Pure and Applied Geophysics

, Volume 175, Issue 12, pp 4427–4447 | Cite as

Inversion of Density Interfaces Using the Pseudo-Backpropagation Neural Network Method

  • Xiaohong Chen
  • Yukun DuEmail author
  • Zhan Liu
  • Wenju Zhao
  • Xiaocheng Chen


This paper presents a new pseudo-backpropagation (BP) neural network method that can invert multi-density interfaces at one time. The new method is based on the conventional forward modeling and inverse modeling theories in addition to conventional pseudo-BP neural network arithmetic. A 3D inversion model for gravity anomalies of multi-density interfaces using the pseudo-BP neural network method is constructed after analyzing the structure and function of the artificial neural network. The corresponding iterative inverse formula of the space field is presented at the same time. Based on trials of gravity anomalies and density noise, the influence of the two kinds of noise on the inverse result is discussed and the scale of noise requested for the stability of the arithmetic is analyzed. The effects of the initial model on the reduction of the ambiguity of the result and improvement of the precision of inversion are discussed. The correctness and validity of the method were verified by the 3D model of the three interfaces. 3D inversion was performed on the observed gravity anomaly data of the Okinawa trough using the program presented herein. The Tertiary basement and Moho depth were obtained from the inversion results, which also testify the adaptability of the method. This study has made a useful attempt for the inversion of gravity density interfaces.


Three-dimensional gravity inversion density interfaces pseudo-BP neural network southern Okinawa trough Moho 



Financial support for this work was provided by the Fundamental Research Funds for the Central Universities (Grant no. 18CX02072A) and the National High Technology Research and Development Program of China (Grant no. 2006AA06Z204). The authors wish to express thanks to Yuguo Li for English manuscript revision.


  1. Albora, A. M., Özmen, A., & Uçan, O. N. (2001). Residual separation of magnetic fields using a cellular neural network approach. Pure and Applied Geophysics, 158(9), 1797–1818.CrossRefGoogle Scholar
  2. Ashida, Y. (1996). Data processing of reflection seismic data by use of neural network. Journal of Applied Geophysics, 35(2–3), 89–98.CrossRefGoogle Scholar
  3. Baan, M., Der, Van, & Christian, J. (2000). Neural networks in geophysical applications. Geophysics, 65(4), 1032–1047.CrossRefGoogle Scholar
  4. Bescoby, D., Cawley, G., & Chroston, P. (2006). Enhanced interpretation of magnetic survey data from archaeological sites using artificial neural networks. Geohysics, 71(5), H45–H53.CrossRefGoogle Scholar
  5. Chua, L. O., & Yang, L. (1988). Cellular neural networks: Theory. IEEE Transactions on Circuits and Systems, 35(10), 1257–1272.CrossRefGoogle Scholar
  6. Elawadi, E., Ahmed, A., & Ushijima, K. (2001). Detection of cavities and tunnels from gravity data using a neural network. Exploration Geophysics, 32(3/4), 204–208.Google Scholar
  7. El-Qady, G., & Ushijima, K. (2001). Inversion of dc resistivity data using neural networks. Geophysical Prospecting, 49(4), 417–430.CrossRefGoogle Scholar
  8. Gao, D. Z., Zhao, J. H., Bo, Y. L., Tang, J., & Jie, W. S. (2004). A profile study of gravitative-magnetic and seismic comprehensive survey in the east china sea. Chinese Journal of Geophysics, 47(5), 853–861.Google Scholar
  9. Guan, Z. N., Hou, J. S., Huang, L. P., & Yao, C. L. (1998). Inversion of gravity and magnetic anomalies using pseudo-bp neural network method and its application. Chinese Journal of Geophysics, 2, 015.Google Scholar
  10. Han, B., Zhang, X. H., Pei, J. X., & Zhang, W. G. (2007). Characteristics of crust-mantle in east China sea and adjacent regions. Progress in Geophysics, 22(2), 376–382.Google Scholar
  11. Huang, Z. (2008). Gravity, magnetic and electrical prospecting of petroleum. Dong Ying: China University of Petroleum Press.Google Scholar
  12. Huang, Z., Shimeld, J., Williamson, M., & Katsube, J. (1996). Permeability prediction with artificial neural network modeling in the venture gas field, offshore eastern canada. Geophysics, 61(2), 422–436.CrossRefGoogle Scholar
  13. Liang, R. C., Wang, S. G., & Wu, J. L. (2001). Preliminary study on geophysical field and the new crust in the middle of the Okinawa trough. Marine Geology and Quaternary Geology, 21(1), 57–64.Google Scholar
  14. Lin, C. S., Wang, S. C., & Wang, Y. (1999). The magnetic basement and geological structure of the southern Okinawa trough and its vicinity. Acta Oceanologica Sinica, 6, 006.Google Scholar
  15. Liu, Z., Sun, L. P., Fan, F. X., Wu, S. G., & Zhao, W. J. (2006). The basement tectonics in north of the Okinawa trough. Progress in Geophysics, 21(4), 1086–1092.Google Scholar
  16. Meng, L., Zhang, X. H., Wen, Z. H., Meng, X. J., & Wang, M. J. (2016). Thermal modeling of tectonic activity contrast between the south part and the middle and north parts of the Okinawa trough. Chinese Journal of Geophysics, 59(9), 3302–3317.Google Scholar
  17. Nagy, D., Papp, G., & Benedek, J. (2000). The gravitational potential and its derivatives for the prism. Journal of Geodesy, 74(7–8), 552–560.CrossRefGoogle Scholar
  18. Oldenburg, D. W. (1974). The inversion and interpretation of gravity anomalies. Geophysics, 39(4), 526–536.CrossRefGoogle Scholar
  19. Osman, O., Albora, A. M., & Ucan, O. N. (2007). Forward modeling with forced neural networks for gravity anomaly profıle. Mathematical Geology, 39(6), 593–605.CrossRefGoogle Scholar
  20. Parker, R. L. (1973). The rapid calculation of potential anomalies. Geophysical Journal of the Royal Astronomical Society, 31(31), 447–455.CrossRefGoogle Scholar
  21. Poulton, M. M., Sternberg, B. K., & Glass, C. E. (1992). Neural network pattern recognition of subsurface em images. Journal of Applied Geophysics, 29(1), 21–36.CrossRefGoogle Scholar
  22. Reguzzoni, M., & Sampietro, D. (2015). Gemma: An earth crustal model based on Goce satellite data. International Journal of Applied Earth Observation and Geoinformation, 35, 31–43.CrossRefGoogle Scholar
  23. Richard, J. B. (1995). Potential theory in gravity and magnetic applications. Cambridge: Cambridge University Press.Google Scholar
  24. Sampietro, D., & Sansò, F. (2012). Uniqueness theorems for inverse gravimetric problems. Berlin: Springer.CrossRefGoogle Scholar
  25. Spichak, V., & Popova, I. (2002). Artificial neural network inversion of magnetotelluric data in terms of three-dimensional earth macroparameters. Geophysical Journal International, 142(1), 15–26.CrossRefGoogle Scholar
  26. Taylor, C. L., & Vasco, D. W. (1999). Inversion of gravity gradiometry data using a neural network 60th ann. SEG Technical Program Expanded Abstracts, 9(1), 1779.Google Scholar
  27. Wiener, J. M. (1991). Predicting carbonate permeabilities from wireline logs using a back-propagation neural network. SEG Technical Program Expanded Abstracts, 10(1), 1646.Google Scholar
  28. Yang, W. D., Wang, Z. Y., & Zeng, J. L. (2001). Geologic features of the Okinawa trough axis. Marine Geology & Quaternary Geology, 21(2), 1–6.Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Xiaohong Chen
    • 1
    • 2
  • Yukun Du
    • 3
    Email author
  • Zhan Liu
    • 1
    • 2
  • Wenju Zhao
    • 4
  • Xiaocheng Chen
    • 5
  1. 1.School of GeosciencesChina University of Petroleum (East China)QingdaoChina
  2. 2.Laboratory for Marine Mineral ResourcesQingdao National Laboratory for Marine Science and TechnologyQingdaoChina
  3. 3.Research Institute of Unconventional Oil and Gas and Renewable EnergyChina University of Petroleum (East China)QingdaoChina
  4. 4.China National Petroleum CorporationZhuozhouChina
  5. 5.Marine and Environmental Geology Department, Qingdao Geo-exploration Academy of ChinaMetallurgical Geology BureauQingdaoChina

Personalised recommendations