Advertisement

Natural Resources Research

, Volume 28, Issue 1, pp 31–46 | Cite as

Isolation Forest as an Alternative Data-Driven Mineral Prospectivity Mapping Method with a Higher Data-Processing Efficiency

  • Yongliang ChenEmail author
  • Wei Wu
Original Paper
  • 143 Downloads

Abstract

Mineral exploration targets can be delineated through multivariate analysis. These targets are usually recognized as anomalies in the procedure of data mining using a detection algorithm. In this paper, isolation forest, which is a data-mining algorithm for anomaly detection, was adapted to map gold prospectivity in the Laotudingzi–Xiaosiping district in Jilin Province, northeastern China. The performance of the isolation forest model was compared with those of restricted Boltzmann machine and logistic regression models for mapping gold prospectivity. The isolation forest model outperforms the restricted Boltzmann machine model but not the logistic regression model based on the receiver operating characteristic curve and area under the curve; however, the isolation forest model is much more efficient than the other two models in terms of data-processing efficiency. It takes 15.48, 254.74, and 57.33 s, respectively, to integrate the predictor map layers using the three models. Gold mineral exploration targets were optimally delineated by using the Youden index to maximize spatial association between delineated gold mineral exploration targets and the discovered gold deposits. Gold mineral exploration targets predicted by the three models occupy 10.97, 10.36, and 8.40% of the study area and contain 88, 81, and 81% of the discovered gold deposits. Therefore, the isolation forest algorithm is a potentially useful mineral prospectivity mapping method.

Keywords

Mineral prospectivity Isolation forest Restricted Boltzmann machine Logistic regression Receiver operating characteristic curve The Youden index 

Notes

Acknowledgments

We are grateful to Editor Carranza for his help which greatly improved the English of the manuscript. We are also grateful to Profs. Zuo and Yousefi for their constructive comments. This work was supported by the National Natural Science Foundation of China (Grant Nos. 41472299 and 41672322).

References

  1. Abedi, M., Gholami, A., & Norouzi, G. H. (2013). A stable downward continuation of airborne magnetic data: A case study for mineral prospectivity mapping in Central Iran. Computers and Geosciences, 52(1), 269–280.Google Scholar
  2. Abedi, M., Norouzi, G. H., & Bahroudi, A. (2012a). Support vector machine for multi-classification of mineral prospectivity areas. Computers and Geosciences, 46(2), 272–283.Google Scholar
  3. Abedi, M., Torabi, S. A., Norouzi, G. H., & Hamzeh, M. (2012b). ELECTRE III: A knowledge-driven method for integration of geophysical data with geological and geochemical data in mineral prospectivity mapping. Journal of Applied Geophysics, 87(12), 9–18.Google Scholar
  4. Abedi, M., Torabi, S. A., Norouzi, G. H., Hamzeh, M., & Elyasi, G. R. (2012c). PROMETHEE II: A knowledge-driven method for copper exploration. Computers and Geosciences, 46(2), 255–263.Google Scholar
  5. Agterberg, F. P. (1974). Automatic contouring of geological maps to detect target areas for mineral exploration. Mathematical Geology, 6(4), 373–395.Google Scholar
  6. Agterberg, F. P. (1989). LOGDIA-FORTRAN 77 program for logistic regression with diagnostics. Computers and Geosciences, 15(4), 599–614.Google Scholar
  7. Agterberg, F.P. (1990). Combining indicator patterns for mineral resource evaluation. In China University of Geosciences (Eds.), proceedings of international workshop on statistical prediction of mineral resources (Vol. 1, pp. 1–15). Wuhan: International Association for Mathematical Geosciences.Google Scholar
  8. Agterberg, F. P. (1992). Combining indicator patterns in weights of evidence modeling for resource evaluation. Nonrenewable Resources, 1(1), 39–50.Google Scholar
  9. Agterberg, F. P., Bonham-Carter, G. F., & Wright, D. F. (1990). Statistical pattern integration for mineral exploration. In G. Gaal & D. F. Merriam (Eds.), Computer applications in resource estimation prediction and assessment for metals and petroleum (pp. 1–19). Oxford: Pergamon Press.Google Scholar
  10. An, P., Moon, W. M., & Rencz, A. N. (1991). Application of fuzzy theory for integration of geological, geophysical and remotely sensed data. Canadian Journal of Exploration Geophysics, 27(1), 1–11.Google Scholar
  11. Asadi, H. H., Sansoleimani, A., Fatehi, M., & Carranza, E. J. M. (2016). An AHP–TOPSIS predictive model for district-scale mapping of porphyry Cu–Au potential: A case study from Salafchegan area (Central Iran). Natural Resources Research, 25(4), 417–429.Google Scholar
  12. Barnicoat, A. C. (2007). Mineral systems and exploration science: Linking fundamental controls on ore deposition with the exploration process. In C. J. Andrews (Ed.), Digging deeper. Proceedings of the ninth biennial SGA meeting (pp. 1407–1411). Dublin: Irish Association for Economic Geology.Google Scholar
  13. Bergmann, R., Ludbrook, J., & Spooren, W. P. J. M. (2000). Different outcomes of the Wilcoxon–Mann–Whitney test from different statistics packages. The American Statistician, 54(1), 72–77.Google Scholar
  14. Bonham-Carter, G. F., Agterberg, F. P., & Wright, D. F. (1988). Integration of geological datasets for gold exploration in Nova Scotia. Photogrammetric Engineering and Remote Sensing, 54(11), 1585–1592.Google Scholar
  15. Breiman, L. (2001). Random forests. Machine Learning, 45, 5–32.Google Scholar
  16. Brown, W., Gedeon, T., & Groves, D. I. (2003a). Use of noise to augment training data: A neural network method of mineral–potential mapping in regions of limited known deposit examples. Natural Resources Research, 13(2), 141–152.Google Scholar
  17. Brown, W. M., Gedeon, T. D., Groves, D. I., & Barnes, R. G. (2000). Artificial neural networks: A new method for mineral prospectivity mapping. Australian Journal of Earth Sciences, 47(4), 757–770.Google Scholar
  18. Brown, W., Groves, D., & Gedeon, T. (2003b). Use of fuzzy membership input layers to combine subjective geological knowledge and empirical data in a neural network method for mineral-potential mapping. Natural Resources Research, 12(3), 183–200.Google Scholar
  19. Carranza, E. J. M. (2009). Objective selection of suitable unit cell size in data-driven modeling of mineral prospectivity. Computers and Geosciences, 35(10), 2032–2046.Google Scholar
  20. Carranza, E. J. M. (2010). Improved wildcat modelling of mineral prospectivity. Resource Geology, 60(2), 129–149.Google Scholar
  21. Carranza, E. J. M. (2015). Data-driven evidential belief modeling of mineral potential using few prospects and evidence with missing values. Natural Resources Research, 24(3), 291–304.Google Scholar
  22. 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.Google Scholar
  23. 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.Google Scholar
  24. Carranza, E. J. M., & Hale, M. (2002a). Where are porphyry copper deposits spatially localized? A case study in Benguet province, Philippines. Natural Resources Research, 11(1), 45–59.Google Scholar
  25. Carranza, E. J. M., & Hale, M. (2002b). Wildcat mapping of gold potential, Baguio district, Philippines. Transactions of the Institutions of Mining and Metallurgy (Applied Earth Science), 111(2), 100–105.Google Scholar
  26. 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.Google Scholar
  27. 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.Google Scholar
  28. Carranza, E. J. M., & Laborte, A. G. (2015b). Random forest predictive modeling of mineral prospectivity with small number of prospects and data with missing values in Abra (Philippines). Computers and Geosciences, 74(1), 60–70.Google Scholar
  29. Carranza, E. J. M., & Laborte, A. G. (2016). Data-driven predictive modeling of mineral prospectivity using Random Forests: A case study in Catanduanes Island (Philippines). Natural Resources Research, 25(1), 35–50.Google Scholar
  30. Carranza, E. J. M., Woldai, T., & Chikambwe, E. M. (2005). Application of data-driven evidential belief functions to prospectivity mapping for aquamarine-bearing pegmatites, Lundazi district, Zambia. Natural Resources Research, 14(1), 47–63.Google Scholar
  31. Chen, Y. L. (2003). Indicator pattern combination for mineral resource potential mapping with the general C-F model. Mathematical Geology, 35(3), 301–321.Google Scholar
  32. Chen, Y. L. (2004). MRPM: Three visual basic programs for mineral resource potential mapping. Computers and Geosciences, 30(9–10), 969–983.Google Scholar
  33. Chen, Y. L. (2015). Mineral potential mapping with a restricted Boltzmann machine. Ore Geology Reviews, 71, 749–760.Google Scholar
  34. Chen, Y. L., Lu, L. J., & Li, X. B. (2014). Application of continuous restricted Boltzmann machine to identify multivariate geochemical anomaly. Journal of Geochemical Exploration, 140, 56–63.Google Scholar
  35. Chen, Y. L., & Wu, W. (2016). A prospecting cost-benefit strategy for mineral potential mapping based on ROC curve analysis. Ore Geology Reviews, 74, 26–38.Google Scholar
  36. Chen, Y. L., & Wu, W. (2017a). Mapping mineral prospectivity using an extreme learning machine regression. Ore Geology Reviews, 80, 200–213.Google Scholar
  37. Chen, Y. L., & Wu, W. (2017b). Mapping mineral prospectivity by using one class support vector machine to identify multivariate geological anomalies from digital geological survey. Australian Journal of Earth Sciences, 44(5), 639–651.Google Scholar
  38. Chen, Y. L., & Wu, W. (2017c). Application of one-class support vector machine to quickly identify multivariate anomalies from geochemical exploration data. Geochemistry: Exploration Environment, Analysis, 17, 231–238.Google Scholar
  39. Cheng, Q. M. (2015). Boost WofE: A new sequential weights of evidence model reducing the effect of conditional dependency. Mathematical Geosciences, 47(5), 591–621.Google Scholar
  40. Cheng, Q. M., Chen, Z. J., & Khaled, A. (2007). Application of fuzzy weights of evidence method in mineral resource assessment for gold in Zhenyuan District, Yunnan Province, China. Earth Science—Journal of China University of Geosciences, 32(2), 175–184. (In Chinese with English Abstract).Google Scholar
  41. Chung, C. F., & Moon, W. M. (1990). Combination rules of spatial geoscience data for mineral exploration. Geoinformatics, 2, 159–169.Google Scholar
  42. David, P. M. W. (2011). Evaluation: From precision, recall and F-score to ROC, informedness, markedness & correlation. Journal of Machine Learning Technologies, 2(1), 37–63.Google Scholar
  43. D’Ercole, C., Groves, D. I., & Knox-Robinson, C. M. (2000). Using fuzzy logic in a geographic information system environment to enhance conceptually based prospectivity analysis of Mississippi valley-type mineralization. Australian Journal of Earth Sciences, 47(5), 913–927.Google Scholar
  44. Ding, Z., & Fei, M. (2013). An anomaly detection approach based on isolation forest algorithm for streaming data using sliding window. In 3rd IFAC international conference on intelligent control and automation science (Vol. 46(20), pp. 12–17). Chengdu: The International Federation of Automatic Control.Google Scholar
  45. Elliott, B. A., Verma, R., & Kyle, J. R. (2016). Prospectivity modeling for Cambrian-Ordovician hydraulic fracturing sand resources around the Llano Uplift, Central Texas. Natural Resources Research, 25(4), 389–415.Google Scholar
  46. Ford, A., Miller, J. M., & Mol, A. G. (2015). A comparative analysis of weights of evidence, evidential belief functions, and fuzzy logic for mineral potential mapping using incomplete data at the scale of investigation. Natural Resources Research, 25(1), 19–33.Google Scholar
  47. Gao, Y., Zhang, Z., Xiong, Y., & Zuo, R. (2016). Mapping mineral prospectivity for Cu polymetallic mineralization in southwest Fujian Province, China. Ore Geology Reviews, 75, 16–28.Google Scholar
  48. Geranian, H., Tabatabaei, S. H., Asadi, H. H., & Carranza, E. J. M. (2016). Application of discriminant analysis and support vector machine in mapping gold potential areas for further drilling in the Sari-Gunay gold deposit, NW Iran. Natural Resources Research, 25(2), 145–159.Google Scholar
  49. Gonbadi, A. G., Tabatabaei, S. H., & Carranza, E. J. M. (2015). Supervised geochemical anomaly detection by pattern recognition. Journal of Geochemical Exploration, 157, 81–91.Google Scholar
  50. Harris, D., & Pan, G. (1999). Mineral favorability mapping: A comparison of artificial neural networks, logistic regression, and discriminant analysis. Natural Resources Research, 8(2), 93–109.Google Scholar
  51. Harris, D., Zurcher, L., Stanley, M., Marlow, J., & Pan, G. (2003). A comparative analysis of favorability mappings by weights of evidence, probabilistic neural networks, discriminant analysis, and logistic regression. Natural Resources Research, 12(4), 241–255.Google Scholar
  52. He, Y., Zhu, X., Wang, G., Sun, H., & Wang, Y. (2017). Predicting bugs in software code changes using isolation forest. In IEEE international conference on software quality, reliability and security (QRS 2017) (pp. 297–305). Prague: IEEE Press.Google Scholar
  53. Jia, S. S., Zhao, C. F., Wang, E. D., Fu, J. F., & Xi, X. F. (2008). The study on regional tectonics of Jinying gold ore in Baishan City, Jilin Province. Geotectonica et Metallogenia, 32(4), 492–499. (In Chinese with English Abstract).Google Scholar
  54. Karimi, M., Menhaj, M. B., & Mesgari, M. S. (2008). Preparing mineral potential map using fuzzy logic in GIS environment. In The international archives of the photogrammetry, remote sensing and spatial information sciences, l, XXXVII, Part B8 (pp. 1263–1270). Beijing: International Society for Photogrammetry and Remote Sensing.Google Scholar
  55. Knox-Robinson, C. M. (2000). Vectorial fuzzy logic: A novel technique for enhanced mineral prospectivity mapping, with reference to the orogenic gold mineralisation potential of the Kalgoorlie Terrane, western Australia. Australian Journal of Earth Sciences, 47(5), 929–941.Google Scholar
  56. Li, B. Y., Yang, Z. Y., & Wang, Y. F. (2010). Geological characteristics and genesis of Huanggoushan and Banmiaozi gold deposits in Laoling metallogenic belt of southern Jilin. Global Geology, 29(3), 392–399. (In Chinese with English Abstract).Google Scholar
  57. Liu, W., Deng, J., Chu, X. L., Zhai, Y. S., Xu, G. Z., & Li, X. J. (2000). Characteristics and geological background of formation of large and giant ore deposits within the northern margin of the north China platform. Progress in Geophysics, 15(2), 67–78. (In Chinese with English Abstract).Google Scholar
  58. Liu, F. T., Ting, K. M., & Zhou, Z. H. (2008). Isolation forest. In Proceedings of the eighth IEEE international conference on data mining (ICDM) (pp. 413–422). Pisa: IEEE Press.Google Scholar
  59. McCuaig, T. C., Beresford, S., & Hronsky, J. (2010). Translating the mineral system approach into an effective exploration targeting system. Ore Geology Reviews, 38(3), 128–138.Google Scholar
  60. McKay, G., & Harris, J. R. (2016). Comparison of the data-driven random forests model and a knowledge-driven method for mineral prospectivity mapping: A case study for gold deposits around the Huritz Group and Nueltin Suite, Nunavut, Canada. Natural Resources Research, 25(2), 125–143.Google Scholar
  61. Mejia-Herrera, P., Royey, J. J., Caumon, G., & Cheilletz, A. (2015). Curvature attribute from surface-restoration as predictor variable in Kupferschiefer copper potentials. Natural Resources Research, 24(3), 275–290.Google Scholar
  62. Molan, Y. E., & Behnia, P. (2013). Prospectivity mapping of Pb–Zn SEDEX mineralization using remote-sensing data in the Behabad area, Central Iran. International Journal of Remote Sensing, 34(4), 1164–1179.Google Scholar
  63. Nykänen, V., Groves, D. I., Ojala, V. J., & Gardoll, S. J. (2008). Combined conceptual/empirical prospectivity mapping for orogenic gold in the northern Fennoscandian Shield, Finland. Australian Journal of Earth Sciences, 55(1), 39–59.Google Scholar
  64. Oh, H. J., & Lee, S. (2010). Application of artificial neural network for gold–silver deposits potential mapping: A case study of Korea. Natural Resources Research, 19(2), 103–124.Google Scholar
  65. Porwal, A., Carranza, E. J. M., & Hale, M. (2006). A hybrid fuzzy weights-of-evidence model for mineral potential mapping. Natural Resources Research, 15(1), 1–15.Google Scholar
  66. Puggini, L., & McLoone, S. (2018). An enhanced variable selection and isolation forest based methodology for anomaly detection with OES data. Engineering Applications of Artificial Intelligence, 67, 126–135.Google Scholar
  67. Rodriguez-Galiano, V. F., Chica-Olmo, M., & Chica-Rivas, M. (2014). Predictive modelling of gold potential with the integration of multisource information based on random forest: A case study on the Rodalquilar area, Southern Spain. International Journal of Geographical Information Science, 28(7), 1336–1354.Google Scholar
  68. Schisterman, E. F., Perkins, N. J., Liu, A., & Bondell, H. (2005). Optimal cut-point and its corresponding Youden Index to discriminate individuals using pooled blood samples. Epidemiology, 16, 73–81.Google Scholar
  69. Skabar, A. A. (2003). Mineral potential mapping using feed-forward neural networks. In Proceedings of the international joint conference on neural networks (Vol. 3, 1814–1819). Portland: IEEE Press.Google Scholar
  70. Susto, G. A., Beghi, A., & McLoone, S. (2107). Anomaly detection through on-line isolation forest: An application to plasma etching. In 28th annual SEMI advanced semiconductor manufacturing conference (ASMC 2017) (pp. 89–94). Saratoga Springs: IEEE Press.Google Scholar
  71. Tangestani, M. H., & Moore, F. (2001). Porphyry copper potential mapping using the weights-of-evidence model in a GIS, northern Shahr-e-Babak, Iran. Australian Journal of Earth Sciences, 48(5), 913–927.Google Scholar
  72. Varian, H. (2005). Bootstrap tutorial. Mathematica Journal, 9, 768–775.Google Scholar
  73. Wu, F., Lin, J., Wilde, S. A., Zhang, Q., & Yang, J. (2005). Nature and significance of early Cretaceous giant igneous event in eastern China. Earth and Planetary Science Letters, 233(1–2), 103–119.Google Scholar
  74. Xiong, Y., & Zuo, R. (2017). Effects of misclassification costs on mapping mineral prospectivity. Ore Geology Reviews, 82, 1–9.Google Scholar
  75. Youden, W. J. (1950). Index for rating diagnostic tests. Cancer, 3, 32–35.Google Scholar
  76. Yousefi, M., & Carranza, E. J. M. (2015). Fuzzification of continuous-value spatial evidence for mineral prospectivity mapping. Computers and Geosciences, 74, 97–109.Google Scholar
  77. Yousefi, M., & Carranza, E. J. M. (2016). Data-driven index overlay and Boolean logic mineral prospectivity modeling in greenfields exploration. Natural Resources Research, 25, 3–18.Google Scholar
  78. Yousefi, M., & Carranza, E. J. M. (2017). Union score and fuzzy logic mineral prospectivity mapping using discretized and continuous spatial evidence values. Journal of African Earth Sciences, 128, 47–60.Google Scholar
  79. Yousefi, M., & Nykänen, V. (2016). Data-driven logistic-based weighting of geochemical and geological evidence layers in mineral prospectivity mapping. Journal of Geochemical Exploration, 164, 94–106.Google Scholar
  80. Zhang, L. M., Wang, D. S., & Zhang, D. W. (2011). Geologic characteristics, ore-controlling factors and prospects of the Gaoligou gold deposit in Jilin Province. Geology and Resources, 20(5), 350–353. (In Chinese with English Abstract).Google Scholar
  81. Zhang, Z., Zuo, R., & Xiong, Y. (2016). A comparative study of fuzzy weights of evidence and random forests for mapping mineral prospectivity for skarn-type Fe deposits in the southwestern Fujian metallogenic belt, China. Science China Earth Sciences, 59(3), 556–572.Google Scholar
  82. Zheng, C. J. (1995). The geological features and origin of the Huanggoushan gold deposit, Jilin Province. Jilin Geology, 14(3), 1–16. (In Chinese with English Abstract).Google Scholar
  83. Zhong, G. J., Run, T. Y., & Cai, Y. (2014). Geological features and origin of Cuocaogou gold deposit. Western Prospecting Engineering, 3, 117–124. (In Chinese Without English Abstract).Google Scholar
  84. Zhou, X. B., Li, J. F., Wang, K. Y., Liang, Y. H., Zhang, M., Wei, L. M., et al. (2016). Geochemical characteristics of ore-forming fluid in Huanggoushan gold deposit, Jilin Province. Earth Science, 41(1), 121–130. (In Chinese with English Abstract).Google Scholar
  85. Zuo, R., & Carranza, E. J. M. (2011). Support vector machine: A tool for mapping mineral potential. Computers and Geosciences, 37(12), 1967–1975.Google Scholar

Copyright information

© International Association for Mathematical Geosciences 2018

Authors and Affiliations

  1. 1.Institute of Mineral Resources Prognosis on Synthetic InformationJilin UniversityChangchunChina
  2. 2.Changchun Institute of Urban Planning and DesignChangchunChina

Personalised recommendations