Applications of deep convolutional neural networks in prospecting prediction based on two-dimensional geological big data

  • Shi Li
  • Jianping ChenEmail author
  • Jie Xiang
Deep Learning & Neural Computing for Intelligent Sensing and Control


There are many challenges in the task of predicting ore deposits from big data repositories. The data are inherently complex and of great significance to the intervenient spatial relevance of deposits. The characteristics of the data make it difficult to use machine learning algorithms for the quantitative prediction of mineral resources. There are considerable interest and value in extracting spatial distribution characteristics from two-dimensional (2-d) ore-controlling factor layers under different metallogenic conditions. In this paper we undertake such analysis using a deep convolutional neural network algorithm named AlexNet. Training on the 2-d mineral prediction and classification model is performed using data from the Songtao–Huayuan sedimentary manganese deposit. It mines the coupling correlation between the spatial distribution of chemical elements, sedimentary facies, the outcrop of Datangpo Formation, faults, water system, and the areas where manganese ore bodies are present, as well as the correlation among different ore-controlling factors by employing the AlexNet networks. By comparing the training loss, training accuracy, verification accuracy, and recall of models trained by different scales of grids and different combinations of ore-controlling factor layers, we further discuss the most appropriate scale division and the optimal combination of ore-controlling factors to make the model achieve its strongest robustness. It is found that the prediction performance of AlexNet networks reaches its peak when selecting a grid division of 200 pixels × 200 pixels (the actual distance is 10 km × 10 km) and inputting the distribution layers of 21 chemical elements maps, lithofacies–paleogeographic map, formation and tectonic map, outcrop map of Datangpo Formation, and water system map. The training loss, training accuracy, verification accuracy, and recall of the optimal model are 0.0000001, 100.00%, 86.21%, and 91.67%, respectively. The proposed method is successfully applied to the 2-d metallogenic prediction in Songtao–Huayuan study area. And five metallogenic prospective areas from A to E are delineated with large probability for potential ore bodies.


Geological big data Prospecting prediction Convolutional neural networks Songtao–Huayuan Mn deposit 



This research was financially supported by the Chinese MOST project “Methods and Models for Quantitative Prediction of Deep Metallogenic Geological Anomalies” (2017YFC0601502).

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.


  1. 1.
    Zhao PD (2015) Digital mineral exploration and quantitative evaluation in the big data age. Geol Bull China 34(7):1255–1259Google Scholar
  2. 2.
    Xiao KY, Sun L, Li N et al (2015) Mineral resources assessment under the thought of big data. Geol Bull China 34(7):1266–1272Google Scholar
  3. 3.
    Chen JP, Li J, Cui N et al (2015) The construction and application of geological cloud under the big data background. Geol Bull China 34(7):1260–1265Google Scholar
  4. 4.
    Yu PP, Chen JP, Chai FS et al (2015) Research on model-driven quantitative prediction and evaluation of mineral resources based on geological big data concept. Geol Bull China 34(7):1333–1343Google Scholar
  5. 5.
    Zheng X, Li JC, Wang X et al (2015) Construction of the national geological information service system in the age of big data. Geol Bull China 34(7):1316–1322Google Scholar
  6. 6.
    Li S, Chen JP, Xiang J (2018) Prospecting information extraction by text mining based on convolutional neural networks—a case study of the Lala copper deposit, China. IEEE Access 6:52286–52297CrossRefGoogle Scholar
  7. 7.
    Yong LW, Jian ZJ, Chen JP et al (2017) Construction and prediction of prospecting model based on big data intelligence. China Min Mag 26(9):79–84Google Scholar
  8. 8.
    Zuo RG, Xiong YH (2018) Big data analytics of identifying geochemical anomalies supported by machine learning methods. Nat Resour Res 27(1):5–13CrossRefGoogle Scholar
  9. 9.
    Twarakavi NKC, Misra D, Bandopadhyay S (2006) Prediction of arsenic in bedrock derived stream sediments at a gold mine site under conditions of sparse data. Nat Resour Res 15(1):15–26CrossRefGoogle Scholar
  10. 10.
    Chen M, Mao S, Liu Y (2014) Big data: a survey. Mob Netw Appl 19(2):171–209CrossRefGoogle Scholar
  11. 11.
    O’Brien JJ, Spry PG, Nettleton D et al (2015) Using random forests to distinguish gahnite compositions as an exploration guide to Broken Hill-type Pb–Zn–Ag deposits in the Broken Hill domain, Australia. J Geochem Explor 149:74–86CrossRefGoogle Scholar
  12. 12.
    Gonbadi AM, Tabatabaei SH, Carranza EJM (2015) Supervised geochemical anomaly detection by pattern recognition. J Geochem Explor 157:81–91CrossRefGoogle Scholar
  13. 13.
    Kirkwood C, Cave M, Beamish D et al (2016) A machine learning approach to geochemical mapping. J Geochem Explor 167:49–61CrossRefGoogle Scholar
  14. 14.
    Zhao JN, Chen SY, Zuo RG (2016) Identifying geochemical anomalies associated with Au–Cu mineralization using multifractal and artificial neural network models in the Ningqiang district, Shaanxi, China. J Geochem Explor 164:54–64CrossRefGoogle Scholar
  15. 15.
    Xiong YH, Zuo RG (2016) Recognition of geochemical anomalies using a deep autoencoder network. Comput Geosci 86:75–82CrossRefGoogle Scholar
  16. 16.
    Chen YL, Wu W (2017) Application of one-class support vector machine to quickly identify multivariate anomalies from geochemical exploration data. Geochem Explor Environ Anal 17(3):231–238CrossRefGoogle Scholar
  17. 17.
    Chen JP, Li J, Xie S et al (2017) China geological big data research status. J Geol 41(3):353–366Google Scholar
  18. 18.
    Chen SM (2012) Research of multiple geoscience information prospecting prediction in Xikuangshan antimony ore field. China University of Geosciences, BeijingGoogle Scholar
  19. 19.
    Chen JP (2008) The research and application of neural network pattern recognition technique for oil and gas geochemistry base on MATLAB. China University of Geosciences, BeijingGoogle Scholar
  20. 20.
    Yang H (2016) Research and application of the combination of deep learning and principal component analysis. Chengdu University of Technology, ChengduGoogle Scholar
  21. 21.
    Albora AM, Ucan ON, Ozmen A et al (2001) Separation of Bouguer anomaly map using cellular neural network. J Appl Geophys 46(2):129–142CrossRefGoogle Scholar
  22. 22.
    Liu Z, Liu MC, Wei W et al (2010) Gravity anomaly separation based on cellular neural network. J China Univ Pet (Ed Nat Sci) 34(4):57–61Google Scholar
  23. 23.
    Li C, Jiang YL, Hu MK et al (2015) Study and application of gravity anomaly separation by cellular neural networks. Comput Tech Geophys Geochem Explor 37(1):16–21Google Scholar
  24. 24.
    Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313(5786):504–507MathSciNetCrossRefzbMATHGoogle Scholar
  25. 25.
    Liu YP, Zhu LX, Zhou YZ (2018) Application of convolutional neural network in prospecting prediction of ore deposits: taking the Zhaojikou Pb–Zn ore deposit in Anhui Province as a case. Acta Petrol Sin 34(11):3217–3224Google Scholar
  26. 26.
    Dang Y, Zhang JX, Deng KZ et al (2017) Study on the evaluation of land cover classification using remote sensing images based on AlexNet. J Geo-Inf Sci 19(11):1530–1537Google Scholar
  27. 27.
    Zhou Q, Du YS, Yuan LJ et al (2017) Exploration models of ancient natural gas seep sedimentary-type manganese ore deposit: a case study of the Nanhua Period “Datangpo” type manganese ore in the conjunction area of Guizhou, Hunan and Chongqing. Acta Geol Sin 91(10):2285–2298Google Scholar
  28. 28.
    Liu XF, Wang QS, Gao XJ (1989) Manganese ore geology in Guizhou. Guizhou People’s Publishing House, GuiyangGoogle Scholar
  29. 29.
    Wang YG, Wang LX, Zhu SC et al (1985) Sedimentary environment and manganese formation of the Datangpo formation in eastern Guizhou. Guizhou People’s Publishing House, GuiyangGoogle Scholar
  30. 30.
    He MH (1993) Petrographical facies and paleogeography and manganese: forming conditions of Datangpo epoch of early Sinian period in Songtao and adjacent areas. Guizhou Geol 10(1):62–67Google Scholar
  31. 31.
    He MH (2001) Sedimentary facies and palaeogeography during the early Sinian and potential of the rhodochrosite deposits in northeastern Guizhou and its adjacent areas. Sediment Geol Tethyan Geol 21(3):39–47Google Scholar
  32. 32.
    Xiang WQ, Xiao YK (2013) Geological characteristics and metallogenic regularity for Nanhuan Datangpo manganese deposits from Tongren–Songtao region. J Southwest Univ Sci Technol 28(4):31–38Google Scholar
  33. 33.
    Mou J, Wang AH, Huang DG (2014) Sedimentary micro-facies features and prospecting prediction of manganese-bearing rock series in Songtao–Yinjiang area of Guizhou. Guizhou Geol 31(2):99–104Google Scholar
  34. 34.
    Kuang WL, Li XY, Yang SX (2014) The mineralization geological characteristics and genesis of Minle type manganese deposits in northwestern of Hunan Province. Chin J Geol 49(1):305–323Google Scholar
  35. 35.
    Wang YG (1990) Old hot brine manganese deposits in a shallow-sea rift basin: an example from the Sinian manganese deposits in the Wuling mountain area. Sediment Geol Tethyan Geol 1:38–45Google Scholar
  36. 36.
    Zhao DX (1990) Intraclastic structures and gravity flow sedimentation of rhodochrosite ore in Sinian Datangpo formation. Sci Geol Sin 2:149–157Google Scholar
  37. 37.
    Liu BJ, Yu GM, Chen CS (1993) Ophiolite submarine fan of the Shigaze Group in the Yarlung Zangbo suture zone and its plate tectonic significance. Sediment Geol Tethyan Geol 13(2):16–27Google Scholar
  38. 38.
    Zhou Q, Du YS (2012) Ancient natural gas leakage and manganese mineralization: a case study of the Nanhua Datangpo manganese deposits in eastern Guizhou. Geological Publishing House, Beijing, pp 2–10Google Scholar
  39. 39.
    Zhou Q, Du YS, Qin Y (2013) Ancient natural gas seepage sedimentary-type manganese metallogenic system and ore-forming model: a case study of “Datangpo type” manganese deposits formed in rift basin of Nanhua Period along Guizhou–Hunan–Chongqing border area. Miner Depos 32(3):457–466Google Scholar
  40. 40.
    Du YS, Zhou Q, Yu WC et al (2015) Linking the Cryo-genian manganese matallogenic process in the south-east margin of Yangtze block to break-up of Rodinia supercontinent and Sturtian glaciation. Geol Sci Technol Inf 34(6):1–7Google Scholar
  41. 41.
    Hobert JP (2011) The data augmentation algorithm: theory and methodology. In: Brooks S, Gelman A, Jones G et al (eds) Handbook of Markov chain Monte Carlo. CRC Press, London, pp 253–293Google Scholar
  42. 42.
    Salehinejad H, Valaee S, Dowdell T et al (2018) Image augmentation using radial transform for training deep neural networks. In: IEEE international conference on acoustics, speech and signal processing. IEEE Press, New York, pp 3016–3020Google Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  1. 1.School of Earth Sciences and ResourcesChina University of Geosciences (Beijing)BeijingChina
  2. 2.Land Resources Information Development and Research Key Laboratory of BeijingBeijingChina
  3. 3.MNR Key Laboratory of Metallogeny and Mineral AssessmentInstitute of Mineral Resources, CAGSBeijingChina

Personalised recommendations