A U-Net-based denoising method for semi-airborne transient electromagnetic data and its application

Authors

LIU Dong, Institute of Geotechnical and Underground Engineering, Shandong University, Jinan 250061, China; Guangxi Communications Investment Group CO., Ltd., Nanning 530022, China; Guangxi Longma Expressway Co., Ltd., Nanning 530022, ChinaFollow
FENG Hao, Institute of Geotechnical and Underground Engineering, Shandong University, Jinan 250061, China
WANG Yongxin, Institute of Geotechnical and Underground Engineering, Shandong University, Jinan 250061, China; Shandong Provincial Communications Planning and Design Institute Group CO., LTD., Jinan 250101, China
ZHOU Xiaosheng, Institute of Geotechnical and Underground Engineering, Shandong University, Jinan 250061, China; Guangxi Communications Investment Group CO., Ltd., Nanning 530022, China; Guangxi Longma Expressway Co., Ltd., Nanning 530022, China
YAO Yuhong, Guangxi Communications Investment Group CO., Ltd., Nanning 530022, China; Guangxi Longma Expressway Co., Ltd., Nanning 530022, China
SUN Huaifeng, Institute of Geotechnical and Underground Engineering, Shandong University, Jinan 250061, ChinaFollow

Abstract

Objective and Methods The semi-airborne transient electromagnetic (SATEM) method, an efficient geophysical exploration technique, has been extensively applied to mineral resource exploration, groundwater surveys, and geothermal resource surveys. However, the collected data are frequently susceptible to noise interference, significantly affecting the accuracy of subsequent data processing and interpretation. To address issues such as residual noise and the loss of effective signals, enhance denoising effects, and reduce the influence of subjective factors, this study proposed a denoising method for SATEM data based on the U-Net deep learning architecture (also referred to as the U-Net-based method) by applying U-Net to SATEM data denoising. In this method, a U-shaped encoder-decoder architecture is employed to automatically learn and extract noise features from the data through an end-to-end training approach. The encoder learns and extracts noise features from data, while the decoder reconstructs the noise features and restores denoised data. By introducing skip connections to the symmetric layers in the encoder and the decoder, the U-Net-based method effectively integrates the low-level features bearing rich spatial information with the high-level features containing semantic information, thus achieving accurate denoising. Results and Conclusions Practical calculation cases indicate that the U-Net-based method can improve the signal-to-noise ratio (SNR) of data by approximately 10 dB after denoising, proving significant advantages of denoising SATEM data compared to traditional denoising methods. This method has been employed to denoise the measured data of the No.2 Fenghuang tunnel in the Laibin-Du'an section of the Hezhou-Bama expressway in Guangxi, significantly enhancing the interpretability of the multi-channel diagrams and apparent resistivity images after data denoising. Therefore, the U-Net-based method holds great practical significance for SATEM data denoising, thus providing effective technical support for future geophysical exploration.

Keywords

semi-airborne transient electromagnetic (SATEM) method, deep learning, U-Net, denoising, complex noise

DOI

10.12363/issn.1001-1986.24.05.0303

Recommended Citation

LIU Dong, FENG Hao, WANG Yongxin, et al. (2025) "A U-Net-based denoising method for semi-airborne transient electromagnetic data and its application," Coal Geology & Exploration: Vol. 53: Iss. 1, Article 19.
DOI: 10.12363/issn.1001-1986.24.05.0303
Available at: https://cge.researchcommons.org/journal/vol53/iss1/19

Reference

[1] MOGI T，KUSUNOKI K，KAIEDA H，et al. Grounded electrical-source airborne transient electromagnetic (GREATEM) survey of Mount Bandai，north-eastern Japan[J]. Exploration Geophysics，2009，40(1)：1−7.

[2] 嵇艳鞠，王远，徐江，等. 无人飞艇长导线源时域地空电磁勘探系统及其应用[J]. 地球物理学报，2013，56(11)：3640−3650.

JI Yanju，WANG Yuan，XU Jiang，et al. Development and application of the grounded long wire source airborne electromagnetic exploration system based on an unmanned airship[J]. Chinese Journal of Geophysics，2013，56(11)：3640−3650.

[3] 方涛，张建军，付成群，等. 无人机地空瞬变电磁系统在冶山地下巷道探测中的应用[J]. 地球物理学进展，2015，30(5)：2366−2372.

FANG Tao，ZHANG Jianjun，FU Chengqun，et al. Using ground-airborne transient electromagnetic system on unmanned aerial vehicle detecting Yeshan underground tunnels[J]. Progress in Geophysics，2015，30(5)：2366−2372.

[4] 刘富波，李巨涛，刘丽华，等. 无人机平台半航空瞬变电磁勘探系统及其应用[J]. 地球物理学进展，2017，32(5)：2222−2229.

LIU Fubo，LI Jutao，LIU Lihua，et al. Development and application of a new semi-airborne transient electromagnetic system with UAV platform[J]. Progress in Geophysics，2017，32(5)：2222−2229.

[5] WU Xin，XUE Guoqiang，FANG Guangyou，et al. The development and applications of the semi-airborne electromagnetic system in China[J]. IEEE Access，2019，7：104956−104966.

[6] 叶琼瑶，张军，赵友超，等. 岩溶隧道勘察接地源半航空瞬变电磁三维响应规律研究[J]. 应用基础与工程科学学报，2021，29(5)：1108−1123.

YE Qiongyao，ZHANG Jun，ZHAO Youchao，et al. Study on the three-dimensional response law of semi-airborne transient electromagnetic of grounding source for karst tunnel investigation[J]. Journal of Basic Science and Engineering，2021，29(5)：1108−1123.

[7] 林君，薛国强，李貅. 半航空电磁探测方法技术创新思考[J]. 地球物理学报，2021，64(9)：2995−3004.

LIN Jun，XUE Guoqiang，LI Xiu. Technological innovation of semi-airborne electromagnetic detection method[J]. Chinese Journal of Geophysics，2021，64(9)：2995−3004.

[8] JI Yanju，LI Dongsheng，YUAN Guiyang，et al. Noise reduction of time domain electromagnetic data：Application of a combined wavelet denoising method[J]. Radio Science，2016，51(6)：680−689.

[9] 岳望. 基于核函数的航空瞬变电磁去噪方法研究[D]. 成都：成都理工大学，2018.

YUE Wang. Research on airborne transient electromagnetic denoising method based on kernel function[D]. Chengdu：Chengdu University of Technology，2018.

[10] 朱通. 基于Hilbert-Huang变换的瞬变电磁噪声压制研究与应用[D]. 西安：长安大学，2018.

ZHU Tong. Research and application of transient electromagnetic noise suppression based on Hilbert-Huang transform[D]. Xi’an：Chang’an University，2018.

[11] 毛鑫鑫，毛立峰，杨聪，等. 半航空瞬变电磁数据小波降噪方法研究[J]. 地球物理学进展，2021，36(3)：1287−1296.

MAO Xinxin，MAO Lifeng，YANG Cong，et al. Research on wavelet denoising method for semi-airborne transient electromagnetic data[J]. Progress in Geophysics，2021，36(3)：1287−1296.

[12] SUN Huaifeng，CHEN Chengdong，YANG Yang，et al. Motion noise remove for secondary-field semi-airborne transient electromagnetic data[J]. Journal of Applied Geophysics，2022，202：104676.

[13] 宋辉，高洋，陈伟，等. 基于卷积降噪自编码器的地震数据去噪[J]. 石油地球物理勘探，2020，55(6)：1210−1219.

SONG Hui，GAO Yang，CHEN Wei，et al. Seismic noise suppression based on convolutional denoising autoencoders[J]. Oil Geophysical Prospecting，2020，55(6)：1210−1219.

[14] WU Xin，XUE Guoqiang，HE Yiming，et al. Removal of multisource noise in airborne electromagnetic data based on deep learning[J]. Geophysics，2020，85(6)：B193−B208.

[15] ZHU Weiqiang，MOUSAVI S M，BEROZA G C. Seismic signal denoising and decomposition using deep neural networks[J]. IEEE Transactions on Geoscience and Remote Sensing，2019，57(11)：9476−9488.

[16] PUZYREV V. Deep learning electromagnetic inversion with convolutional neural networks[J]. Geophysical Journal International，2019，218(2)：817−832.

[17] 汪凯翔，黄清华，吴思弘. 长短时记忆神经网络在地电场数据处理中的应用[J]. 地球物理学报，2020，63(8)：3015−3024.

WANG Kaixiang，HUANG Qinghua，WU Sihong. Application of long short-term memory neural network in geoelectric field data processing[J]. Chinese Journal of Geophysics，2020，63(8)：3015−3024.

[18] HE Siyuan，CAI Hongzhu，LIU Shuang，et al. Recovering 3D basement relief using gravity data through convolutional neural networks[J]. Journal of Geophysical Research (Solid Earth)，2021，126(10)：e2021JB022611.

[19] 杨洋，王用鑫，李虎，等. 基于深度学习的井间地震CT初至自动拾取方法[J]. 应用基础与工程科学学报，2022，30(1)：183−195.

YANG Yang，WANG Yongxin，LI Hu，et al. Automatic picking method for first arrival of cross-well seismic CT based on deep learning[J]. Journal of Basic Science and Engineering，2022，30(1)：183−195.

[20] 李建平，张硕伟，丁仁伟，等. 面向地震波初至智能拾取的超分辨率深度残差方法研究[J]. 石油地球物理勘探，2023，58(2)：251−262.

LI Jianping，ZHANG Shuowei，DING Renwei，et al. Research on depth residual method of super-resolution for intelligent seismic wave first arrival pickup[J]. Oil Geophysical Prospecting，2023，58(2)：251−262.

[21] GUO Rui，YAO Heming，LI Maokun，et al. Joint inversion of audio-magnetotelluric and seismic travel time data with deep learning constraint[J]. IEEE Transactions on Geoscience and Remote Sensing，2021，59(9)：7982−7995.

[22] MOUSAVI S M，ELLSWORTH W L，ZHU Weiqiang，et al. Earthquake transformer—an attentive deep-learning model for simultaneous earthquake detection and phase picking[J]. Nature Communications，2020，11：3952.

[23] BERGEN K J，JOHNSON P A，DE HOOP M V，et al. Machine learning for data-driven discovery in solid earth geoscience[J]. Science，2019，363(6433)：eaau0323.

[24] CIREGAN D，MEIER U，SCHMIDHUBER J. Multi-column deep neural networks for image classification[C]//2012 IEEE Conference on Computer Vision and Pattern Recognition. Providence，RI，USA. IEEE，2012：3642–3649.

[25] 韩卫雪，周亚同，池越. 基于深度学习卷积神经网络的地震数据随机噪声去除[J]. 石油物探，2018，57(6)：862−869.

HAN Weixue，ZHOU Yatong，CHI Yue. Deep learning convolutional neural networks for random noise attenuation in seismic data[J]. Geophysical Prospecting for Petroleum，2018，57(6)：862−869.

[26] 常德宽，雍学善，王一惠，等. 基于深度卷积神经网络的地震数据断层识别方法[J]. 石油地球物理勘探，2021，56(1)：1−8.

CHANG Dekuan，YONG Xueshan，WANG Yihui，et al. Seismic fault interpretation based on deep convolutional neural networks[J]. Oil Geophysical Prospecting，2021，56(1)：1−8.

[27] WU Sihong，HUANG Qinghua，ZHAO Li. Convolutional neural network inversion of airborne transient electromagnetic data[J]. Geophysical Prospecting，2021，69(8/9)：1761−1772.

[28] RONNEBERGER O，FISCHER P，BROX T. U-Net：Convolutional networks for biomedical image segmentation[M]//Lecture notes in computer science. Cham：Springer International Publishing，2015：234–241.

[29] 赵明，陈石，房立华，等. 基于U形卷积神经网络的震相识别与到时拾取方法研究[J]. 地球物理学报，2019，62(8)：3034−3042.

ZHAO Ming，CHEN Shi，FANG Lihua，et al. Earthquake phase arrival auto-picking based on U-shaped convolutional neural network[J]. Chinese Journal of Geophysics，2019，62(8)：3034−3042.

[30] 孙永壮，黄鋆，俞伟哲，等. 基于U-Net网络的端到端地震高分辨率处理技术[J]. 地球物理学进展，2021，36(3)：1297−1305.

SUN Yongzhuang，HUANG Jun，YU Weizhe，et al. End-to-end high-resolution seismic processing method based on U-Net network[J]. Progress in Geophysics，2021，36(3)：1297−1305.

[31] 陈成栋. 半航空瞬变电磁数据采集设计和数据校正研究[D]. 济南：山东大学，2021.

CHEN Chengdong. Research on data acquisition design and data correction of semi-airborne transient electromagnetic data[D]. Jinan：Shandong University，2021.