{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T22:15:16Z","timestamp":1782425716226,"version":"3.54.5"},"reference-count":40,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Natural Science Foundation of China","award":["42074161"],"award-info":[{"award-number":["42074161"]}]},{"name":"National Natural Science Foundation of China","award":["41774132"],"award-info":[{"award-number":["41774132"]}]},{"name":"Free Exploration Project of Central South University","award":["2020zzts185"],"award-info":[{"award-number":["2020zzts185"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>The high-fidelity attenuation of random ground penetrating radar (GPR) noise is important for enhancing the signal-noise ratio (SNR). In this paper, a novel network structure for convolutional denoising autoencoders (CDAEs) was proposed to effectively resolve various problems in the noise attenuation process, including overfitting, the size of the local receptive field, and representational bottlenecks and vanishing gradients in deep learning; this approach also significantly improves the noise attenuation performance. We described the noise attenuation process of conventional CDAEs, and then presented the output feature map of each convolutional layer to analyze the role of convolutional layers and their impacts on GPR data. Furthermore, we focused on the problems of overfitting, the local receptive field size, and the occurrence of representational bottlenecks and vanishing gradients in deep learning. Subsequently, a network structure optimization strategy, including a dropout regularization layer, an atrous convolution layer, and a residual-connection structure, was proposed, namely convolutional denoising autoencoders with network structure optimization (CDAEsNSO), comprising an intermediate version, called atrous-dropout CDAEs (AD-CDAEs), and a final version, called residual-connection CDAEs (ResCDAEs), all of which effectively improve the performance of conventional CDAEs. Finally, CDAEsNSO was applied to attenuate noise for the H-beam model, tunnel lining model, and field pipeline data, confirming that the algorithm adapts well to both synthetic and field data. The experiments verified that CDAEsNSO not only effectively attenuates strong Gaussian noise, Gaussian spike impulse noise, and mixed noise, but it also causes less damage to the original waveform data and maintains high-fidelity information.<\/jats:p>","DOI":"10.3390\/rs13091761","type":"journal-article","created":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T21:35:39Z","timestamp":1619904939000},"page":"1761","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":36,"title":["Deep Convolutional Denoising Autoencoders with Network Structure Optimization for the High-Fidelity Attenuation of Random GPR Noise"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6290-7797","authenticated-orcid":false,"given":"Deshan","family":"Feng","sequence":"first","affiliation":[{"name":"School of Geosciences and Info-Physics, Central South University, Changsha 410083, China"},{"name":"The Key Laboratory of Metallogenic Prediction of Nonferrous Metals, Ministry of Education, Changsha 410083, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4078-3620","authenticated-orcid":false,"given":"Xiangyu","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Geosciences and Info-Physics, Central South University, Changsha 410083, China"},{"name":"The Key Laboratory of Metallogenic Prediction of Nonferrous Metals, Ministry of Education, Changsha 410083, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3039-4683","authenticated-orcid":false,"given":"Xun","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Geosciences and Info-Physics, Central South University, Changsha 410083, China"},{"name":"The Key Laboratory of Metallogenic Prediction of Nonferrous Metals, Ministry of Education, Changsha 410083, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siyuan","family":"Ding","sequence":"additional","affiliation":[{"name":"School of Geosciences and Info-Physics, Central South University, Changsha 410083, China"},{"name":"The Key Laboratory of Metallogenic Prediction of Nonferrous Metals, Ministry of Education, Changsha 410083, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7444-9586","authenticated-orcid":false,"given":"Hua","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Geosciences and Info-Physics, Central South University, Changsha 410083, China"},{"name":"The Key Laboratory of Metallogenic Prediction of Nonferrous Metals, Ministry of Education, Changsha 410083, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,5,1]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Dong, Z., Ye, S., Gao, Y., Fang, G., Zhang, X., Xue, Z., and Zhang, T. (2016). Rapid detection methods for asphalt pavement thicknesses and defects by a vehicle-mounted ground penetrating radar (GPR) system. Sensors, 16.","DOI":"10.3390\/s16122067"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1016\/j.conbuildmat.2017.02.105","article-title":"Utilization of air-launched ground penetrating radar (GPR) for pavement condition assessment","volume":"141","author":"Khamzin","year":"2017","journal-title":"Constr. Build. Mater."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"121","DOI":"10.2113\/JEEG22.2.121","article-title":"Concrete bridge deck deterioration assessment using ground penetrating radar (GPR)","volume":"22","author":"Diamanti","year":"2017","journal-title":"J. Environ. Eng. Geophys."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Solla, M., Lag\u00fcela, S., and Fern\u00e1ndez, N. (2019). Assessing rebar corrosion through the combination of nondestructive GPR and IRT methodologies. Remote Sens., 11.","DOI":"10.3390\/rs11141705"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"107662","DOI":"10.1016\/j.measurement.2020.107662","article-title":"GPR laboratory tests and numerical models to characterize cracks in cement concrete specimens, exemplifying damage in rigid pavement","volume":"158","author":"Rasol","year":"2020","journal-title":"Measurement"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"517","DOI":"10.1007\/s11104-017-3531-3","article-title":"Ground penetrating radar (GPR) detects fine roots of agricultural crops in the field","volume":"423","author":"Liu","year":"2018","journal-title":"Plant Soil."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1016\/j.jappgeo.2017.12.010","article-title":"Blind test of nondestructive underground void detection by ground penetrating radar (GPR)","volume":"149","author":"Lai","year":"2018","journal-title":"J. Appl. Geophys."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"4280","DOI":"10.1109\/JSTARS.2017.2717960","article-title":"Application of the Curvelet Transform for clutter and noise removal in GPR data","volume":"10","author":"Terrasse","year":"2017","journal-title":"IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1002\/nsg.12095","article-title":"Direct-wave denoising of low-frequency ground-penetrating radar in open pits based on empirical curvelet transform","volume":"18","author":"He","year":"2020","journal-title":"Near Surf. Geophys."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"3909","DOI":"10.4028\/www.scientific.net\/AMM.687-691.3909","article-title":"A de-noising method for GPR signal based on EEMD","volume":"687","author":"Gan","year":"2014","journal-title":"Appl. Mech. Mater. Trans. Tech. Publ. Ltd."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1615","DOI":"10.1109\/LGRS.2015.2415736","article-title":"GPR Signal Denoising and Target Extraction with the CEEMD Method","volume":"12","author":"Li","year":"2015","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1088\/1742-2140\/aa8cb4","article-title":"GPR random noise reduction using BPD and EMD","volume":"15","author":"Ostoori","year":"2018","journal-title":"J. Geophys. Eng."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Zhang, X., Feng, X., and Zhang, X. (2019). Dip Filter and Random Noise Suppression for GPR B-Scan Data Based on a Hybrid Method in f-x Domain. Remote Sens., 11.","DOI":"10.3390\/rs11182180"},{"key":"ref_14","first-page":"1","article-title":"A denoising method for detecting reflected waves from buried objects by ground-penetrating radar","volume":"96","author":"Kobayashi","year":"2013","journal-title":"Electr. Commun. Jpn."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"3159","DOI":"10.1109\/TGRS.2018.2793856","article-title":"Damped dreamlet representation for exploration seismic data interpolation and denoising","volume":"56","author":"Huang","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_16","first-page":"207","article-title":"Ground Penetrating Radar Weak Signals Denoising via Semi-soft Threshold Empirical Wavelet Transform","volume":"24","author":"Qiao","year":"2019","journal-title":"Ing\u00e9nierie Syst. Inf."},{"key":"ref_17","first-page":"196","article-title":"Research on weak signal extraction and noise removal for GPR data based on principal component analysis","volume":"18","author":"Chen","year":"2015","journal-title":"Glob. Geol."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Huang, W., Wang, R., and Chen, X. (2017). Damped sparse representation for seismic random noise attenuation. SEG Technical Program Expanded Abstracts 2017, Society of Exploration Geophysicists.","DOI":"10.1190\/segam2017-17665286.1"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1993","DOI":"10.1109\/LGRS.2017.2745564","article-title":"Sparse Bayesian learning-based seismic denoise by using physical wavelet as basis functions","volume":"14","author":"Deng","year":"2017","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Bi, W., Zhao, Y., and An, C. (2018). Clutter elimination and random-noise denoising of GPR signals using an SVD method based on the Hankel matrix in the local frequency domain. Sensors, 18.","DOI":"10.3390\/s18103422"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1883","DOI":"10.1109\/TGRS.2018.2870087","article-title":"Structured graph dictionary learning and application on the seismic denoising","volume":"57","author":"Liu","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"4659","DOI":"10.1109\/TGRS.2019.2892183","article-title":"Radar image series denoising of space targets based on Gaussian process regression","volume":"57","author":"Bai","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1504\/IJSPM.2019.104118","article-title":"A Morphological component analysis based on mixed dictionary for signal denoising of ground penetrating radar","volume":"14","author":"Zhang","year":"2019","journal-title":"Int. J. Simul. Process. Model."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"V159","DOI":"10.1190\/geo2015-0222.1","article-title":"Mathematical morphological filtering for linear noise attenuation of seismic data","volume":"81","author":"Li","year":"2016","journal-title":"Geophysics"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"V369","DOI":"10.1190\/geo2016-0580.1","article-title":"A method for low-frequency noise suppression based on mathematical morphology in microseismic monitoring","volume":"82","author":"Huang","year":"2017","journal-title":"Geophysics"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1109\/LGRS.2015.2502662","article-title":"Enhanced GPR Signal for Layered Media Time-Delay Estimation in Low-SNR Scenario","volume":"13","author":"Li","year":"2016","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Gondara, L. (2016, January 12\u201315). Medical image denoising using convolutional denoising autoencoders. Proceedings of the 2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW), Barcelona, Spain.","DOI":"10.1109\/ICDMW.2016.0041"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Zhou, H., Feng, X., Dong, Z., Liu, C., and Liang, W. (2021). Application of Denoising CNN for Noise Suppression and Weak Signal Extraction of Lunar Penetrating Radar Data. Remote Sens., 13.","DOI":"10.3390\/rs13040779"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Grais, E.M., and Plumbley, M.D. (2017, January 14\u201316). Single channel audio source separation using convolutional denoising autoencoders. Proceedings of the 2017 IEEE global conference on signal and information processing (GlobalSIP), Montreal, QC, Canada.","DOI":"10.1109\/GlobalSIP.2017.8309164"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"448","DOI":"10.1016\/j.measurement.2018.08.010","article-title":"An enhancement denoising autoencoder for rolling bearing fault diagnosis","volume":"130","author":"Meng","year":"2018","journal-title":"Measurement"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1016\/j.neucom.2019.07.106","article-title":"DEVDAN: Deep evolving denoising autoencoder","volume":"390","author":"Ashfahani","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"9476","DOI":"10.1109\/TGRS.2019.2926772","article-title":"Seismic signal denoising and decomposition using deep neural networks","volume":"57","author":"Zhu","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"V367","DOI":"10.1190\/geo2019-0468.1","article-title":"Deep denoising autoencoder for seismic random noise attenuation","volume":"85","author":"Saad","year":"2020","journal-title":"Geophysics"},{"key":"ref_34","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Dahl, G.E., Sainath, T.N., and Hinton, G.E. (2013, January 26\u201330). Improving deep neural networks for LVCSR using rectified linear units and dropout. Proceedings of the 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, Vancouver, BC, Canada.","DOI":"10.1109\/ICASSP.2013.6639346"},{"key":"ref_36","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., and Ren, S. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"10437","DOI":"10.1007\/s11042-017-4440-4","article-title":"Deep residual learning for image steganalysis","volume":"77","author":"Wu","year":"2018","journal-title":"Multimed. Tools Appl."},{"key":"ref_39","first-page":"1","article-title":"GPR Detection of Tunnel Lining Cavities and Reverse-time Migration Imaging","volume":"17","author":"Lyu","year":"2020","journal-title":"Appl. Geophys."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1109\/JSTARS.2015.2503289","article-title":"A new approach of rotated staggered grid FD method with unsplit convolutional PML for GPR","volume":"9","author":"Zhang","year":"2015","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/9\/1761\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:56:23Z","timestamp":1760162183000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/9\/1761"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,1]]},"references-count":40,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2021,5]]}},"alternative-id":["rs13091761"],"URL":"https:\/\/doi.org\/10.3390\/rs13091761","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,1]]}}}