Parameter inversion and application of the Cole-Cole model for time-domain induced polarization spectra based on the backpropagation neural network
YANG Hai-Ming1(), YAO Wei-Xing1(), TANG Su1, PAN Zhan-Chao1,2, GUAN Li-Wei1,2
1. China Geological Survey Urumqi Comprehensive Survey Center on Natural Resources, Urumqi 830057, China 2. Innovation Base of Metallogenic Prediction and Prospecting in Central Asia Orogenic Belt, Urumqi 830057, China
The spectral parameters of the Cole-Cole model can improve the resolution of comprehensive interpretation of time-domain induced polarization (IP) data, contributing somewhat to the exploration of metal deposits. Applying the backpropagation neural network (BPNN) model to the prediction and inversion of spectral parameters can avoid high computational complexity to improve the inversion speed. Moreover, the BPNN model can fully explore the utilization efficiency of time-domain IP data to enrich the characteristic information of subsurface ore bodies. Based on this, this study derived the mathematical expression of the time-domain apparent polarizability attenuation curve using the digital filtering algorithm. With the mathematical expression as the forward/inverse model, this study comparatively analyzed the impacts of four factors-the sample size of the training set, the number of neurons in the input layer, the node number of hidden layers, and the number of hidden layers-on the training and inversion effects of the BPNN model, determining the optimal model. Furthermore, this study trained the BPNN model using time-domain IP data from eight time windows. Finally, this study applied the trained BPNN model for prediction and inversion based on the measured time-domain IP data. The results indicate that the BPNN model is feasible in inverting spectral parameters based on both theoretical and measured datasets, manifesting high inversion accuracy and minor errors. Overall, the results of this study can assist in distinguishing paragenetic and associated minerals and reducing misinterpretation.
杨海明, 姚卫星, 唐塑, 潘展超, 关力伟. 基于BP神经网络的时域激电谱Cole-Cole模型参数反演及应用[J]. 物探与化探, 2025, 49(2): 433-440.
YANG Hai-Ming, YAO Wei-Xing, TANG Su, PAN Zhan-Chao, GUAN Li-Wei. Parameter inversion and application of the Cole-Cole model for time-domain induced polarization spectra based on the backpropagation neural network. Geophysical and Geochemical Exploration, 2025, 49(2): 433-440.
Grissemann C, Rammlmair D, Siegwart C, et al. Spectral induced polarisation linked to image analyses:A new approach[C]// Applied mineralogy:In research,economy,technology,ecology and culture,vol.2:Sixth international congress on applied mineralogy, 2000.
[2]
Pelton W H, Ward S H, Hallof P G, et al. Mineral discrimination and removal of inductive coupling with multifrequency IP[J]. Geophysics, 1978, 43(3):588.
[3]
Major J, Silic J. Restrictions on the use of Cole-Cole dispersion models in complex resistivity interpretation[J]. Geophysics, 1981, 46(6):916-931.
[4]
Carlson N, Hughes L, Zonge K. Hydrocarbon exploration using induced polarization apparent resistivity,and electromagnetic scattering[J]. Geophysical Prospecting for Petrole, 1983, 47(4):451-451.
Luo Y Z, Fang S. An approximate inversion of the apparent complex resistivity spectrum[J]. Earth Science Journal, 1986, 11,(1):93-102.
[6]
Ghorbani A, Camerlynck C, Florsch N, et al. Bayesian inference of the Cole-Cole parameters from time- and frequency- domain induced polarization[J]. Geophysical Prospecting, 2007, 55:589-605.
[7]
梁盛军. 复电阻率法三维正反演问题研究[D]. 北京: 中国地质大学(北京), 2011.
[7]
Liang S J. Research on complex resistivity 3D modeling and inversing problem[D]. Beijing: China University of Geosciences(Beijing), 2011.
[8]
Mark H, Bülent T. 1D and 2D Cole-Cole inversion of time-domain induced polarization data[J]. Geophysical Prospecting, 2007, 55:117-133.
Luo R L, Li Y N. Spectrum parameters of Cole-Cole model inversion based on time-domain IP data[C]// The 9th China International Symposium on Electromagnetics of the Earth,Guilin, 2009:285-288.
Peng W, Liang Y Q, Zhang C et al. The application of Cole-Cole model parameters to the time domain induced polarization prospecting[J]. Geophysical and Geochemical Exploration, 2018, 42(3):513-517.
[11]
李密. 基于时间域激电数据的频谱参数反演研究与应用[D]. 广西: 桂林理工大学, 2011.
[11]
Li M. Time domain induced polarization data based on the spectral parameters and application of inversion[D]. Guangxi: Guilin University of Technology, 2011.
[12]
岑海波. 基于人工智能的时域激电解释研究[D]. 广西: 桂林理工大学, 2023.
[12]
Cen H B. Research on time domain IP interpretation based on artificial intelligence[D]. Guangxi: Guilin University of Technology, 2023.
Li J, Wang X M, Zhang Y H, et al. Research on the seismic phase picking method based on the deep convolution neural network[J]. Chinese Journal of Geophysics, 2020, 63(4):1591-1606.
Yang K, Liu C, He J L, et al. Research on magnetotelluric time series classification based on artificial neural network[J]. Geophysical and Geochemical Exploration, 2024, 48(2):498-507.
Zhao J, Ran Q, Zhu B H, et al. A method for identifying faults based on well-controlled multi-attribute fusion using a feedforward neural network[J]. Geophysical and Geochemical Exploration, 2024, 48(4):1045-1053.
[16]
Guptasarma D. Computation of the time-domain response of a polarizable ground[J]. Geophysics, 1982, 47(11):534-541.
[17]
刘瑞泽. 时间域谱激电法正演与谱特征参数最优化计算研究[D]. 河北: 河北地质大学, 2022.
[17]
Liu R Z. Research on time-domain spectral induced polarization methodforward modeling and optimal calculation of spectralcharacteristic parameters[D]. Hebei: Hebei GEO University, 2022.
[18]
傅良魁. 电法勘探教程[M]. 北京: 地质出版社, 1983.
[18]
Fu L K. Electrical Exploration Tutorial[M]. Beijing: Geological Publishing House, 1983.
[19]
李金铭. 激发极化法方法技术指南[M]. 北京: 地质出版社, 2004.
[19]
Li J M. Technical Specifications for Induced Polarization Method[M]. Beijing: Geological Publishing House, 2004.
Luo Y Z, Wu Z X. The application of frequency dependent factor in spectral induced polarization method[J]. Chinese Journal of Geophysics, 1992, 35(4):490-500.
