Slope tomography is a method to estimate subsurface velocity macromodels from the slopes and traveltimes of local coherent reflection events. In geologically complex areas, the macromodels obtained from slope tomography tend to yield larger errors. To address this issue, this study proposed a method for error correction of the models using deep learning. Specifically, with macromodels determined using slope tomography-based inversion serving as input and corresponding theoretical models as labels, a neural network was trained, yielding a nonlinear mapping from the slope tomography-derived macromodel to the corresponding theoretical model. To ensure that the trained neural network was applicable to measured seismic data, the training samples were generated from the inversion model and migration profiles of measured seismic data. Tests based on the data synthesized using the theoratical model validated the accuracy and effectiveness of the proposed method. The proposed method was then applied to the 2D measured seismic data from beaches and shallow seas, yielding velocity models with elevated precision and depth migration imaging profiles with high quality.
葛大明. 基于深度学习的二维斜率层析反演模型误差校正方法[J]. 物探与化探, 2025, 49(2): 385-393.
GE Da-Ming. A deep learning-based method for error correction of 2D slope tomography-based inversion models. Geophysical and Geochemical Exploration, 2025, 49(2): 385-393.
Billette F, Lambaré G. Velocity macro-model estimation from seismic reflection data by stereotomography[J]. Geophysical Journal International, 1998, 135(2):671-690.
[2]
Jin C K, Zhang J Z. Stereotomography of seismic data acquired on undulant topography[J]. Geophysics, 2018, 83(4):U35-U41.
[3]
Sambolian S, Operto S, Ribodetti A, et al. Parsimonious slope tomography based on eikonal solvers and the adjoint-state method[J]. Geophysical Journal International, 2019, 218(1):456-478.
doi: 10.1093/gji/ggz150
Jin C K, Zhang J Z. Implementation methods of stereotomography and analysis of influence factors on its results[J]. Computerized Tomography Theory and Applications, 2014, 23(6):939-950.
Ye Y F, Sun J G, Zhang Y M, et al. Construction of low-frequency model with three-dimensional tomographic velocity inversion and application in deep-water bock W of South China Sea[J]. Journal of Jilin University:Earth Science Edition, 2018, 48(4):1253-1259.
[6]
Liu J, Zhang J Z. Joint inversion of seismic slopes,traveltimes and gravity anomaly data based on structural similarity[J]. Geophysical Journal International, 2022, 229(1):390-407.
[7]
Yang H C, He W L, Ma F, et al. Slope tomography dynamically weighted according to the locations of the reflection points[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62:5905311.
Xiong K, Yang K, Xing F Y, et al. Inversion strategy and data space extraction for stereo-tomography based on a combination of structure tensor and kinematic demigration.Ⅱ:Practice[J]. Geophysical Prospecting for Petroleum, 2018, 57(2):254-261,273.
doi: 10.3969/j.issn.1000-1441.2018.02.011
Zhang L Q, Yang K, Xing F Y, et al. 2D stereo-tomography inversion constrained by regularization of stratum framework[J]. Chinese Journal of Geophysics, 2019, 62(2):634-647.
[10]
Costa J C, da Silva F J, Gomes E N, et al. Regularization in slope tomography[J]. Geophysics, 2008, 73(5):VE39-VE47.
[11]
Guillaume P, Reinier M, Lambaré G, et al. Dip constrained non-linear slope tomography[C]// SEG Technical Program Expanded Abstracts 2013,Society of Exploration Geophysicists, 2013:4811-4815.
[12]
Kurose T, Yamanaka H. Joint inversion of receiver function and surface-wave phase velocity for estimation of shear-wave velocity of sedimentary layers[J]. Exploration Geophysics, 2006, 37(1):93-101.
Zhang P, Song X D, Xiong A L. Advancement of joint inversion of gravity and seismic data and its application[J]. Progress in Geophysics, 2019, 34(5):1818-1825.
Xiang P, Wang J D, Tan S Q, et al. Simultaneous and joint inversion of gravity and seismic data based on variable density-velocity relation[J]. Oil Geophysical Prospecting, 2020, 55(3):686-693,474.
Liu J, Zhang J Z. Review of velocity-density coupling in joint inversion of seismic and gravity data[J]. Progress in Geophysics, 2020, 35(3):976-986.
[16]
Yang H C, Li P, Ma F, et al. Building near-surface velocity models by integrating the first-arrival traveltime tomography and supervised deep learning[J]. Geophysical Journal International, 2023, 235(1):326-341.
[17]
Araya-Polo M, Jennings J, Adler A, et al. Deep-learning tomography[J]. The Leading Edge, 2018, 37(1):58-66.
[18]
Araya-Polo M, Farris S, Florez M. Deep learning-driven velocity model building workflow[J]. The Leading Edge, 2019, 38(11):872a1-872a9.
[19]
Wang W L, Ma J W. Velocity model building in a crosswell acquisition geometry with image-trained artificial neural networks[J]. Geophysics, 2020, 85(2):U31-U46.
[20]
Li S C, Liu B, Ren Y X, et al. Deep-learning inversion of seismic data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(3):2135-2149.
[21]
Liu B, Yang S L, Ren Y X, et al. Deep-learning seismic full-waveform inversion for realistic structural models[J]. Geophysics, 2021, 86(1):R31-R44.
[22]
Kazei V, Ovcharenko O, Alkhalifah T. Velocity model building by deep learning:From general synthetics to field data application[C]// SEG Technical Program Expanded Abstracts 2020,Virtual,Society of Exploration Geophysicists, 2020:1561-1565.
[23]
Fabien-Ouellet G, Sarkar R. Seismic velocity estimation:A deep recurrent neural-network approach[J]. Geophysics, 2020, 85(1):U21-U29.
doi: 10.1190/GEO2018-0786.1
[24]
Geng Z C, Zhao Z Y, Shi Y Z, et al. Deep learning for velocity model building with common-image gather volumes[J]. Geophysical Journal International, 2021, 228(2):1054-1070.
[25]
Muller A P O, Bom C R, Costa J C, et al. Deep-Tomography:Iterative velocity model building with deep learning[J]. Geophysical Journal International, 2022, 232(2):975-989.
[26]
Tavakoli F B, Operto S, Ribodetti A, et al. Slope tomography based on eikonal solvers and the adjoint-state method[J]. Geophysical Journal International, 2017, 209(3):1629-1647.
[27]
Dai Y H, Yuan Y. A nonlinear conjugate gradient method with a strong global convergence property[J]. SIAM Journal on Optimization, 1999, 10(1):177-182.
[28]
Nocedal J, Wright S J. Numerical optimization,2th ed[M]. New York,NY,USA: Springer, 2006.
Zhang Y, Meng D C, Song L W, et al. Seismic velocity inversion method based on feature enhancement U-Net[J]. Oil Geophysical Prospecting, 2024, 59(2):185-194.
[30]
Yang F S, Ma J W. Deep-learning inversion:A next-generation seismic velocity model building method[J]. Geophysics, 2019, 84(4):R583-R599.
Xu X, Zou Z H, Han M L, et al. Deep-learning velocity model building by jointly using seismic first arrivals and early-arrival waveforms[J]. Chinese Journal of Geophysics, 2023, 66(12):5107-5122.
Yang T W, Cao D P, Du N Q, et al. Prediction of shear-wave velocity using receiver functions based on the deep learning method[J]. Chinese Journal of Geophysics, 2022, 65(1):214-226.
