Wave-equation migration: Advances, artificial intelligence enhancement, comparisons, and outlook

Abstract

Wave-equation–based seismic migration is a core technology for high-resolution subsurface imaging in applications such as hydrocarbon exploration and geothermal resource assessment. It provides a more complete physical description of seismic wave propagation than ray-based migration methods, and is therefore essential for imaging complex geological structures characterized by strong velocity contrasts and steeply dipping reflectors. This paper presents a systematic review and comparative analysis of wave-equation prestack depth-migration methods, including reference-velocity–based one-way wave-equation depth migration (OWDM), accurate-velocity–based OWDM, reverse-time migration, and full-wave-equation depth migration. The theoretical foundations, wavefield extrapolation characteristics, imaging mechanisms, and numerical implementations of these methods are examined within a unified framework. Particular emphasis is placed on clarifying the intrinsic limitations of one-way wave-equation migration in handling turning waves and large propagation angles, and on contrasting the strengths and weaknesses of time-domain versus depth-domain full-wave-equation migration. Based on representative numerical experiments and field data examples, the imaging performance, computational efficiency, and practical applicability of the four migration schemes are comprehensively compared. In addition, recent advances in artificial intelligence-assisted seismic imaging are reviewed, focusing on wavefield propagator design and migration artifact suppression. This review provides practical guidance for selecting appropriate migration strategies in complex geological settings and offers insights into future developments of wave-equation–based seismic imaging.

Keywords

Wave-equation migration / Seismic imaging / Research progress / Imaging comparison

References

[1] Bednar JB. A Brief History of Seismic Migration. Geophysics . 2005; 70(3): 3MJ-20MJ. doi: 10.1190/1.1926579

[2] Claerbout JF. Imaging the Earth’s Interior . Cambridge, MA, USA: Blackwell Scientific Publications; 1985.

[3] Gray SH, Etgen J, Dellinger J, Whitmore D. Seismic migration problems and solutions. Geophysics. 2001; 66(5): 1622-1640. doi: 10.1190/1.1487107

[4] Fomel S, Landa E, Taner MT. Poststack velocity analysis by separation and imaging of seismic diffractions. Geophysics. 2007; 72(6): U89-U94. doi: 10.1190/1.2781533

[5] Gazdag J. Wave equation migration with the phase—shift method. Geophysics. 1978; 43(7): 1342-1351. doi: 10.1190/1.1440899

[6] Lee MW, Suh SY. Optimization of one—way wave equations. Geophysics. 1985; 50(10): 1634-1637. doi: 10.1190/1.1441853

[7] Gazdag J, Sguazzero P. Migration of seismic data by phase shift plus interpolation. Geophysics. 1984; 49(2): 124-131. doi: 10.1190/1.1441643

[8] Stoffa PL, Fokkema JT, de Luna Freire RM, Kessinger WP. Split—step Fourier migration. Geophysics. 1990; 55(4): 410-421. doi: 10.1190/1.1442850

[9] Zhang L, James WRG, Michael HSF. Split—step complex Padé—Fourier depth migration. Geophys J Int . 2007; 171(3): 1308-1313. doi: 10.1111/j.1365—246X.2007.03610.x

[10] Ristow D, Rühl T. Fourier finite—difference migration. Geophysics. 1994; 59(12): 1882-1893. doi: 10.1190/1.1443575

[11] Biondi B. Stable—wide—angle Fourier finite—difference downward extrapolation of 3D wavefields. Geophysics. 2002; 67(3): 872-882. doi: 10.1190/1.1484530

[12] Salcedo M, Novais A, Schleicher J, Costa JC. Optimization of the parameters in complex Padé FFD migration. Geophysics. 2017; 82(3): S259-S269. doi: 10.1190/geo2016—0324.1

[13] Huang J, Hu T, Wang S. Fourier finite—difference migration of internal multiples. Chin J Geophys . 2022; 65(11): 4394-4403. [In Chinese]. doi: 10.6038/cjg2022P0790

[14] Wu R. Wide—angle elastic wave one—way propagation in heterogeneous media and an elastic wave complex—screen method. J Geophys Res Solid Earth. 1994; 99(B1): 751-766. doi: 10.1029/93JB02518

[15] Zhang Y, Zhang G, Bleistein N. True amplitude wave equation migration arising from true amplitude one—way wave equations. Inverse Probl. 2003; 19(5): 1113-1138. doi: 10.1088/0266—5611/19/5/307

[16] Amazonas D, Aleixo R, Melo G, Schleicher J, Novais A, Costa JC. Including lateral velocity variations into true—amplitude common—shot wave—equation migration. Geophysics. 2010; 75(5): S175-S186. doi: 10.1190/1.3481469

[17] Zhu H, Wang D, Hu B, Zhang W, Chen Y. Sparsity—promoting wide—angle least—squares one—way migration. Acta Geophys. 2024; 72(5): 3091-3108. doi: 10.1007/s11600—023—01215—0

[18] Kosloff D, Kessler D. Accurate depth migration by a generalized phase—shift method. Geophysics. 1987; 52(8): 1074-1084. doi: 10.1190/1.1442373

[19] Grimbergen JLT, Dessing FJ, Wapenaar K. Modal expansion of one—way operators in laterally varying media. Geophysics . 1998; 63(3): 995-1005. doi: 10.1190/1.1444410

[20] Sun Y, Kim YS, Qu S, Verschuur E. Joint migration inversion: Features and challenges. J Geophys Eng. 2020; 17(3): 525-538. doi: 10.1093/jge/gxaa012

[21] Li A, Liu X. An optimised one—way wave migration method for complex media with arbitrarily varying velocity based on eigen—decomposition. J Geophys Eng. 2021; 18(5): 776-787. doi: 10.1093/jge/gxab051

[22] Revelo DE, Pestana RC. One—way wave—equation migration based on Jacobi—Anger expansion in arbitrarily lateral varying media. IEEE Trans Geosci Remote Sens . 2025; 63: 4501610. doi: 10.1109/TGRS.2025.3533469

[23] Li A. Efficient one—way wave—equation depth migration using fast Fourier Transform and complex Padé approximation via Helmholtz operator. IEEE Trans Geosci Remote Sens. 2026; 64: 5901211. doi: 10.1109/TGRS.2026.3651624

[24] Berkhout AJ. Review paper: An outlook on the future of seismic imaging, Part II: Full—wavefield migration. Geophys Prospect. 2014; 62(5): 931-949. doi: 10.1111/1365—2478.12154

[25] Davydenko M, Verschuur DJ. Full—wavefield migration: Using surface and internal multiples in imaging. Geophys Prospect. 2017; 65(1): 7-21. doi: 10.1111/1365—2478.12360

[26] Li A, Verschuur DJ, Liu X, Abolhassani S. An accurate propagator for heterogeneous media in full wavefield migration. IEEE Trans Geosci Remote Sens. 2024; 62: 4506210. doi: 10.1109/TGRS.2024.3397887

[27] Bashir Y, Babasafari AA, Alashloo SM, Muztaza NM, Ali SH, Imran QS. Seismic wave propagation characteristics using conventional and advance modelling algorithm for d—data imaging. J Seism Explor . 2021; 30(1): 21-44.

[28] Whitmore ND. Iterative depth migration by backward time propagation. In: SEG Technical Program Expanded Abstracts 1983 . 53rd SEG Annual International Meeting; 1983; Las Vegas, NV. Society of Exploration Geophysicists; 1983: 382-385. doi: 10.1190/1.1893867

[29] Baysal E, Kosloff DD, Sherwood JWC. Reverse time migration. Geophysics . 1983; 48(11): 1514-1524. doi: 10.1190/1.1441434

[30] Kosloff DD, Baysal E. Migration with the full acoustic equation. Geophysics. 1983; 48(6): 677-687. doi: 10.1190/1.1441498

[31] Bashir Y, Waheed U, Ali SH, Karaman A, İmren C. Enhanced wave modeling & optimal plane—wave destruction (OPWD) method for diffraction separation and imaging. Comput Geosci. 2024; 187: 105576. doi: 10.1016/j.cageo.2024.105576

[32] Zhang L, Slob E, van der Neut J, Wapenaar K. Artifact—free reverse time migration. Geophysics. 2018; 83(5): A65-A68. doi: 10.1190/geo2017—0795.1

[33] Xu Q, Wang Y. Seismic reverse time migration based on biaxial wavefield decomposition. Geophysics. 2024; 89(1): S61-S70. doi: 10.1190/geo2022—0698.1

[34] Nguyen BD, McMechan GA. Excitation amplitude imaging condition for prestack reverse—time migration. Geophysics . 2013; 78(1): S37-S46. doi: 10.1190/geo2012—0079.1

[35] Wang J, Li Q, Qiao B, Qi J. Reverse time migration using excitation amplitude imaging condition based on accurate first—arrival traveltimes calculation. IEEE Trans Geosci Remote Sens. 2025; 63: 5903111. doi: 10.1109/TGRS.2025.3527144

[36] Symes WW. Reverse time migration with optimal checkpointing. Geophysics. 2007; 72(5): SM213-SM221. doi: 10.1190/1.2742686

[37] Sun W, Fu L. Two effective approaches to reduce data storage in reverse time migration. Comput Geosci. 2013; 56: 69-75. doi: 10.1016/j.cageo.2013.03.013

[38] Yang P, Brossier R, Métivier L, Virieux J. Wavefield reconstruction in attenuating media: A checkpointing—assisted reverse—forward simulation method. Geophysics. 2016; 81(6): R349-R362. doi: 10.1190/geo2016—0082.1

[39] Cai W, Zhu P, Li Z. Simulation and reconstruction for 3D elastic wave using multi—GPU and CUDA—aware MPI. Comput Geosci. 2024; 190: 105616. doi: 10.1016/j.cageo.2024.105616

[40] Dai W, Schuster G. Plane—wave least—squares reverse—time migration. Geophysics. 2013; 78(4): S165-S177. doi: 10.1190/geo2012—0377.1

[41] Yao G, Jakubowicz H. Least—squares reverse—time migration in a matrix—based formulation. Geophys Prospect. 2016; 64(3): 611-621. doi: 10.1111/1365—2478.12305

[42] Vamaraju J, Tuvi R, Zhao ZY, Sen MK. Optimal minibatch shot selection for target—oriented least—squares reverse time migration. Geophysics. 2022; 87(4): A55-A60. doi: 10.1190/geo2021—0579.1

[43] Wang M, He B. Elastic least—squares reverse time migration based on integration of the Hessian. IEEE Trans Geosci Remote Sens. 2025; 63: 5912711. doi: 10.1109/TGRS.2025.3563393

[44] Li C, Huang J, Li Z, Wang R. Plane—wave least—squares reverse time migration with a preconditioned stochastic conjugate gradient method. Geophysics. 2018; 83(1): S33-S46. doi: 10.1190/geo2017—0339.1

[45] Mu X, Huang J, Yang J, Guo X, Guo Y. Least—squares reverse time migration in TTI media using a pure qP—wave equation. Geophysics. 2020; 85(4): S199-S216. doi: 10.1190/geo2019—0320.1

[46] Qiao Z, Chen T, Sun C. Anisotropic attenuation compensated reverse time migration of pure qP—wave in transversely isotropic attenuating media. Surv Geophys . 2022; 43(5): 1435-1467. doi: 10.1007/s10712—022—09717—0

[47] Huang J, Mu X, Yang J, Su L. Least—squares reverse time migration in viscoacoustic tilted transversely isotropic media. Geophysics . 2025; 90(3): S69-S88. doi: 10.1190/geo2023—0422.1

[48] Zhang D, Schuster GT. Least—squares reverse time migration of multiples. Geophysics . 2013; 79(1): S11-S21. doi: 10.1190/geo2013—0156.1

[49] Lu S, Liu F, Chemingui N, Valenciano A, Long A. Least—squares full—wavefield migration. Leading Edge . 2018; 37(1): 46-51. doi: 10.1190/tle37010046.1

[50] Liu Y, Zhang Y, Zheng Y. Reverse time migration of phase—encoded all—order multiples. Geophysics . 2022; 87(2): S45-S52. doi: 10.1190/geo2021—0004.1

[51] Wu H, Lu S, Dong X, Deng X, Gao R. Least—squares full—wavefield reverse time migration using a modeling engine with vector reflectivity. IEEE Trans Geosci Remote Sens. 2023; 61: 5901112. doi: 10.1109/TGRS.2023.3234902

[52] Sandberg K, Beylkin G. Full—wave—equation depth extrapolation for migration. Geophysics. 2009; 74(6): WCA121-WCA128. doi: 10.1190/1.3202535

[53] Wu B, Wu R, Gao J. Preliminary investigation of wavefield depth extrapolation by two—way wave equations. Int J Geophys . 2012; 2012: 968090. doi: 10.1155/2012/968090

[54] Pan J. A new upward and downward wavefield continuation for two—way wave equation migration. In: SEG Technical Program Expanded Abstracts 2015. 85th SEG Annual International Meeting; October 18—23, 2015; New Orleans, LA. Society of Exploration Geophysicists; 2015: 4180-4184. doi: 10.1190/segam2015—5829692.1

[55] You J, Cao J. Full—wave—equation depth extrapolation for migration using matrix multiplication. Geophysics. 2020; 85(6): S395-S403. doi: 10.1190/geo2019—0323.1

[56] Li A, Liu X, Zhao Q, You J, Zhu X. Hybrid boundary full—wave—equation depth migration based on dual—sensor acquisition system and its application. J Appl Geophys. 2022; 203: 104679. doi: 10.1016/j.jappgeo.2022.104679

[57] You J, Pan N, Liu W, Cao J. Efficient wavefield separation by reformulation of two—way wave—equation depth—extrapolation scheme. Geophysics. 2022; 87(4): S209-S222. doi: 10.1190/geo2021—0629.1

[58] Li A, Zhu X, Liu T, Liao J, Liu X, You J. One—step sparse—matrix method for full wave equation depth migration. Geophysics. 2024; 89(6): S405-S413. doi: 10.1190/geo2023—0372.1

[59] Li A, Li C, Lai F, Liao J, Liu T. An acoustic wave—equation depth migration method using generalized two—way phase shift operator for anisotropic media. IEEE Geosci Remote Sens Lett. 2025; 22: 7504505. doi: 10.1109/LGRS.2025.3549919

[60] Mousavi SM, Beroza GC. Deep—learning seismology. Science . 2022; 377(6607): eabm4470. doi: 10.1126/science.abm4470

[61] Khosro Anjom F, Vaccarino F, Socco LV. Machine learning for seismic exploration: Where are we and how far are we from the holy grail? Geophysics. 2024; 89(1): WA157-WA178. doi: 10.1190/geo2023—0129.1

[62] Sheng H, Wu X, Si X, Li J, Zhang S, Duan X. Seismic foundation model: A next—generation deep—learning model in geophysics. Geophysics. 2025; 90(2): IM59-IM79. doi: 10.1190/geo2024—0262.1

[63] Bashir Y, Alashloo SYM, Ghosh DP. Chapter 3 — Seismic wave modeling and high—resolution imaging. In: Bashir Y, ed. Seismic Imaging Methods and Applications for Oil and Gas Exploration. Elsevier; 2022: 57-132.

[64] Fu LY, Tang C, Wei W, Du Q. Data—driven double—focusing resolution analyses for seismic imaging. Geophysics. 2024; 89(4): S311-S324. doi: 10.1190/geo2023—0064.1

[65] Vantassel JP, Bhochhibhoya S. Toward more—robust, AI—enabled subsurface seismic imaging for geotechnical applications. Comput Geotech . 2025; 187: 107443. doi: 10.1016/j.compgeo.2025.107443

[66] Song C, Wang Y. Simulating seismic multifrequency wavefields with the Fourier feature physics—informed neural network. Geophys J Int. 2023; 232(3): 1503-1514. doi: 10.1093/gji/ggac399

[67] Sun J, Zhao Z, Ma J, Yang J. Elastic wavefield decomposition using the physical—constrained neural network and its application on reverse—time migration. IEEE Trans Geosci Remote Sens. 2025; 63: 4505811. doi: 10.1109/TGRS.2025.3571593

[68] Yu Y, Li Y, Wu X, Jia X. Enhancing one—way wave equation—based migration with deep learning. Geophysics . 2023; 88(1): WA105-WA114. doi: 10.1190/geo2022—0159.1

[69] Li F, Gao J, Sun W, et al. LSTM Network Assisted Construction of the Angle—Dependent Point Spread Function and Its Applications in Seismic Imaging. IEEE Trans Geosci Remote Sens. 2025; 63: 5906822. doi: 10.1109/TGRS.2025.3535529

[70] Zou C, Azizzadenesheli K, Ross ZE, Clayton RW. Deep neural Helmholtz operators for 3—D elastic wave propagation and inversion. Geophys J Int. 2024; 239(3): 1469-1484. doi: 10.1093/gji/ggae342

[71] Liu Z, Chen Y, Schuster G. Deep convolutional neural network and sparse least—squares migration. Geophysics. 2020; 85(4): WA241-WA253. doi: 10.1190/geo2019—0412.1

[72] Torres K, Sacchi M. Least—squares reverse—time migration via deep—learning updated operators. Geophysics . 2022; 87(6): S315-S333. doi: 10.1190/geo2021—0491.1

[73] Wu B, Hu H, Zhou HW. Convolutional neural network—assisted least—squares migration. Surv Geophys. 2023; 44(4): 1107-1124. doi: 10.1007/s10712—023—09777—w

[74] Mu X, Saad OM, Alkhalifah T. SiameseLSRTM: Enhancing least—squares reverse time migration with a Siamese network. arXiv. Preprint posted online May 13, 2025. Last accessed April 3, 2026. doi: 10.48550/arXiv.2505.08305

[75] Chen Y, Huang Y, Huang L. Suppressing migration image artifacts using a support vector machine method. Geophysics . 2020; 85(5): S255-S268. doi: 10.1190/geo2019—0157.1

[76] Yoo J, Zwartjes P. Attenuation of seismic migration smile artifacts with deep learning. Artif Intell Geosci. 2022; 3: 123-131.

[77] Yang L, Fomel S, Wang S, Chen X, Chen Y. Deep learning with soft attention mechanism for small—scale ground roll attenuation. Geophysics. 2024; 89(1): WA179-WA193. doi: 10.1190/geo2023—0150.1

[78] Wang K, Hu T, Zhao B, Wang S. Surface—related multiple attenuation based on a self—supervised deep neural network with local wavefield characteristics. Geophysics. 2023; 88(5): V387-V402. doi: 10.1190/geo2022—0599.1

[79] Liu X, Hu T, Wang S. Physics—informed self—supervised learning with phase resemblance constraint for internal multiple attenuation. IEEE Trans Geosci Remote Sens. 2024; 62: 5928113. doi: 10.1109/TGRS.2024.3462440

[80] Fernandez MR, Ettrich N, Delescluse M, Rabaute A, Keuper J. Towards deep learning for seismic demultiple. Geophys Prospect. 2025; 73(4): 1185-1203. doi: 10.1111/1365—2478.13672

[81] Lin L, Zhong Z, Li C, et al. Machine learning for subsurface geological feature identification from seismic data: Methods, datasets, challenges, and opportunities. Earth Sci Rev. 2024; 257: 104887. doi: 10.1016/j.earscirev.2024.104887

[82] Zhang W, Gao J, Cheng Y, Li Z, Jiang X, Zhu J. Deep—learning for accelerating least—squares reverse—time migration. J Appl Geophys. 2022; 200: 104645. doi: 10.1016/j.jappgeo.2022.104645

[83] Wu B, Yao G, Ma X, Chen H, Wu D, Cao J. Least—squares reverse time migration of simultaneous sources with deep—learning—based denoising. Geophysics. 2024; 89(3): S289-S299. doi: 10.1190/geo2023—0320.1

[84] Zhao T, Di H, Abubakar A. Evaluating machine learning—predicted subsurface properties via seismic data reconstruction. Geophysics. 2024; 89(6): R509-R519. doi: 10.1190/geo2023—0124.1