Natural Resources Research

, Volume 28, Issue 4, pp 1285–1298 | Cite as

Mapping Geochemical Anomalies Through Integrating Random Forest and Metric Learning Methods

  • Ziye Wang
  • Renguang ZuoEmail author
  • Yanni DongEmail author
Original Paper


Extracting geochemical anomalies from geochemical exploration data is one of the most important activities in mineral exploration. Geochemical anomaly detection can be regarded as a binary classification problem. The similarity between geochemical samples can be measured by their distance. The key issue of this classification is to find the intrinsic relationship and distance between geochemical samples to separate geochemical anomalies from background. In this paper, a hybrid method that integrates random forest and metric learning (RFML) is used to identify geochemical anomalies related to Fe-polymetallic mineralization in Southwest Fujian Province of China. RFML does not require any specific statistical assumption on geochemical data, nor does it depend on sufficient known mineral occurrences as the prior knowledge. The geochemical anomaly map obtained by the RFML method showed that the known Fe deposits and the generated geochemical anomaly area have strong spatial association. Meanwhile, the receiver operating characteristic curves for the results of RFML and another method, namely maximum margin metric learning, indicated that the RFML method exhibited better performance, suggesting that RFML can be effectively applied to recognize geochemical anomalies.


Mineral exploration Machine learning Random forest Metric learning Geochemical anomalies GIS Fujian 



We thank Prof. John Carranza, Dr. M. Yousefi and an anonymous reviewer whose comments and suggestions helped us improve this study. This study was jointly supported by the National Natural Science Foundation of China (41772344, 61801444), the Natural Science Foundation of Hubei Province (China) (2017CFA053), the Hong Kong Scholars Program (XJ2018012), the Fundamental Research Funds for the Central Universities, China University of Geosciences (Wuhan) (CUG170687) and the Most Special Fund from the State Key Laboratory of Geological Processes and Mineral Resources, China University of Geosciences (MSFGPMR03-3).


  1. Baghshah, M. S., & Shouraki, S. B. (2010). Non-linear metric learning using pairwise similarity and dissimilarity constraints and the geometrical structure of data. Pattern Recognition, 43, 2982–2992.CrossRefGoogle Scholar
  2. Bar-Hillel, A., Hertz, T., Shental, N., & Weinshall, D. (2005). Learning a mahalanobis metric from equivalence constraints. Journal of Machine Learning Research, 6, 937–965.Google Scholar
  3. Breiman, L. (1984). Classification and regression trees. Rubber Company.Google Scholar
  4. Breiman, L. (1996). Bagging predictors. Machine Learning, 24, 123–140.Google Scholar
  5. Breiman, L. (2001). Random forest. Machine Learning, 45, 5–32.CrossRefGoogle Scholar
  6. Cao, Q., Ying, Y., & Li, P. (2012). Distance metric learning revisited (pp. 283–298). Berlin: Springer.Google Scholar
  7. Carranza, E. J. M. (2009). Geochemical anomaly and mineral prospectivity mapping in GIS. Handbook of exploration & environmental geochemistry (Vol. 11). Amsterdam: Elsevier.Google Scholar
  8. Carranza, E. J. M. (2011). Analysis and mapping of geochemical anomalies using logratio-transformed stream sediment data with censored values. Journal of Geochemical Exploration, 110, 167–185.CrossRefGoogle Scholar
  9. Carranza, E. J. M., & Laborte, A. G. (2015a). 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.CrossRefGoogle Scholar
  10. Carranza, E. J. M., & Laborte, A. G. (2015b). Data-driven predictive mapping of gold prospectivity, Baguio district, Philippines: Application of Random Forests algorithm. Ore Geology Reviews, 71, 777–787.CrossRefGoogle Scholar
  11. 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, 35–50.CrossRefGoogle Scholar
  12. Chen, Y., & An, A. (2016). Application of ant colony algorithm to geochemical anomaly detection. Journal of Geochemical Exploration, 164, 75–85.CrossRefGoogle Scholar
  13. Chen, Y., & Wu, W. (2017). 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
  14. Cheng, Q. (2007). Mapping singularities with stream sediment geochemical data for prediction of undiscovered mineral deposits in Gejiu, Yunnan Province, China. Ore Geology Reviews, 32, 314–324.CrossRefGoogle Scholar
  15. Cheng, Q., & Agterberg, F. P. (2009). Singularity analysis of ore-mineral and toxic trace elements in stream sediments. Computers & Geosciences, 35, 234–244.CrossRefGoogle Scholar
  16. Cheng, Q., Agterberg, F. P., & Ballantyne, S. B. (1994). The separation of geochemical anomalies from background by fractal methods. Journal of Geochemical Exploration, 51, 109–130.CrossRefGoogle Scholar
  17. Cheng, Q., Xu, Y., & Grunsky, E. (2000). Integrated spatial and spectrum method for geochemical anomaly separation. Natural Resources Research, 9, 43–52.CrossRefGoogle Scholar
  18. Cohen, D. R., Kelley, D. L., Anand, R., & Coker, W. B. (2010). Major advances in exploration geochemistry, 1998–2007. Geochemistry: Exploration, Environment, Analysis, 10, 3–16.Google Scholar
  19. Dong, Y., Du, B., & Zhang, L. (2015a). Target detection based on random forest metric learning. IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing, 8, 1830–1838.CrossRefGoogle Scholar
  20. Dong, Y., Du, B., Zhang, L., & Hu, X. (2018). Hyperspectral target detection via adaptive information-theoretic metric learning with local constraints. Remote Sensing, 10, 1415.CrossRefGoogle Scholar
  21. Dong, Y., Zhang, L., Zhang, L., & Du, B. (2015b). Maximum margin metric learning based target detection for hyperspectral images. ISPRS Journal of Photogrammetry & Remote Sensing, 108, 138–150.CrossRefGoogle Scholar
  22. Egozcue, J., Pawlowskyglahn, V., Mateufigueras, G., & Barcelóvidal, C. (2003). Isometric logratio transformations for compositional data analysis. Mathematical Geology, 35, 279–300.CrossRefGoogle Scholar
  23. Fabrigar, L., Wegener, D., MacCallum, R., & Strahan, E. (1999). Evaluating the use of exploratory factor analysis in psychological research. Psychological Methods, 4, 272.CrossRefGoogle Scholar
  24. Filzmoser, P., Hron, K., Reimann, C., & Garrett, R. (2009). Robust factor analysis for compositional data. Computers & Geosciences, 35, 1854–1861.CrossRefGoogle Scholar
  25. Franc, V., & Sonnenburg, S. (2009). Optimized cutting plane algorithm for large-scale risk minimization. Journal of Machine Learning Research, 10, 2157–2192.Google Scholar
  26. 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.CrossRefGoogle Scholar
  27. Ge, C., Han, F., Zhou, T., & Chen, D. (1981). Geological characteristics of the Makeng iron deposit of marine volcano-sedimentary origin. Acta Geosicientia Sinica, 3, 47–69. (In Chinese with English Abstract).Google Scholar
  28. Gonbadi, A. M., Tabatabaei, S. H., & Carranza, E. J. M. (2015). Supervised geochemical anomaly detection by pattern recognition. Journal of Geochemical Exploration, 157, 81–91.CrossRefGoogle Scholar
  29. Grunsky, E. C. (2010). The interpretation of geochemical survey data. Geochemistry: Exploration, Environment, Analysis, 10, 27–74.Google Scholar
  30. Hu, R., Bi, X., Jiang, G., Chen, H., Peng, J., Qi, Y., et al. (2012). Mantle-derived noble gases in ore-forming fluids of the granite-related Yaogangxian tungsten deposit, Southeastern China. Mineralium Deposita, 47, 623–632.CrossRefGoogle Scholar
  31. Kirkwood, C., Cave, M., Beamish, D., Grebby, S., & Ferreira, A. (2016). A machine learning approach to geochemical mapping. Journal of Geochemical Exploration, 167, 49–61.CrossRefGoogle Scholar
  32. Kohavi, R. (1995). A study of cross-validation and bootstrap for accuracy estimation and model selection. In Proceedings of the 14th international joint conference on artificial intelligence, Montreal, Canada (pp. 1137–1145).Google Scholar
  33. Liaw, A., & Wiener, M. (2002). Classification and regression by random Forest. R News, 2, 18–22.Google Scholar
  34. Mao, J., Pirajno, F., & Cook, N. (2011). Mesozoic metallogeny in East China and corresponding geodynamic settings-An introduction to the special issue. Ore Geology Reviews, 43, 1–7.CrossRefGoogle Scholar
  35. Mao, J., Tao, K., Xie, F., Xu, N., & Chen, S. (2001). Rock-forming and ore-forming processes and tectonic environments in Southwest Fujian. Acta Petrologica Et Mineralogica, 20, 329–336. (In Chinese with English abstract).Google Scholar
  36. Parsa, M., Maghsoudi, A., & Yousefi, M. (2018). Spatial analyses of exploration evidence data to model skarn-type copper prospectivity in the Varzaghan district, NW Iran. Ore Geology Reviews, 92, 97–112.CrossRefGoogle Scholar
  37. Peng, J., Zhou, M., Hu, R., Shen, N., Yuan, S., et al. (2006). Precise molybdenite Re–Os and mica Ar–Ar dating of the Mesozoic Yaogangxian tungsten deposit, central Nanling district, South China. Mineralium Deposita, 41, 661–669.CrossRefGoogle Scholar
  38. Reimann, C., Filzmoser, P., & Garrett, R. G. (2002). Factor analysis applied to regional geochemical data: Problems and possibilities. Applied Geochemistry, 17, 185–206.CrossRefGoogle Scholar
  39. 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.CrossRefGoogle Scholar
  40. Rose, A. W., Hawkes, H. E., & Webb, J. S. (1979). Geochemistry in mineral exploration (2nd ed.). London: Academic Press.Google Scholar
  41. Roshanravan, B., Aghajani, H., Yousefi, M., & Kreuzer, O. (2018). An improved prediction-area plot for prospectivity analysis of mineral deposits. Natural Resources Research, 1–17.Google Scholar
  42. Shu, L., Faure, M., Wang, B., Zhou, X., & Song, B. (2008). Late Palaeozoic-early Mesozoic geological features of South China: Response to the Indosinian collision events in Southeast Asia. Comptes Rendus Geoscience, 340, 151–165.CrossRefGoogle Scholar
  43. Singer, D. A., & Kouda, R. (2001). Some simple guides to finding useful information in exploration geochemical data. Natural Resources Research, 10, 137–147.CrossRefGoogle Scholar
  44. Tripathi, V. S. (1979). Factor analysis in geochemical exploration. Journal of Geochemical Exploration, 11, 263–275.CrossRefGoogle Scholar
  45. Wang, F. (2011). Semi-supervised metric learning by maximizing constraint margin. IEEE Transactions on Systems Man & Cybernetics, Part B (Cybernetics), 41, 931–939.CrossRefGoogle Scholar
  46. Wang, H., Cheng, Q., & Zuo, R. (2015a). Spatial characteristics of geochemical patterns related to Fe mineralization in the southwestern Fujian province (China). Journal of Geochemical Exploration, 148, 259–269.CrossRefGoogle Scholar
  47. Wang, Z., Dong, Y., & Zuo, R. (2019). Mapping geochemical anomalies related to Fe–polymetallic mineralization using the maximum margin metric learning method. Ore Geology Reviews, 107, 258–265.CrossRefGoogle Scholar
  48. Wang, S., Zhang, D., & Vatuva, A. (2015b). Zircon U–Pb geochronology, geochemistry and Hf isotope compositions and their implications of the Dayang and Juzhou Granite from Longyan Area in Fujian Province. Geochemica, 44, 440–468.Google Scholar
  49. Wang, H., & Zuo, R. (2015). A comparative study of trend surface analysis and spectrum–area multifractal model to identify geochemical anomalies. Journal of Geochemical Exploration, 155, 84–90.CrossRefGoogle Scholar
  50. Wang, J., & Zuo, R. (2018). Identification of geochemical anomalies through combined sequential Gaussian simulation and grid-based local singularity analysis. Computers & Geosciences, 118, 52–64.CrossRefGoogle Scholar
  51. Wang, J., Zuo, R., & Caers, J. (2017). Discovering geochemical patterns by factor-based cluster analysis. Journal of Geochemical Exploration, 181, 106–115.CrossRefGoogle Scholar
  52. Wang, Z., Zuo, R., & Zhang, Z. (2015c). Spatial analysis of Fe deposits in Fujian Province, China: Implications for mineral exploration. Journal of Earth Science, 26, 813–820.CrossRefGoogle Scholar
  53. Wong, T. (2015). Performance evaluation of classification algorithms by k-fold and leave-one-out cross validation. Pattern Recognition, 48, 2839–2846.CrossRefGoogle Scholar
  54. Wu, G., Zhang, D., Chen, B., & Wu, J. (2000). Transformation of Mesozoic tectonic domain and its relation to mineralization in Southeastern China: An evidence of Southwestern Fujian Province. Earth Science, 25, 390–396. (In Chinese with English abstract).Google Scholar
  55. Xie, X., Mu, X., & Ren, T. (1997). Geochemical mapping in China. Journal of Geochemical Exploration, 60, 99–113.CrossRefGoogle Scholar
  56. Xiong, C., Johnson, D. M., & Corso, J. J. (2012). Efficient max-margin metric learning. In 6th International workshop on evolution and change in data management (pp. 1–9).Google Scholar
  57. Xiong, Y., & Zuo, R. (2016). Recognition of geochemical anomalies using a deep autoencoder network. Computers & Geosciences, 86, 75–82.CrossRefGoogle Scholar
  58. Xiong, Y., & Zuo, R. (2018). GIS-based rare events logistic regression for mineral prospectivity mapping. Computers & Geosciences, 111, 18–25.CrossRefGoogle Scholar
  59. Xiong, Y., Zuo, R., Wang, K., & Wang, J. (2018). Identification of geochemical anomalies via local RX anomaly detector. Journal of Geochemical Exploration, 189, 64–71.CrossRefGoogle Scholar
  60. Yan, H., Lu, J., Deng, W., & Zhou, X. (2014). Discriminative multimetric learning for kinship verification. IEEE Transactions on Information Forensics and Security, 9, 1169–1178.CrossRefGoogle Scholar
  61. Yousefi, M. (2017). Recognition of an enhanced multi-element geochemical signature of porphyry copper deposits for vectoring into mineralized zones and delimiting exploration targets in Jiroft area, SE Iran. Ore Geology Reviews, 83, 200–214.CrossRefGoogle Scholar
  62. Yousefi, M., & Carranza, E. J. M. (2015a). Fuzzification of continuous-value spatial evidence for mineral prospectivity mapping. Computers & Geosciences, 74, 97–109.CrossRefGoogle Scholar
  63. Yousefi, M., & Carranza, E. J. M. (2015b). Prediction–area (P–A) plot and C–A fractal analysis to classify and evaluate evidential maps for mineral prospectivity modeling. Computers & Geosciences, 79, 69–81.CrossRefGoogle Scholar
  64. 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.CrossRefGoogle Scholar
  65. Yousefi, M., Kamkar-Rouhani, A., & Carranza, E. J. M. (2012). Geochemical mineralization probability index (GMPI): A new approach to generate enhanced stream sediment geochemical evidential map for increasing probability of success in mineral potential mapping. Journal of Geochemical Exploration, 115, 24–35.CrossRefGoogle Scholar
  66. Zhang, Z., Cheng, Q., Yang, J., & Hu, X. (2018). Characterization and origin of granites from the Luoyang Fe deposit, southwestern Fujian Province, South China. Journal of Geochemical Exploration, 184, 119–135.CrossRefGoogle Scholar
  67. Zhang, D., Wu, G., Di, Y., Yu, X., Shi, Y., Zhang, X., et al. (2013). SHRIMP U–Pb zircon geochronology and Nd–Sr isotopic study of the Mamianshan Group: Implications for the Neoproterozoic tectonic development of southeast China. International Geology Review, 55, 730–748.CrossRefGoogle Scholar
  68. Zhang, Z., Zuo, R., & Cheng, Q. (2015a). The mineralization age of the Makeng Fe deposit, South China: Implications from U–Pb and Sm–Nd geochronology. International Journal of Earth Sciences, 104, 663–682.CrossRefGoogle Scholar
  69. Zhang, Z., Zuo, R., & Cheng, Q. (2015b). Geological features and formation processes of the Makeng F e Deposit, China. Resource Geology, 65, 266–284.CrossRefGoogle Scholar
  70. 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, 556–572.CrossRefGoogle Scholar
  71. Zuo, R. (2011). Identifying geochemical anomalies associated with Cu and Pb–Zn skarn mineralization using principal component analysis and spectrum-area fractal modeling in the Gangdese Belt, Tibet (China). Journal of Geochemical Exploration, 111, 13–22.CrossRefGoogle Scholar
  72. Zuo, R. (2017). Machine learning of mineralization-related geochemical anomalies: A review of potential methods. Natural Resources Research, 26, 457–464.CrossRefGoogle Scholar
  73. Zuo, R., Carranza, E. J. M., & Wang, J. (2016). Spatial analysis and visualization of exploration geochemical data. Earth-Science Reviews, 158, 9–18.CrossRefGoogle Scholar
  74. Zuo, R., Cheng, Q., Agterberg, F. P., & Xia, Q. (2009). Application of singularity mapping technique to identify local anomalies using stream sediment geochemical data, a case study from Gangdese, Tibet, western China. Journal of Geochemical Exploration, 101, 225–235.CrossRefGoogle Scholar
  75. Zuo, R., & Wang, J. (2016). Fractal/multifractal modeling of geochemical data: A review. Journal of Geochemical Exploration, 164, 33–41.CrossRefGoogle Scholar
  76. Zuo, R., Xia, Q., & Wang, H. (2013). Compositional data analysis in the study of integrated geochemical anomalies associated with mineralization. Applied Geochemistry, 28, 202–211.CrossRefGoogle Scholar
  77. Zuo, R., & Xiong, Y. (2018). Big data analytics of identifying geochemical anomalies supported by machine learning methods. Natural Resources Research, 27, 1–9.CrossRefGoogle Scholar
  78. Zuo, R., Zhang, Z., Zhang, D., Carranza, E. J. M., & Wang, H. (2015). Evaluation of uncertainty in mineral prospectivity mapping due to missing evidence: A case study with skarn-type Fe deposits in Southwestern Fujian Province, China. Ore Geology Reviews, 71, 502–515.CrossRefGoogle Scholar

Copyright information

© International Association for Mathematical Geosciences 2019

Authors and Affiliations

  1. 1.State Key Laboratory of Geological Processes and Mineral ResourcesChina University of GeosciencesWuhanChina
  2. 2.Hubei Subsurface Multi-scale Imaging Key Laboratory, Institute of Geophysics and GeomaticsChina University of GeosciencesWuhanChina
  3. 3.Department of Land Surveying and Geo-InformaticsThe Hong Kong Polytechnic UniversityHong KongChina

Personalised recommendations