Data-driven Mineral Prospectivity Mapping by Joint Application of Unsupervised Convolutional Auto-encoder Network and Supervised Convolutional Neural Network

Abstract

The excellent performance of convolutional neural network (CNN) and its variants in image classification makes it a potential perfect candidate for dealing with multi-geoinformation involving abundant spatial information. In this paper, we tested, for data-driven mineral prospectivity mapping, the efficacy of using unsupervised convolutional auto-encoder network (CAE) to support CNN modeling for synthesis of multi-geoinformation. First, two simple unsupervised CAE networks were constructed to distinguish patches of tif image (i.e., nine predictive evidence maps forming a tif-format image) with nine channels that have high reconstructed errors, which represent prospective areas (i.e., mineralized). Then, the patches of tif image with the lowest reconstructed errors were regarded as background (or non-prospective areas). We varied the CAE network architecture and training epochs and combinations of evidence maps for trials to obtain reliable results. Then, the AUC, or area under the receiver operating characteristic curve, was used to demonstrate empirically that high reconstructed errors are representative of spatial signatures of prospective areas. The proposed coherent spatial signatures, namely patches of a tif image with the highest reconstructed errors and the lowest reconstructed errors representing prospective and non-prospective areas, respectively, were used in the subsequent CNN modeling. The results of CNN modeling using training data derived from CAE exhibited strong spatial correlation with known Au deposits in the study area. The training loss and accuracy of the CNN modeling together with resulting favorability map that were comparable with results from previous study proved the plausibility of the proposed methodology, and therefore, the practice of extracting coherent spatial signatures of prospective and non-prospective areas in unsupervised manner using CAE network and then using these coherent spatial signatures in supervised learning with CNN is a new potential approach for mineral prospectivity mapping.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

References

  1. Agterberg, F. P., & Bonham-Carter, G. F. (2005). Measuring the performance of mineral-potential maps. Natural Resources Research, 14(1), 1–17.

    Article  Google Scholar 

  2. Agterberg, F. P., & Cheng, Q. (2002). Conditional independence test for weights-of-evidence modeling. Natural Resources Research, 11(4), 249–255.

    Article  Google Scholar 

  3. Agterberg, F. P., Bonham-Carter, G. F., Cheng, Q. M., & Wright, D. F. (1993). Weights of evidence modeling and weighted logistic regression for mineral potential mapping. Computers in geology, 25, 13–32.

    Google Scholar 

  4. Arel, I., Rose, D. C., & Karnowski, T. P. (2010). Deep machine learning - a new frontier in artificial intelligence research [research frontier]. Computational Intelligence Magazine IEEE, 5(4), 13–18.

    Article  Google Scholar 

  5. Bradley, A. P. (1997). The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern recognition, 30(7), 1145–1159.

    Article  Google Scholar 

  6. Breslow, N. E., & Cain, K. C. (1988). Logistic regression for two-stage case-control data. Biometrika, 75(1), 11–20.

    Article  Google Scholar 

  7. Carranza, E. J. M. (2004). Weights of evidence modeling of mineral potential, a case study using small number of prospects, Abra. Philippines. Natural Resources Research, 13(3), 173–187.

    Article  Google Scholar 

  8. Carranza, E. J. M. (2008). Geochemical anomaly and mineral prospectivity mapping in GIS. Newyork: Elsevier.

    Google Scholar 

  9. Carranza, E. J. M., & Hale, M. (2001a). Geologically constrained fuzzy mapping of gold mineralization potential, Baguio district. Philippines. Natural Resources Research, 10(2), 125–136.

    Article  Google Scholar 

  10. Carranza, E. J. M., & Hale, M. (2001b). Logistic regression for geologically constrained mapping of gold potential, Baguio district. Philippines. Exploration and Mining Geology, 10(3), 165–175.

    Article  Google Scholar 

  11. Carranza, E. J. M., & Hale, M. (2003). Evidential belief functions for data-driven geologically constrained mapping of gold potential, Baguio district. Philippines. Ore Geology Reviews, 22(1–2), 117–132.

    Article  Google Scholar 

  12. Carranza, E. J. M., & Laborte, A. G. (2015a). Data-driven predictive mapping of gold prospectivity, Baguio district, Philippines, application of random forests algorithm. Ore Geology Reviews, 71, 777–787.

    Article  Google Scholar 

  13. Carranza, E. J. M., & Laborte, A. G. (2015b). Data-driven predictive modeling of mineral prospectivity using random forests, a case study in Catanduanes Island (Philippines). Natural Resources Research, 25(1), 1–16.

    Google Scholar 

  14. Carranza, E. J. M., & Laborte, A. G. (2015c). Random forest predictive modeling of mineral prospectivity with small number of prospects and data with missing values in Abra (Philippines). Computers & Geosciences, 74, 60–70.

    Article  Google Scholar 

  15. Carranza, E. J. M., Hale, M., & Faassen, C. (2008). Selection of coherent deposit-type locations and their application in data-driven mineral prospectivity mapping. Ore Geology Reviews, 33(3–4), 536–558.

    Article  Google Scholar 

  16. Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE, synthetic minority over-sampling technique. Journal of artificial intelligence research, 16, 321–357.

    Article  Google Scholar 

  17. Chawla, N. V., Japkowicz, N., & Kotcz, A. (2004). Special issue on learning from imbalanced data sets. ACM SIGKDD explorations newsletter, 6(1), 1–6.

    Article  Google Scholar 

  18. Chen, M., Shi, X., Zhang, Y., Wu, D., & Guizani, M. (2017a). Deep features learning for medical image analysis with convolutional autoencoder neural network. IEEE Transactions on Big Data. https://doi.org/10.1109/TBDATA.2017.2717439.

    Article  Google Scholar 

  19. Chen, T., Xu, R., He, Y., & Wang, X. (2017b). Improving sentiment analysis via sentence type classification using BiLSTM-CRF and CNN. Expert Systems with Applications, 72, 221–230.

    Article  Google Scholar 

  20. Chen, Y., & Y., & Gong, Q, S. . (2007). Discussion on the division of deposit scale and the index of ore prospecting. GANSU GEOLOGY, 16(3), 6–11. ((In Chinese)).

    Google Scholar 

  21. Chen, Y. (2015). Mineral potential mapping with a restricted Boltzmann machine. Ore Geology Reviews, 71, 749–760.

    Article  Google Scholar 

  22. Chen, Y., & Wu, W. (2017). Mapping mineral prospectivity using an extreme learning machine regression. Ore Geology Reviews, 80, 200–213.

    Article  Google Scholar 

  23. Chung, C. J., & Keating, P. B. (2002). Mineral potential evaluation based on airborne geophysical data. Exploration Geophysics, 33(1), 28–34.

    Article  Google Scholar 

  24. Domingos, P. (1999). A general method for making classifiers cost-sensitive (pp. 1049–1001). Instituto Superior Técnico, Lisboa: Artificial Intelligence Group.

    Google Scholar 

  25. Dong, Y., Liu, X., Zhang, G., Chen, Q., Zhang, X., Li, W., et al. (2012). Triassic diorites and granitoids in the Foping area, constraints on the conversion from subduction to collision in the Qinling orogen, China. Journal of Asian Earth Sciences, 47, 123–142.

    Article  Google Scholar 

  26. Elkan, C. (2001). The foundations of cost-sensitive learning. Paper presented at the International joint conference on artificial intelligence.

  27. Fatehi, M., & Asadi, H. H. (2017). Data integration modeling applied to drill hole planning through semi-supervised learning, a case study from the Dalli Cu-Au porphyry deposit in the central Iran. Journal of African Earth Sciences, 128, 147–160.

    Article  Google Scholar 

  28. Granek, J. (2016). Application of machine learning algorithms to mineral prospectivity mapping. PhD thesis, University of British Columbia, URL,https,//open.library.ubc.ca/media/stream/pdf/24/21.0340340/0340344.

  29. Hronsky, J. M., & Kreuzer, O. P. (2019). Applying spatial prospectivity mapping to exploration targeting, fundamental practical issues and suggested solutions for the future. Ore Geology Reviews, 107, 647–653.

    Article  Google Scholar 

  30. Ioffe, S., & Szegedy, C. (2015). Batch normalization, accelerating deep network training by reducing internal covariate shift. International Conference on International Conference on Machine Learning. JMLR.org.

  31. Jiang, L., Li, C., Cai, Z., & Zhang, H. (2013). Sampled Bayesian network classifiers for class-imbalance and cost-sensitive learning. Paper presented at the 2013 IEEE 25th International Conference on Tools with Artificial Intelligence.

  32. Jin, W. J., Zhang, Q., He, D. F., & Jia, X. Q. (2005). SHRIMP dating of adakites in western Qinling and their implications. Acta Petrol. Sin., 21, 959–966. ((In Chinese with English abstract)).

    Google Scholar 

  33. Jin, X. Y., Li, J. W., Hofstra, A. H., & Sui, J. X. (2016). Magmatic-hydrothermal origin of the early Triassic laodou lode gold deposit in the Xiahe-Hezuo district, West Qinling orogen, china: implications for gold metallogeny. Mineralium Deposita, 52(6), 883–902.

    Article  Google Scholar 

  34. Joly, A., Porwal, A., McCuaig, T. C., Chudasama, B., Dentith, M. C., & Aitken, A. R. A. (2015). Mineral systems approach applied to GIS-based 2D-prospectivity modelling of geological regions, Insights from Western Australia. Ore Geology Reviews, 71, 673–702.

    Article  Google Scholar 

  35. Lecun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444.

    Article  Google Scholar 

  36. Lecun, Y., Boser, B. E., Denker, J. S., Henderson, D., & Jackel, L. D. (1990). Handwritten digit recognition with a back-propagation network. Advances in neural information processing systems, 2, 396–404.

    Google Scholar 

  37. Leite, E. P., & Filho, C. R. D. S. (2009). Probabilistic neural networks applied to mineral potential mapping for platinum group elements in the Serra Leste region, Carajás Mineral Province. Brazil. Computers & Geosciences, 35(3), 675–687.

    Article  Google Scholar 

  38. Li, J. W., Sui, J. X., Jin, X. Y., Wen, G., Chang, J., Zhu, R., et al. (2019a). The intrusion-related gold deposits in the Xiahe-Hezuo district, West Qinling Orogen, Geodynamic setting and exploration potential. Earth Science Frontiers, 26(5), 017–032. ((In Chinese with English abstract)).

    Google Scholar 

  39. Li, H., Li, X., Yuan, F., Jowitt, S. M., Zhang, M., Zhou, J., & Wu, B. (2020a). Convolutional neural network and transfer learning based mineral prospectivity modeling for geochemical exploration of Au mineralization within the Guandian-Zhangbaling area, Anhui Province. China. Applied Geochemistry, 122, 104747.

    Article  Google Scholar 

  40. Li, J., Sui, J., Jin, X., Wen, G., & Chang, J. (2014). A magmatic related gold system in the Xiahe-Hezuo district, Western Qinling Orogen. China. Acta Geologica Sinica-English Edition, 88(s2), 751–752.

    Article  Google Scholar 

  41. Li, J., Yuan, Z. H., Li, Z., Ren, A., Ding, C. W., Draper, J., et al. (2019b). Normalization and dropout for stochastic computing-based deep convolutional neural networks. Integration-the Vlsi Journal, 65, 395–403.

    Article  Google Scholar 

  42. Li, T., Zuo, R., Xiong, Y., & Peng, Y. (2020b). Random-drop data augmentation of deep convolutional neural network for mineral prospectivity mapping. Natural Resources Research. https://doi.org/10.1007/s11053-020-09742-z.

    Article  Google Scholar 

  43. Li, X. W., Mo, X. X., Yu, X. H., Ding, Y., Huang, X. F., Wei, P., et al. (2013). Petrology and geochemistry of the early Mesozoic pyroxene andesites in the Maixiu Area, West Qinling, China, Products of subduction or syn-collision? Lithos, 172, 158–174.

    Article  Google Scholar 

  44. Lin, M., Chen, Q., &Yan, S. (2013). Network in network. arXiv preprint arXiv:1312.4400.

  45. Lindsay, M., Aitken, A., Ford, A., Dentith, M., Hollis, J., & Tyler, I. (2016). Reducing subjectivity in multi-commodity mineral prospectivity analyses, Modelling the west Kimberley, Australia. Ore Geology Reviews, 76, 395–413.

    Article  Google Scholar 

  46. Liu, Y., Zhou, K., Zhang, N., & Wang, J. (2018). Maximum entropy modeling for orogenic gold prospectivity mapping in the Tangbale-Hatu belt, western Junggar, China. Ore Geology Reviews, 100, 133–147.

    Article  Google Scholar 

  47. Lu, X., Zheng, X., & Yuan, Y. (2017). Remote sensing scene classification by unsupervised representation learning. IEEE Transactions on Geoscience and Remote Sensing, 9(55), 5148–5157.

    Article  Google Scholar 

  48. Lu, Z. Y., Nicklaw, C., Fleetwood, D., Schrimpf, R., & Pantelides, S. (2003). Erratum, structure, properties, and dynamics of oxygen vacancies in amorphous SiO2. Physical Review Letters, 91(3), 039901.

    Article  Google Scholar 

  49. Luo, B., Zhang, H., & Lü, X. (2012a). U-Pb zircon dating, geochemical and Sr–Nd–Hf isotopic compositions of early Indosinian intrusive rocks in west qinling, central china, petrogenesis and tectonic implications. Contributions to Mineralogy & Petrology, 164(4), 551–569.

    Article  Google Scholar 

  50. Luo, B. J., Zhang, H. F., & Xiao, Z. Q. (2012b). Petrogenesis and tectonic implications of the Early Indosinian Meiwu pluton in west Qinling, central China. Earth Science Frontiers, 19, 199–213.

    Google Scholar 

  51. Marmanis, D., Datcu, M., Esch, T., & Stilla, U. (2016). Deep learning earth observation classification using imagenet pretrained networks. IEEE Geoscience and Remote Sensing Letters, 13(1), 105–109.

    Article  Google Scholar 

  52. Moeini, H., & Torab, F. M. (2017). Comparing compositional multivariate outliers with autoencoder networks in anomaly detection at Hamich exploration area, east of Iran. Journal of Geochemical Exploration, 180, 15–23.

    Article  Google Scholar 

  53. Ngiam, J., Chen, Z., Chia, D., Koh, P. W., Le, Q. V., & Ng, A. Y. (2010). Tiled convolutional neural networks. Advances in neural information processing systems, 23, 1279–1287.

    Google Scholar 

  54. Nielsen, M. A. (2015). Neural networks and deep learning. Determination Press.

  55. Occhipinti, S. A., Metelka, V., Lindsay, M. D., Hollis, J. A., Aitken, A. R., Tyler, I. M., & McCuaig, T. C. (2016). Multicommodity mineral systems analysis highlighting mineral prospectivity in the Halls Creek Orogen. Ore Geology Reviews, 72, 86–113.

    Article  Google Scholar 

  56. Prado, E. M. G., de Souza Filho, C. R., Carranza, E. J. M., & Motta, J. G. (2020). Modeling of Cu-Au prospectivity in the carajás mineral province (Brazil) through machine learning, dealing with imbalanced training data. Ore Geology Reviews, 124, 103611.

    Article  Google Scholar 

  57. Quinlan, J. R. (1991). Improved estimates for the accuracy of small disjuncts. Machine learning, 6(1), 93–98.

    Google Scholar 

  58. Ravi, D., Wong, C., Deligianni, F., Berthelot, M., Andreu-Perez, J., Lo, B., et al. (2017). Deep learning for health informatics. IEEE Journal of Biomedical & Health Informatics, 21(1), 4–21.

    Article  Google Scholar 

  59. Rodriguez-Galiano, V., Sanchez-Castillo, M., Chica-Olmo, M., & Chica-Rivas, M. (2015). Machine learning predictive models for mineral prospectivity, an evaluation of neural networks, random forest, regression trees and support vector machines. Ore Geology Reviews, 71, 804–818.

    Article  Google Scholar 

  60. Sankar, M., Batri, K., & Partvathi, R. (2016). Earliest diabetic retinopathy classification using deep convolution neural networks. International Journal of Advanced Engineering Technology, 2(1), 460–470.

    Google Scholar 

  61. Shabankareh, M., & Hezarkhani, A. (2017). Application of support vector machines for copper potential mapping in Kerman region Iran. Journal of African Earth Sciences, 128, 116–126.

    Article  Google Scholar 

  62. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout, a simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 15(1), 1929–1958.

    Google Scholar 

  63. Stensgaard, B. M., Chung, C. J., Rasmussen, T. M., & Stendal, H. (2006). Assessment of mineral potential using cross-validation techniques and statistical analysis, a case study from the Paleoproterozoic of West Greenland. Economic Geology, 101(7), 1397–1413.

    Article  Google Scholar 

  64. Sui, J. X., Li, J. W., Wen, G., & Jin, X. Y. (2017a). The Dewulu reduced Au-Cu skarn deposit in the Xiahe-Hezuo district, West Qinling orogen, China: implications for an intrusion-related gold system. Ore Geology Reviews, 80, 1230–1244.

    Article  Google Scholar 

  65. Sui, J.X. (2012). Geochronology and genesis of the Zaozigou gold deposit, Gansu province, China. M.Sc. dissertation, China University of Geosciences, Wuhan, China (In Chinese with English abstract).

  66. Sui, J. X., Li, J. W., Wen, G., & Jin, X. Y. (2017b). The Dewulu reduced Au-Cu skarn deposit in the Xiahe-Hezuo district, West Qinling orogen, China, Implications for an intrusion-related gold system. Ore Geology Reviews, 80, 1230–1244.

    Article  Google Scholar 

  67. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Rabinovich, A. (2015). Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1-9).

  68. Torppa, J., Nykänen, V., & Molnár, F. (2019). Unsupervised clustering and empirical fuzzy memberships for mineral prospectivity modelling. Ore Geology Reviews, 107, 58–71.

    Article  Google Scholar 

  69. Vishnu, H., V. Robert, B. Kalyan., & M. Chitre. (2018). A semi-supervised learning approach to polymetallic nodule parameter modeling. OCEANS 2018 MTS/IEEE Charleston, IEEE

  70. Wang, J., Zuo, R., & Xiong, Y. (2020). Mapping mineral prospectivity via semi-supervised random forest. Natural Resources Research, 29(1), 189–202.

    Article  Google Scholar 

  71. Wason, R. (2018). Deep learning, Evolution and expansion. Cognitive Systems Research, 52, 701–708.

    Article  Google Scholar 

  72. Wu, H., & Zhao, J. S. (2018). Deep convolutional neural network model based chemical process fault diagnosis. Computers & Chemical Engineering, 115, 185–197.

    Article  Google Scholar 

  73. Xiong, Y., & Zuo, R. (2016). Recognition of geochemical anomalies using a deep autoencoder network. Computers & Geosciences, 86, 75–82.

    Article  Google Scholar 

  74. Xiong, Y., Zuo, R., & Carranza, E. J. M. (2018). Mapping mineral prospectivity through big data analytics and a deep learning algorithm. Ore Geology Reviews, 102, 811–817.

    Article  Google Scholar 

  75. Yu, F., & Koltun, V. (2015). Multi-scale context aggregation by dilated convolutions. (pp. 1–13).

  76. Zadrozny, B., Langford, J., & Abe, N. (2003). Cost-sensitive learning by cost-proportionate example weighting. Paper presented at the Third IEEE international conference on data mining.

  77. Zhang, H. F., Jin, L. L., Zhang, L., Harris, N., Zhou, L., Hu, S. H., & Zhang, B. R. (2007). Geochemical and Pb-Sr-Nd isotopic compositions of granitoids from western Qinling belt, constraints on basement nature and tectonic affinity. Sci. China Earth, 50, 184–196.

    Article  Google Scholar 

  78. Zhang, S., Xiao, K., Carranza, E. J. M., Yang, F., & Zhao, Z. (2019a). Integration of auto-encoder network with density-based spatial clustering for geochemical anomaly detection for mineral exploration. Computers & Geosciences, 130, 43–56.

    Article  Google Scholar 

  79. Zhang, S., Xiao, K., Carranza, E. J. M., & Yang, F. (2019b). Maximum entropy and random forest modeling of mineral potential, analysis of gold prospectivity in the Hezuo-Meiwu District, West Qinling Orogen China. Natural Resources Research, 28(3), 645–664.

    Article  Google Scholar 

  80. Zuo, R., Xiong, Y. H., & Y. H., J. Wang, J., & Carranza E. J. M. . (2019). Deep learning and its application in geochemical mapping. Earth-Science Reviews, 192, 1–14.

    Article  Google Scholar 

Download references

Acknowledgments

Funding support for this research was derived from the National Key Research and Development Program of China (Project No. 2017YFC0601501), The China National Mineral Resources Assessment Initiative (Project Nos. 1212010733806 and 1,212,011,120,140) and China Scholarship Council (CSC No. 201906400022).

Author information

Affiliations

Authors

Corresponding authors

Correspondence to Shuai Zhang or Emmanuel John M. Carranza or Hantao Wei or Keyan Xiao.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Zhang, S., Carranza, E.J.M., Wei, H. et al. Data-driven Mineral Prospectivity Mapping by Joint Application of Unsupervised Convolutional Auto-encoder Network and Supervised Convolutional Neural Network. Nat Resour Res (2021). https://doi.org/10.1007/s11053-020-09789-y

Download citation

Keywords

  • Deep learning
  • Convolutional neural network
  • Unsupervised convolutional auto-encoder network
  • Mineral prospectivity mapping