JSEJournal of Seismic Exploration0963-0651AccScience Publishing10.36922/JSE025280034ArticleA physics-constrained sparse basis learning method for mixed noise suppressionhttps://geophysical-press.com/journal/JSE/34/4/10.36922/JSE025280034WangYongsheng,WangDeying,ZhangKai,LiuWenqing,KouLongjiang,LiHuailiang20253442025-10-27Suppressing complex mixed noise in seismic data poses a significant challenge for conventional methods, which often cause signal damage or leave residual noise. While sparse basis learning is a promising approach for this task, traditional data-driven learning methods are often insensitive to the physical properties of seismic signals, leading to incomplete noise removal and compromised signal fidelity. To address this limitation, we propose a physics-constrained sparse basis learning method for mixed noise suppression. Our method integrates local dip attributes—estimated and iteratively refined by a plane-wave destructor filter—as a physical constraint within the dictionary learning framework. This constraint guides the learning process to achieve high-fidelity signal reconstruction while effectively suppressing multiple noise types. Tests on complex synthetic and real data demonstrate that the proposed method outperforms conventional techniques and industry-standard workflows in attenuating mixed noise, including strong anomalous amplitudes, ground roll, and random and coherent components, thereby significantly enhancing the signal-to-noise ratio and imaging quality.Multiple-type noise suppression, Dictionary learning, Physical constraint, Plane-wave destructor filter

Zhang H, Chen, X, Li H, et al. 3D seismic data denoising approach based on curvelet transform. Oil Geophys Prospect. 2017;52(2):226-232.   Liu Y, Fomel S, Liu C, Wang D, Liu G, Feng X. High-order seislet transform and its application of random noise attenuation. Chin J Geophys. 2009;52(8):2142-2151. doi: 10.3969/j.issn.0001-5733.2009.08.024   Zhang H, Chen X, Yang H. Optimistic wavelet basis selection in seismic signal noise elimination. Oil Geophys Prospect. 2011;46(1):70-75.   Wrinch D, Jeffreys H. On certain fundamental principles of scientific inquiry. Philos Mag. 1921;42(250):369-390. doi: 10.1080/14786442108633773   Häuser M, Ma J. Interpolating seismic data via the POCS method based on shearlet transform. J Geophys Eng. 2012;9(3):852-861.   Herrmann FJ. Curvelet-based seismic data processing: A multiscale and nonlinear approach. Geophysics. 2006;71(4):E11-E25.   Herrmann FJ, Hennenfent G, Moghaddam PP. Compressive seismic data acquisition: An overview. Geophysics. 2008;73(1):R23-R33.   Huang X. A simulation of acquisition design and data processing for offshore compressive sensing seismic. Oil Geophys Prospect. 2020;55(2):248-256.   Starck JL, Candès EJ, Donoho DL. The curvelet transform for image denoising. IEEE Trans Image Process. 2002;11(6):670-684. doi: 10.1109/tip.2002.1014998   Aharon M, Elad M, Bruckstein A. K-SVD: An algorithm for designing overcomplete dictionaries for sparse representation. IEEE Trans Signal Process. 2006;54(11):4311-4322. doi: 10.1109/TSP.2006.881199   Engan K, Aase SO, Husoy JH. Frame Based Signal Compression using Method of Optimal Directions (MOD). In: 1999 IEEE International Symposium on Circuits and Systems, ISCAS’99. Vol. 4. United States: IEEE; 1999. p. 244-247. doi: 10.1109/ISCAS.1999.779928   Liu L, Liu Y, Liu C, Zheng Z. Iterative seismic random noise suppression method based on compressive sensing. Chin J Geophys. 2021;64(12):4629-4643. doi: 10.6038/cjg2021P0045   Zhang K, Zuo W, Chen Y, Meng D, Lei L. Beyond a Gaussian denoiser: Residual learning of deep CNN for image denoising. IEEE Trans Image Process. 2017; 26(7):3142-3155. doi: 10.1109/TIP.2017.2662206   Kaur R, Waldeland AU, Alaei R, Solberg AHS. Self-supervised learning for seismic denoising. IEEE Trans Geosci Remote Sens. 2022;60:1-12.   Song C, Alkhalifah T, Riyanti F. A physics-informed deep learning approach for denoising seismic data. Geophysics. 2022;87(5):V239-V250.   Sacchi MD, Ulrych TJ, Walker CJ. Interpolation and extrapolation using a high-resolution discrete Fourier transform. IEEE Trans Signal Process. 1998;46(1):31-38. doi: 10.1109/78.651165   Yao Z, Sun C, Li H, Yang A. Time-variant wavelet extraction and seismic reflectivity inversion based on basis pursuit. Oil Geophys Prospect. 2019;54(1):137-144.   Candès EJ, Donoho DL. Curvelets-a new multiresolution representation for visual information. In: Wavelet Applications in Signal and Image Processing VIII. Vol. 4119. United States: SPIE; 2000. p. 248-262.   Chen Y, Ma J, Fomel S. Seismic noise attenuation using a deep-learning approach with a local-correlation-based structural constraint. IEEE Trans Geosci Remote Sens. 2020;58(7):4668-4679.   Zhang L, AlRegib G. SSIM-based quality control for seismic processing. Geophysics. 2021;86(3):V235-V248.   Amini H, Javaherian A. A review of seismic attributes. J Appl Geophys. 2022;205:104764.