappgeo.2011.06.016
     [Google Scholar]
  26. Holden, E.‐J., Wong, J., Kovesi, P., Wedge, D., Dentith, M. & Bagas, L. (2012) Identifying structural complexity in aeromagnetic data: an image analysis approach to greenfields gold exploration. Ore Geology Reviews, 46, 47–59. Available from: https://doi.org/10.1016/j.oregeorev.2011.11.002
     [Google Scholar]
  27. Howarth, R. (2017) Dictionary of mathematical geosciences: with historical notes. Cham: Springer. Available from: https://doi.org/10.1007/978‐3‐319‐57315‐1
     [Google Scholar]
  28. Hufford, G. (2015) Tectono‐hydrothermal evolution of the Neoarchean Abitibi greenstone belt, Canada. Master of Science, Geology, Colorado School of Mines. Available from: https://doi.org/10.13140/RG.2.2.16770.27844
  29. Ispolatov, V., Lafrance, B., Dube, B. & Creaser, R. (2008) Geologic and structural setting of gold mineralization in the Kirkland Lake‐Larder Lake gold belt, Ontario. Economic Geology, 103, 1309–1340. Available from: https://doi.org/10.2113/gsecongeo.103.6.1309
     [Google Scholar]
  30. Joshi, D., Patidar, A.K., Mishra, A., Mishra, A., Agarwal, S., Pandey, A. et al. (2023) Prediction of sonic log and correlation of lithology by comparing geophysical well log data using machine learning principles. GeoJournal, 88, 47–68. Available from: https://doi.org/10.1007/s10708‐021‐10502‐6
     [Google Scholar]
  31. Kaur, H., Zhang, Q., Witte, P., Liang, L., Wu, L. & Fomel, S. (2023) Deep‐learning‐based 3D fault detection for carbon capture and storage. Geophysics, 88, IM101–IM112. Available from: https://doi.org/10.1190/geo2022‐0755.1
     [Google Scholar]
  32. Khadse, C., Patharkar, A.A. & Chaudhari, B.S. (2021) Electromagnetic field and artificial intelligence based fault detection and classification system for the transmission lines in smart grid. Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, 1–15. Available from: https://doi.org/10.1080/15567036.2021.1948637
     [Google Scholar]
  33. Leclerc, A. & Giguère, E. (2010) Fénelon township—province of Québec, Canada. Balmoral Resources Ltd. Technical report on Fenelon property.
     [Google Scholar]
  34. Loh, W.‐Y. & Shih, Y.‐S. (1997) Split selection methods for classification trees. Statistica Sinica, 7, 815–840.
     [Google Scholar]
  35. Lorentzen, M., Bredesen, K., Gregersen, U., Smit, F. & Laghari, S. (2022) Fault mapping of the Gassum Formation reservoir and the Fjerritslev Formation caprock interval at the Stenlille gas storage site using a pre‐trained convolutional neural network. Proceedings of the 16th Greenhouse Gas Control Technologies Conference (GHGT‐16) 23‐24 Oct 2022, 12. Available at SSRN: https://doi.org/10.2139/ssrn.4277405
  36. Mamuya, Y.D., Lee, Y.‐D., Shen, J.‐W., Shafiullah, M. & Kuo, C.‐C. (2020) Application of machine learning for fault classification and location in a radial distribution grid. Applied Sciences, 10, 4965. Available from: https://doi.org/10.3390/app10144965
     [Google Scholar]
  37. Markovic, M., Malehmir, R. & Malehmir, A. (2022) Diffraction pattern recognition using deep semantic segmentation. Near Surface Geophysics, 20, 507–518. Available from: https://doi.org/10.1002/nsg.12227
     [Google Scholar]
  38. Markovic, M., Malehmir, R. & Malehmir, A. (2023) Diffraction denoising using self‐supervised learning. Geophysical Prospecting, 71, 1215–1225. Available from: https://doi.org/10.1111/1365‐2478.13340
     [Google Scholar]
  39. Mathworks . (2022) Statistics and machine learning toolbox™ user's guide. Natick, MA, United States: The MathWorks Inc.
     [Google Scholar]
  40. Mercier‐Langevin, P. & Dube, B. (2017) Archean base and precious metal deposits, southern Abitibi greenstone belt, Canada. Reviews in Economic Geology, 19, 1–5. Available from: https://doi.org/10.5382/Rev.19
     [Google Scholar]
  41. Merghadi, A., Yunus, A.P., Dou, J., Whiteley, J., Thaipham, B., Bui, D.T. et al. (2020) Machine learning methods for landslide susceptibility studies: a comparative overview of algorithm performance. Earth‐Science Reviews, 207, 103225. Available from: https://doi.org/10.1016/j.earscirev.2020.103225
     [Google Scholar]
  42. Meyer, H., Reudenbach, C. & Nauss, T. (2019) Spatial autocorrelation in geoscientific machine learning applications: moving from data reproduction to spatial prediction. In: 21st EGU General Assembly, EGU2019, Proceedings from the conference held 7–12 April, 2019 in Vienna, Austria, id.1621. Munich, Germany, EGU. pp. 1–11. Available from: https://doi.org/10.1016/j.ecolmodel.2019.108815
  43. Ministry of Natural Resources and Forests . (2023) LiDAR—digital models (terrain, canopy, slope). In: Québec, D. (Ed.) Ministry of Natural Resources and Forests. Available from: https://www.donneesquebec.ca/recherche/dataset/produits-derives-de-base-du-lidar
     [Google Scholar]
  44. Mohamed, I.M., Mohamed, S., Mazher, I. & Chester, P. (2019) Formation lithology classification: insights into machine learning methods. In: SPE annual technical conference and exhibition. Dallas, TX, SPE. pp. D021S033R005. Available from: https://doi.org/10.2118/196096‐ms
  45. Monecke, T., Mercier‐Langevin, P., Dubé, B., Frieman, B.M., Monecke, T., Mercier‐Langevin, P. & Dubé, B. (2017) Geology of the Abitibi greenstone belt. In: Archean base and precious metal deposits, southern Abitibi greenstone belt, Canada. Houston, TX: Society of Economic Geologists. pp. 7–50. Available from: https://doi.org/10.5382/Rev.19.01
     [Google Scholar]
  46. Muehlmann, C., Nordhausen, K. & Yi, M. (2021) On cokriging, neural networks, and spatial blind source separation for multivariate spatial prediction. IEEE Geoscience and Remote Sensing Letters, 18, 1931–1935. Available from: https://doi.org/10.1109/LGRS.2020.3011549
     [Google Scholar]
  47. Oliver, J., Yer, J.A., Dubé, B., Aubertin, R., Burson, M., Panneton, G., Friedman, R. & Hamilton, M. (2012) Structure, stratigraphy, U‐Pb geochronology and alteration characteristics of gold mineralization at the detour lake gold deposit, Ontario, Canada. Exploration and Mining Geology, 20, 1–30.
     [Google Scholar]
  48. Othniel, K.L. (2014) Exploring and using the magnetic methods. In: Maged, M. (Ed.) Advanced geoscience remote sensing. Rijeka: IntechOpen. Available from: https://doi.org/10.5772/57163
     [Google Scholar]
  49. Parvar, K. (Ed.) (2020) UAV Aeromagnetic survey logistics report. Ottawa: Pioneer Exploration Consultants Ltd.
     [Google Scholar]
  50. Pelletier, C., Nadeau‐Benoit, V., Boudreau, S. & Beauvais, M.R. (2023) NI 43‐101 technical report for the Detour‐Fenelon gold trend property, Quebec, Canada. Val‐d'Or: InnovExplo Inc.
     [Google Scholar]
  51. Perrouty, S., Gaillard, N., Piette‐Lauzière, N., Mir, R., Bardoux, M., Olivo, G.R. et al. (2017) Structural setting for Canadian Malartic style of gold mineralization in the Pontiac Subprovince, south of the Cadillac Larder Lake deformation zone, Québec, Canada. Ore Geology Reviews, 84, 185–201. Available from: https://doi.org/10.1016/j.oregeorev.2017.01.009
     [Google Scholar]
  52. Phillips, N. (2022) Formation of gold deposits. Singapore: Springer Nature Singapore.
     [Google Scholar]
  53. Rowbotham, P., Kane, P. & Bentley, M. (2010) Bias in geophysical interpretation–the case for multiple deterministic scenarios. The Leading Edge, 29, 590–595. Available from: https://doi.org/10.1190/1.3422459
     [Google Scholar]
  54. Zhdanov, M.S. (2018) Marine electromagnetic methods. In: Foundations of geophysical electromagnetic theory and methods, 2nd edition, Amsterdam, The Netherlands: Elsevier. pp. 625–662. Available from: https://doi.org/10.1016/B978‐0‐44‐463890‐8.00019‐0
     [Google Scholar]
  55. Salem, A. & Ravat, D. (2003) A combined analytic signal and Euler method (AN‐EUL) for automatic interpretation of magnetic data. Geophysics, 68, 1952–1961. Available from: https://doi.org/10.1190/1.1635049
     [Google Scholar]
  56. Sammut, C. & Webb, G.I. (2011) Encyclopedia of machine learning. New York: Springer Publishing Company, Incorporated. Available from: https://doi.org/10.1007/978‐0‐387‐30164‐8
     [Google Scholar]
  57. Setiadi, I., Marjiyono & Nainggolan, T.B. (2021) Gravity data analysis based on optimum upward continuation filter and 3D inverse modelling (case study at sedimentary basin in Volcanic Region Malang and its surrounding area, East Java). IOP Conference Series: Earth and Environmental Science, 873, 012008. Available from: https://doi.org/10.1088/1755‐1315/873/1/012008
     [Google Scholar]
  58. Smith, S., Zimina, O., Manral, S. & Nickel, M. (2022) Machine‐learning assisted interpretation: integrated fault prediction and extraction case study from the Groningen gas field, Netherlands. Interpretation, 10, SC17–SC30. Available from: https://doi.org/10.1190/int‐2021‐0137.1
     [Google Scholar]
  59. Szatmári, G., Pásztor, L. & Heuvelink, G.B.M. (2021) Estimating soil organic carbon stock change at multiple scales using machine learning and multivariate geostatistics. Geoderma, 403, 115356. Available from: https://doi.org/10.1016/j.geoderma.2021.115356
     [Google Scholar]
  60. Teixeira, C.D., Chemale, F. & Giannoccaro Von Huelsen, M. (2021) Integrated geophysics analysis of crustal structure in the NE Pirapora Aulacogen, Brazil. Journal of South American Earth Sciences, 112, 103585. Available from: https://doi.org/10.1016/j.jsames.2021.103585
     [Google Scholar]
  61. Terry, N., Johnson, C.D., Day‐Lewis, F.D., Parker, B. & Slater, L. (2021) Beware of spatial autocorrelation when applying machine learning algorithms to borehole geophysical logs. Groundwater, 59, 315–319. Available from: https://doi.org/10.1111/gwat.13081
     [Google Scholar]
  62. Thurston, P.C., Ayer, J.A., Goutier, J. & Hamilton, M.A. (2008) Depositional gaps in Abitibi greenstone belt stratigraphy: a key to exploration for syngenetic mineralization. Economic Geology, 103, 1097–1134. Available from: https://doi.org/10.2113/gsecongeo.103.6.1097
     [Google Scholar]
  63. Trott, M., Mooney, C., Azad, S., Sattarzadeh, S., Bluemel, B., Leybourne, M. & Layton‐Matthews, D. (2023) Alteration assemblage characterization using machine learning applied to high‐resolution drill‐core images, hyperspectral data and geochemistry. Geochemistry: Exploration, Environment, Analysis, 23, geochem2023–2032. Available from: https://doi.org/10.1144/geochem2023‐032
     [Google Scholar]
  64. Venter, N., Mokubung, K., Eadie, T., Plastow, G. & Mathew, L. (2014) GL140257—report on airborne geophysical survey for Balmoral Resources Ltd. Aurora: Geotech Ltd.
     [Google Scholar]
  65. Wilkinson, L., Cruden, A. & Krogh, T. (2011) Timing and kinematics of post‐Timiskaming deformation within the Larder Lake‐Cadillac deformation zone, southwest Abitibi greenstone belt, Ontario, Canada. Canadian Journal of Earth Sciences, 36, 627–647. Available from: https://doi.org/10.1139/cjes‐36‐4‐627
     [Google Scholar]
  66. Xu, L. & Green, E.C.R. (2023) Inferring geological structural features from geophysical and geological mapping data using machine learning algorithms. Geophysical Prospecting, 71, 1728–1742. Available from: https://doi.org/10.1111/1365‐2478.13371
     [Google Scholar]
  67. Yahyaoui, A., Yahyaoui, I. & Yumuşak, N. (2018) Machine learning techniques for data classification. In: Yahyaoui, I. (Ed.) Advances in renewable energies and power technologies. Amsterdam, The Netherlands: Elsevier. Available from: https://doi.org/10.1016/B978‐0‐12‐813185‐5.00009‐7
     [Google Scholar]
  68. Zhang, C., Frogner, C., Araya‐Polo, M. & Hohl, D. (2014) Machine‐learning based automated fault detection in seismic traces. 76th EAGE Conference and Exhibition 2014. Utrecht, The Netherlands, European Association of Geoscientists & Engineers. pp. 1–5. Available from: https://doi.org/10.3997/2214‐4609.20141500
/content/journals/10.1111/1365-2478.13589
Loading
Inferring fault structures and overburden depth in 3D from geophysical data using machine learning algorithms – A case study on the Fenelon gold deposit, Quebec, Canada
Geophysical Prospecting 72, 3474 (2024); https://doi.org/10.1111/1365-2478.13589
/content/journals/10.1111/1365-2478.13589
/content/journals/10.1111/1365-2478.13589
Loading

Data & Media loading...

  • Article Type: Research Article
Keyword(s): data processing; interpretation; magnetics; modelling; signal processing

Most Cited This Month Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error