The utilization of Convolutional Neural Network for the analysis of Spectral Induced Polarization data through inversion techniques

Javadi Sharif, Parnian; Arab Amiri, Alireza; Tokhmechi, Behzad; Sharifi, Fereydoun

doi:10.22044/jme.2024.14527.2734

Document Type : Original Research Paper

Authors

¹ Faculty of Mining, Petroleum & Geophysics Engineering, Shahrood University of Technology, Shahrood, Iran

² Faculty of Mining, Petroleum and Geophysics, Shahrood University of Technology, Shahrood, Iran

³ Post Doctoral Researcher, University of Cologne, Cologne, Germany

https://doi.org/10.22044/jme.2024.14527.2734

Abstract

The technique referred to as Complex Resistivity (CR) or Spectral Induced Polarization (SIP) possesses the capability to distinguish between various kinds of minerals or the sources of induced polarization by utilizing the physical characteristics of minerals or polarizable inclusions. The Generalized Effective Medium Theory of Induced Polarization (GEMTip) model is utilized to derive physical characteristics from SIP data. Different inversion methods are applied for this task, though they encounter difficulties such as computational costs, non-linearity, and the intricacy of the inverse issue. To tackle this, a new inversion approach based on Deep Learning (DL) via Convolutional Neural Network (CNN) is proposed for predicting the parameters of polarizable particles from SIP data. The CNN is trained on 20000 synthetic datasets produced using the GEMTip forward model. While DL networks address non-linearities, specific modifications are applied to synthetic datasets to evaluate the influence of non-linearity and correlation on the results. In the Kervian region southwest of Saqqez city, gold mineralization is linked to quartz and pyrite minerals, with two types of pyrite recognized - coarse-grained barren and fine-grained auriferous. The existence of sulfide mineral pyrite, along with variations in pyrite sizes, presents an attractive target for SIP exploration in the investigated area. The trained network is also validated on Gravian data and effectively retrieves parameters as evidenced by the data. The proposed methodology simplifies the inversion process by estimating parameters in one step, enabling a direct and efficient procedure.

Keywords

Main Subjects

Geophysics-Geoelectric

References

[1]. Pelton, W. H., Ward, S. H., Hallof, P. G., Sill, W. R., & Nelson, P. H. (1978). Mineral discrimination and removal of inductive coupling with multifrequency IP. Geophysics, 43(3), 588-609.

[2]. Luo, Y., & Zhang, G. (1998). Theory and application of spectral induced polarization. Society of exploration geophysicists.

[3]. Emond, A. M. (2007). Electromagnetic modeling of porphyry systems from the grain-scale to the deposit-scale using the generalized effective medium theory of induced polarization (Doctoral dissertation, Department of Geology and Geophysics, University of Utah).

[4]. Goold, J. W., Cox, L. H., & Zhdanov, M. S. (2007). Spectral complex conductivity inversion of airborne electromagnetic data. In SEG Technical Program Expanded Abstracts 2007 (pp. 487-491). Society of Exploration Geophysicists.

[5]. Zhdanov, M. (2008). Generalized effective-medium theory of induced polarization. Geophysics, 73(5), F197-F211.

[6]. Sharifi, F., Arab-Amiri, A.R., Borner, R.U., Kamkar-Rouhani, A., (2018). Recovering IP effects from 1-D inversion of HEM data: case study from Kervian gold deposite (Iran), in: AEM2018 7th international workshop on airborne electromagnetic.

[7]. Sharifi, F., Arab-Amiri, A. R., Kamkar-Rouhani, A., & Börner, R. U. (2020). Development of a novel approach for recovering SIP effects from 1-D inversion of HEM data: Case study from the Alut area, northwest of Iran. Journal of Applied Geophysics, 174, 103962.

[8]. Kemna, A. (2000). Tomographic inversion of complex resistivity: Theory and application. Der Andere Verlag.

[9]. Boerner, J. H., Herdegen, V., Repke, J. U., & Spitzer, K. (2017). Spectral induced polarization of the three-phase system CO2–brine–sand under reservoir conditions. Geophysical Journal International, 208(1), 289-305.

[10]. Kemna, A., Binley, A., Cassiani, G., Niederleithinger, E., Revil, A., Slater, L., ... & Zimmermann, E. (2012). An overview of the spectral induced polarization method for near‐surface applications. Near Surface Geophysics, 10(6), 453-468.

[11]. Madsen, L. M., Fiandaca, G., Auken, E., & Christiansen, A. V. (2017). Time-domain induced polarization–an analysis of Cole–Cole parameter resolution and correlation using Markov Chain Monte Carlo inversion. Geophysical Journal International, 211(3), 1341-1353.

[12]. Bérubé, C. L., Chouteau, M., Shamsipour, P., Enkin, R. J., & Olivo, G. R. (2017). Bayesian inference of spectral induced polarization parameters for laboratory complex resistivity measurements of rocks and soils. Computers & Geosciences, 105, 51-64.

[13]. Gurin, G., Ilyin, Y., Nilov, S., Ivanov, D., Kozlov, E., & Titov, K. (2018). Induced polarization of rocks containing pyrite: Interpretation based on X-ray computed tomography. Journal of Applied Geophysics, 154, 50-63.

[14]. Fiandaca, G., Madsen, L. M., & Maurya, P. K. (2018). Re‐parameterisations of the Cole–Cole model for improved spectral inversion of induced polarization data. Near Surface Geophysics, 16(4), 385-399.

[15]. Jackson, D. D., & Matsu'Ura, M. (1985). A Bayesian approach to nonlinear inversion. Journal of Geophysical Research: Solid Earth, 90(B1), 581-591.

[16]. Ivanov, J., Miller, R. D., Xia, J., Steeples, D., & Park, C. B. (2005). The inverse problem of Refraction travel times, part I: Types of Geophysical Nonuniqueness through minimization. Pure and Applied Geophysics, 162, 447-459.

[17]. Aitchison, J. (1982). The statistical analysis of compositional data. Journal of the Royal Statistical Society: Series B (Methodological), 44(2), 139-160.

[18]. Egozcue, J. J., Pawlowsky-Glahn, V., Mateu-Figueras, G., & Barcelo-Vidal, C. (2003). Isometric logratio transformations for compositional data analysis. Mathematical geology, 35(3), 279-300.

[19]. Filzmoser, P., Hron, K., & Reimann, C. (2009). Principal component analysis for compositional data with outliers. Environmetrics: The Official Journal of the International Environmetrics Society, 20(6), 621-632.

[20]. Moghadas, D. (2020). One-dimensional deep learning inversion of electromagnetic induction data using convolutional neural network. Geophysical Journal International, 222(1), 247-259.

[21]. Hansen, T. M., & Cordua, K. S. (2017). Efficient Monte Carlo sampling of inverse problems using a neural network-based forward—Applied to GPR crosshole traveltime inversion. Geophysical Journal International, 211(3), 1524-1533.

[22]. Shahriari, M., Pardo, D., Kargaran, S., & Teijeiro, T. (2022). Automated machine learning for borehole resistivity measurements. arXiv preprint arXiv:2207.09849.

[23]. Linting, M., Meulman, J. J., Groenen, P. J., & van der Koojj, A. J. (2007). Nonlinear principal components analysis: introduction and application. Psychological methods, 12(3), 336.

[24]. Chen, X., Xia, J., Pang, J., Zhou, C., & Mi, B. (2022). Deep learning inversion of Rayleigh-wave dispersion curves with geological constraints for near-surface investigations. Geophysical Journal International, 231(1), 1-14.

[25]. Yousefi, M., Kreuzer, O. P., Nykänen, V., & Hronsky, J. M. (2019). Exploration information systems–A proposal for the future use of GIS in mineral exploration targeting. Ore Geology Reviews, 111, 103005.

[26]. Yousefi, M., & Hronsky, J. M. (2023). Translation of the function of hydrothermal mineralization-related focused fluid flux into a mappable exploration criterion for mineral exploration targeting. Applied Geochemistry, 149, 105561.

[27]. Mohajjal, M., Eshragh, A., (2008). Geological map of Kervian area. Geology survey of Iran.

[28]. Ghazanfari, M, Fazli Khani, T. & Abbasi, Z. (2010). Report on public gold exploration in the area of Kervian. Geological Survey of Iran.

[29]. Najafi Ghoshebolagh, S., Kamkar Rouhani, A., Arab Amiri, A. R., & Bizhani, H. (2021). An Exploration Model for A Gold Deposit in Kervian Area, Kurdistan Province, Iran, using a Combination of Geophysical Results with Geological Information and Other Exploratory Data. Journal of Mining and Environment, 12(2), 413-424.

[30]. Puzyrev, V. (2019). Deep learning electromagnetic inversion with convolutional neural networks. Geophysical Journal International, 218(2), 817-832.

[31]. Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.

[32]. Telford, W. M., Geldart, L. P., & Sheriff, R. E. (1990). Applied geophysics. Cambridge university press.

[33]. Sharifi, F., Arab Amiri, A. R., & Kamkar Rouhani, A. (2019). Using a combination of genetic algorithm and particle swarm optimization algorithm for GEMTIP modeling of spectral-induced polarization data. Journal of Mining and Environment, 10(2), 493-505.

[34]. Thió-Henestrosa, S., & Martín-Fernández, J. A. (2006). Detailed guide to CoDaPack: a freeware compositional software. Geological Society, London, Special Publications, 264(1), 101-118.

[35]. Compositional Data Package, )2022(. University of Girona

[36]. Stacklies, W., Redestig, H., Scholz, M., Walther, D., & Selbig, J. (2016). pcaMethods—a bioconductor package providing PCA methods for incomplete data. Bioinformatics, 23(9), 1164-1167.

[37]. Dürr, O., Sick, B., & Murina, E. (2020). Probabilistic deep learning: With python, keras, and tensorflow probability. Manning Publications.

The utilization of Convolutional Neural Network for the analysis of Spectral Induced Polarization data through inversion techniques

References

References

Volume 16, Issue 2April 2025Pages 633-651

Volume 16, Issue 2
April 2025
Pages 633-651