{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T14:54:21Z","timestamp":1777128861690,"version":"3.51.4"},"reference-count":58,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2022,1,7]],"date-time":"2022-01-07T00:00:00Z","timestamp":1641513600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["41974132, 41504091"],"award-info":[{"award-number":["41974132, 41504091"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Seismic field data are usually contaminated by random or complex noise, which seriously affect the quality of seismic data contaminating seismic imaging and seismic interpretation. Improving the signal-to-noise ratio (SNR) of seismic data has always been a key step in seismic data processing. Deep learning approaches have been successfully applied to suppress seismic random noise. The training examples are essential in deep learning methods, especially for the geophysical problems, where the complete training data are not easy to be acquired due to high cost of acquisition. In this work, we propose a natural images pre-trained deep learning method to suppress seismic random noise through insight of the transfer learning. Our network contains pre-trained and post-trained networks: the former is trained by natural images to obtain the preliminary denoising results, while the latter is trained by a small amount of seismic images to fine-tune the denoising effects by semi-supervised learning to enhance the continuity of geological structures. The results of four types of synthetic seismic data and six field data demonstrate that our network has great performance in seismic random noise suppression in terms of both quantitative metrics and intuitive effects.<\/jats:p>","DOI":"10.3390\/rs14020263","type":"journal-article","created":{"date-parts":[[2022,1,9]],"date-time":"2022-01-09T23:08:26Z","timestamp":1641769706000},"page":"263","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["A Natural Images Pre-Trained Deep Learning Method for Seismic Random Noise Attenuation"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0120-246X","authenticated-orcid":false,"given":"Haixia","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Mathematics and Statistics, Xi\u2019an Jiaotong University, Xi\u2019an 710049, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tingting","family":"Bai","sequence":"additional","affiliation":[{"name":"School of Mathematics and Statistics, Xi\u2019an Jiaotong University, Xi\u2019an 710049, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiqiang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information and Communications Engineering, Xi\u2019an Jiaotong University, Xi\u2019an 710049, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,1,7]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1887","DOI":"10.1190\/1.1443920","article-title":"Lateral prediction for noise attenuation by t-x and f-x techniques","volume":"60","author":"Abma","year":"1995","journal-title":"Geophysics"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1641","DOI":"10.1190\/1.1444852","article-title":"Noncausal spatial prediction filtering for random noise reduction on 3-D poststack data","volume":"65","author":"Gulunay","year":"2000","journal-title":"Geophysics"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1342","DOI":"10.1109\/LGRS.2018.2841840","article-title":"Weighted Multisteps Adaptive Autoregression for Seismic Image Denoising","volume":"15","author":"Liu","year":"2018","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"V61","DOI":"10.1190\/geo2011-0117.1","article-title":"Random noise attenuation using f-x regularized nonstationary autoregression","volume":"77","author":"Liu","year":"2012","journal-title":"Geophysics"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"6574","DOI":"10.1109\/TGRS.2017.2730228","article-title":"Seismic Random Noise Attenuation Using Synchrosqueezed Wavelet Transform and Low-Rank Signal Matrix Approximation","volume":"55","author":"Anvari","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1088\/1742-2132\/13\/2\/135","article-title":"An effective approach to attenuate random noise based on compressive sensing and curvelet transform","volume":"13","author":"Liu","year":"2016","journal-title":"J. Geophys. Eng."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"WD117","DOI":"10.1190\/geo2014-0234.1","article-title":"Signal and noise separation in prestack seismic data using velocity-dependent seislet transform","volume":"80","author":"Liu","year":"2015","journal-title":"Geophysics"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1016\/j.jappgeo.2016.03.030","article-title":"2-D TFPF based on Contourlet transform for seismic random noise attenuation","volume":"129","author":"Zhao","year":"2016","journal-title":"J. Appl. Geophys."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"V169","DOI":"10.1190\/geo2018-0596.1","article-title":"Dictionary learning based on dip patch selection training for random noise attenuation","volume":"84","author":"Zu","year":"2019","journal-title":"Geophysics"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"V261","DOI":"10.1190\/geo2015-0264.1","article-title":"Damped multichannel singular spectrum analysis for 3D random noise attenuation","volume":"81","author":"Huang","year":"2016","journal-title":"Geophysics"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"V25","DOI":"10.1190\/1.3552706","article-title":"Simultaneous seismic data denoising and reconstruction via multichannel singular spectrum analysis","volume":"76","author":"Oropeza","year":"2011","journal-title":"Geophysics"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1109\/MGRS.2017.2762307","article-title":"Deep Learning in Remote Sensing","volume":"5","author":"Zhu","year":"2017","journal-title":"IEEE Geosci. Remote Sens. Mag."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Abdollahi, A., Pradhan, B., Shukla, N., Chakraborty, S., and Alamri, A. (2020). Deep Learning Approaches Applied to Remote Sensing Datasets for Road Extraction: A State-Of-The-Art Review. Remote Sens., 12.","DOI":"10.3390\/rs12091444"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"de Lima, R.P., and Marfurt, K. (2020). Convolutional Neural Network for Remote-Sensing Scene Classification: Transfer Learning Analysis. Remote Sens., 12.","DOI":"10.3390\/rs12234003"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Xu, Z., Zhang, W., Zhang, T., and Li, J. (2021). HRCNet: High-Resolution Context Extraction Network for Semantic Segmentation of Remote Sensing Images. Remote Sens., 13.","DOI":"10.3390\/rs13122290"},{"key":"ref_16","first-page":"033036","article-title":"Seatbelt detection in road surveillance images based on improved dense residual network with two-level attention mechanism","volume":"30","author":"Jingrui","year":"2021","journal-title":"J. Electron. Imaging"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1007\/s12182-020-00530-1","article-title":"A deep learning network for estimation of seismic local slopes","volume":"18","author":"Huang","year":"2021","journal-title":"Pet. Sci."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"R741","DOI":"10.1190\/geo2018-0685.1","article-title":"Regularized elastic full-waveform inversion using deep learning","volume":"84","author":"Zhang","year":"2019","journal-title":"Geophysics"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Wang, Y., Ge, Q., Lu, W., and Yan, X. (2019). Seismic impedance inversion based on cycle-consistent generative adversarial network. SEG Technical Program Expanded Abstracts 2019, Society of Exploration Geophysicists.","DOI":"10.1190\/segam2019-3203757.1"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"6900","DOI":"10.1109\/TGRS.2020.2977635","article-title":"Data-Driven Seismic Waveform Inversion: A Study on the Robustness and Generalization","volume":"58","author":"Zhang","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2140","DOI":"10.1109\/LGRS.2019.2963106","article-title":"Seismic Impedance Inversion Using Fully Convolutional Residual Network and Transfer Learning","volume":"17","author":"Wu","year":"2020","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1319","DOI":"10.1007\/s11053-020-09778-1","article-title":"Stochastic Pix2pix: A New Machine Learning Method for Geophysical and Well Conditioning of Rule-Based Channel Reservoir Models","volume":"30","author":"Pan","year":"2020","journal-title":"Nat. Resour. Res."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2558","DOI":"10.1177\/0144598720937524","article-title":"Conditioning well data to rule-based lobe model by machine learning with a generative adversarial network","volume":"38","author":"Jo","year":"2020","journal-title":"Energy Explor. Exploit."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Mustafa, A., and AlRegib, G. (2020). Joint learning for seismic inversion: An acoustic impedance estimation case study. SEG Technical Program Expanded Abstracts 2020, Society of Exploration Geophysicists.","DOI":"10.1190\/segam2020-3428378.1"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"2135","DOI":"10.1109\/TGRS.2019.2953473","article-title":"Deep-Learning Inversion of Seismic Data","volume":"58","author":"Li","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"V11","DOI":"10.1190\/geo2017-0495.1","article-title":"Deep-learning-based seismic data interpolation: A preliminary result","volume":"84","author":"Wang","year":"2019","journal-title":"Geophysics"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1163","DOI":"10.1093\/gji\/ggz366","article-title":"Seismic signal recognition by unsupervised machine learning","volume":"219","author":"Huang","year":"2019","journal-title":"Geophys. J. Int."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1190\/INT-2018-0161.1","article-title":"Common azimuth seismic data fault analysis using residual U-Net","volume":"8","author":"Liu","year":"2020","journal-title":"Interpretation"},{"key":"ref_29","first-page":"1","article-title":"Distilling knowledge from an ensemble of convolutional neural networks for seismic fault detection","volume":"19","author":"Wang","year":"2020","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_30","first-page":"1","article-title":"Deep Learning Prior Model for Unsupervised Seismic Data Random Noise Attenuation","volume":"19","author":"Qiu","year":"2021","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Wu, B., Meng, D., and Zhao, H. (2021). Semi-Supervised Learning for Seismic Impedance Inversion Using Generative Adversarial Networks. Remote Sens., 13.","DOI":"10.3390\/rs13050909"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"156883","DOI":"10.1109\/ACCESS.2019.2949774","article-title":"A Patch Based Denoising Method Using Deep Convolutional Neural Network for Seismic Image","volume":"7","author":"Zhang","year":"2019","journal-title":"IEEE Access"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"811","DOI":"10.1109\/LGRS.2018.2882058","article-title":"Low-Frequency Noise Suppression Method Based on Improved DnCNN in Desert Seismic Data","volume":"16","author":"Zhao","year":"2019","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_34","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_35","doi-asserted-by":"crossref","first-page":"1598","DOI":"10.1109\/TGRS.2019.2947149","article-title":"Poststack Seismic Data Denoising Based on 3-D Convolutional Neural Network","volume":"58","author":"Liu","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"11585","DOI":"10.1109\/ACCESS.2021.3049479","article-title":"Residual Learning of Cycle-GAN for Seismic Data Denoising","volume":"9","author":"Li","year":"2021","journal-title":"IEEE Access"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"736","DOI":"10.1109\/LGRS.2020.2981965","article-title":"A Branch Construction-Based CNN Denoiser for Desert Seismic Data","volume":"18","author":"Lin","year":"2021","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"709","DOI":"10.1111\/1365-2478.13062","article-title":"A fully unsupervised and highly generalized deep learning approach for random noise suppression","volume":"69","author":"Saad","year":"2021","journal-title":"Geophys. Prospect."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"5304","DOI":"10.1109\/TGRS.2020.3021492","article-title":"Attribute-Based Double Constraint Denoising Network for Seismic Data","volume":"59","author":"Wang","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"V197","DOI":"10.1190\/geo2020-0193.1","article-title":"Complete and representative training of neural networks: A generalization study using double noise injection and natural images","volume":"86","author":"Zhang","year":"2021","journal-title":"Geophysics"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1861","DOI":"10.1109\/LGRS.2020.3007819","article-title":"DCNNs-Based Denoising With a Novel Data Generation for Multidimensional Geological Structures Learning","volume":"18","author":"Sang","year":"2021","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"3142","DOI":"10.1109\/TIP.2017.2662206","article-title":"Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising","volume":"26","author":"Zhang","year":"2017","journal-title":"IEEE Trans. Image Processing"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5\u20139). U-Net: Convolutional Networks for Biomedical Image Segmentation. Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), Munich, Germany.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_45","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_46","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_47","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1109\/72.80290","article-title":"Bounds on the number of hidden neurons in multilayerd perceptions","volume":"2","author":"Huang","year":"1991","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"1032","DOI":"10.1190\/1.1444797","article-title":"Neural networks in geophysical applications","volume":"65","author":"Jutten","year":"2000","journal-title":"Geophysics"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Zhang, C., and Baan, M. (2019). Microseismic and seismic noise attenuation by supervised deep learning with noisy natural images. SEG Technical Program Expanded Abstracts 2019, Society of Exploration Geophysicists.","DOI":"10.1190\/segam2019-3213158.1"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"WA115","DOI":"10.1190\/geo2019-0243.1","article-title":"Can learning from natural image denoising be used for seismic data interpolation?","volume":"85","author":"Zhang","year":"2020","journal-title":"Geophysics"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Bouman, K.L., Johnson, M.D., Zoran, D., Fish, V.L., Doeleman, S.S., and Freeman, W.T. (2016, January 27\u201330). Computational Imaging for VLBI Image Reconstruction. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR.2016.105"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A Survey on Transfer Learning","volume":"22","author":"Pan","year":"2010","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_53","unstructured":"Kingma, D., and Ba, J. (2014). Adam: A Method for Stochastic Optimization. arXiv."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1190\/1.2172306","article-title":"Marmousi2: An elastic upgrade for Marmousi","volume":"25","author":"Martin","year":"2006","journal-title":"Lead. Edge"},{"key":"ref_55","unstructured":"Ganley, D. (2021, July 02). A Method for Calculating Synthetic Seismograms Which Include the Effects of Absorption and Dispersion. Available online: https:\/\/www.semanticscholar.org\/paper\/A-method-for-calculating-synthetic-seismograms-the-Ganley\/c705a08c124fd16a7c02924ac8cd698049828365."},{"key":"ref_56","unstructured":"Robinson, E.A. (1954). Predictive Decomposition of Timeseries with Application to Seismic Exploration. [Ph.D. Thesis, Massachusetts Institute of Technology]."},{"key":"ref_57","first-page":"1552","article-title":"Improving the Signal-to-Noise Ratio of Seismological Datasets by Unsupervised Machine Learning","volume":"90","author":"Chen","year":"2019","journal-title":"Seismol. Res. Lett."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: From error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Processing"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/2\/263\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T14:01:35Z","timestamp":1760364095000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/2\/263"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,7]]},"references-count":58,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2022,1]]}},"alternative-id":["rs14020263"],"URL":"https:\/\/doi.org\/10.3390\/rs14020263","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,7]]}}}