Data Reconstruction of Direct Current Resistivity Method Based on U-Net Convolutional Neural Network

LI Ze-Yang; MA Huan; ZHANG Hao-Nan; DAI Yi-Long; LI Yang; YANG Ying-Yu

doi:10.3969/j.issn.2097-0013.2025.01.020

2025 Vol. 41, No. 1

Article Contents

Article navigation > South China Geology > 2025 > 41(1): 240-248

Next Article Previous Article

LI Ze-Yang, MA Huan, ZHANG Hao-Nan, DAI Yi-Long, LI Yang, YANG Ying-Yu. 2025. Data Reconstruction of Direct Current Resistivity Method Based on U-Net Convolutional Neural Network. South China Geology, 41(1): 240-248. doi: 10.3969/j.issn.2097-0013.2025.01.020

Citation:

LI Ze-Yang, MA Huan, ZHANG Hao-Nan, DAI Yi-Long, LI Yang, YANG Ying-Yu. 2025. Data Reconstruction of Direct Current Resistivity Method Based on U-Net Convolutional Neural Network. South China Geology, 41(1): 240-248. doi: 10.3969/j.issn.2097-0013.2025.01.020

Data Reconstruction of Direct Current Resistivity Method Based on U-Net Convolutional Neural Network

1.
School of Geoscience, Institute of Disaster Prevention, Sanhe 065201, Hebei, China
2.
Institute of Disaster Prevention, Langfang 065000, Hebei, China
3.
School of Information Engineering, Institute of Disaster Prevention, Sanhe 065201, Hebei, China

More Information

Corresponding author: MA Huan, xiongha@hotmail.com

Received Date: 15 November 2024

Revised Date: 26 November 2024

Publish Date: 20 March 2025

Abstract

Abstract

In this paper, a data reconstruction algorithm based on Convolutional Neural Networks (CNN) is proposed for the issue of data mutation caused by humanistic noise in the geophysical resistivity method data acquisition. Given the nonlinear characteristics of the resistivity method control equation, the traditional linear interpolation techniques may lead to a decline in the accuracy of the inversion results. In this study, a CNN model is first constructed and numerical simulation of the resistivity method inversion is carried out by the three-dimensional finite difference method to generate a training dataset and a test dataset. The CNN model is trained using the training set and the U-Net network parameters are optimized based on the loss function results. By comparing the inversion results of data reconstructed with linear interpolation technique and CNN reconstruction of synthetic mutant data, the effectiveness and superiority of CNN in data reconstruction are verified. The results demonstrate that U-Net-CNN can effectively reconstruct nonlinear direct current resistivity method data, providing a new technical approach to improve the accuracy of geophysical data acquisition and the reliability of inversion results.
- Convolutional Neural Network /
- direct current resistivity method /
- numerical simulation /
- data reconstruction

FullText(HTML)

References

[1]	何睿,王润,徐航,刘帅,李彧磊,张硕,陈琨,蔡宇,陈梦源.2024.基于U-Net的湖北省露天矿山土地损毁信息提取应用[J]. 资源环境与工程,38(1):100-110. Google Scholar
[2]	胡阳,汪玲玲,陈海洋,杜子豪. 2022. 基于SE V-Net的三维地震数据断层识别方法[C]. 2022年中国石油物探学术年会论文集(下册), 514-517. Google Scholar
[3]	李明,蒋委君,董佳慧,金少锋,张宸伟,牛瑞卿.2023.基于机器学习的滑坡灾害易发性评价——以三峡库区为例[J]. 华南地质,39(3):413-427. Google Scholar
[4]	齐琪,苏英峰,王晶.2024.基于U-net上气道流体力学分析研究[J]. 医用生物力学,39(S1):422. Google Scholar
[5]	邵才瑞,关丽,张福明.2005.基于测井数据的地质曲面插值重构方法比较[J]. 测井技术,29(4):311-315+388. Google Scholar
[6]	唐云飞,但志平,洪郑天,陈永麟,程沛霖,成果,刘芳婷.2024.CAMU-Net:基于Attention U-Net的视网膜血管分割改进模型[J]. 中国医学物理学杂志,41(8):960-968. Google Scholar
[7]	陶涛,韩鹏,马欢,谭捍东.2024.时移电阻率法三维反演研究[J]. 地球物理学报,67(10):3973-3988. doi: 10.6038/cjg2023R0297 CrossRef Google Scholar
[8]	王方,熊杰,田慧潇,李思平,康佳帅.2024.基于深度学习的大地电磁二维反演方法[J]. 地质科技通报,43(2):344-354. Google Scholar
[9]	吴佳伟. 2023. 基于径向基函数的大地电磁数据重构[D]. 中国地质大学(北京)硕士学位论文. Google Scholar
[10]	邢强,韩爱香.2013.基于压缩感知的过套管电阻率数据重构方法研究[J]. 石油仪器,27(1):46-48+9. Google Scholar
[11]	颜钟. 2012. 基于BP人工神经网络的高密度电法反演理论应用研究[D]. 长江科学院硕士学位论文. Google Scholar
[12]	俞建宝,陈高,李正文,张杨.2009.基于双谱信号重构的物探数据插值方法[J]. 勘探地球物理进展,32(5):326-329+307. Google Scholar
[13]	张岩,周一帆,宋利伟,董宏丽.2023.基于物理约束U-Net网络的地震数据低频延拓[J]. 石油地球物理勘探,58(1):31-45. Google Scholar
[14]	张喆,马福恒,霍吉祥.2024.基于BP神经网络的高密度电法在水库清淤扩容坝后排泥区围堰探测中的应用[J]. 水电能源科学,42(5):174-178. Google Scholar
[15]	张瀚文,曹维娟,罗刚银,江浩,邱香,许杰,史蓉蓉,郑然.2024.基于改进型U-Net的变色油墨血浆判别模型[J]. 南京医科大学学报(自然科学版),44(9):1179-1189. doi: 10.7655/NYDXBNSN231104 CrossRef Google Scholar
[16]	Du H K, Ren Z Y, Tang J T. 2016. A finite-volume approach for 2D magnetotellurics modeling with arbitrary topographies[J]. Studia Geophysica et Geodaetica, 60(2): 332-347. doi: 10.1007/s11200-014-1041-9 CrossRef Google Scholar
[17]	Jiang F B, Dong L, Dai Q W. 2018. Electrical resistivity imaging inversion: An ISFLA trained kernel principal component wavelet neural network approach[J]. Neural Networks, 104: 114-123. doi: 10.1016/j.neunet.2018.04.012 CrossRef Google Scholar
[18]	Lecun Y, Bottou L, Bengio Y, Haffner P. 1998. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 86(11): 2278-2324. doi: 10.1109/5.726791 CrossRef Google Scholar
[19]	Loke M H, Chamvers J E, Rucker D F, Kuras O, Wilkinson P B. 2013. Recent developments in the direct-current geoelectrical imaging method[J]. Journal of Applied Geophysics, 95: 135-156. doi: 10.1016/j.jappgeo.2013.02.017 CrossRef Google Scholar
[20]	Ren Z Y, Tang J T. 2010. 3D direct current resistivity modeling with unstructured mesh by adaptive finite-element method[J]. Geophysics: Journal of the Society of Exploration Geophysicists, 75(1): H7-H17. Google Scholar
[21]	Wu X P, Xiao Y F, Qi C, Wang T T. 2003. Computations of secondary potential for 3D DC resistivity modelling using an incomplete Choleski conjugate - gradient method[J]. Geophysical Prospecting, 51(6): 567-577. doi: 10.1046/j.1365-2478.2003.00392.x CrossRef Google Scholar