Accelerating 2D and 3D frequency-domain seismic wave modeling through interpolating frequency-domain wavefields by deep learning

Cao，Wenzhong1; Li，Quanli2,3,4; Zhang，Jie1; Zhang，Wei2,3,4

2022-07-01

10.1190/geo2021-0435.1

GEOPHYSICS   Impact Factor & Quartile

0016-8033

1942-2156

An attractive feature of finite-difference modeling in the frequency domain is the low recomputation cost to simulate seismic waves for many sources through the same velocity model. However, it is time consuming if many frequencies are involved for solving the linear wave equations, particularly, for large 3D velocity models. We propose accelerating the modeling by applying deep learning. Because similarity appears among the wavefields in near frequencies, we can extract similar features and reconstruct the unknown wavefields by deep learning. We compute fewer frequency-domain wavefields with a large frequency interval by conventional modeling methods, such as finite-difference methods, and then interpolate more frequency-domain wavefields with a small frequency interval by applying deep learning. Numerical examples demonstrate that the U-Net, which is trained by the data on 10 2D simple-layered models, can be used to interpolate the data on SEG Advanced Modeling models and also can be used to interpolate the data on the 3D layered model and 3D overthrust model. A series of tests on perturbation models prove that the U-Net performance is still good when the root-mean-square value of the velocity model perturbation relative to the initial model is up to 15%. Compared with traditional modeling methods, the computational time of interpolating by applying deep learning is negligible, especially for 3D models. After the network is trained, the acceleration strategy helps to reduce the runtime by approximately 50% for a modeling problem because the U-Net can be used to interpolate 50% of the data that would otherwise need to be modeled. Although training the model will take some time, good generalization of the U-Net, especially for 3D problems, enhances its benefits on the application for frequency-domain forward modeling.

finite difference frequency domain interpolation machine learning modeling

EI

English

Corresponding

20222612274060

3D modeling ; Deep learning ; Finite difference method ; Frequency domain analysis ; Learning systems ; Seismic waves ; Seismology ; Three dimensional computer graphics ; Wave equations

Ergonomics and Human Factors Engineering:461.4 ; Seismology:484 ; Earthquake Measurements and Analysis:484.1 ; Data Processing and Image Processing:723.2 ; Computer Applications:723.5 ; Calculus:921.2 ; Mathematical Transformations:921.3 ; Numerical Methods:921.6

GEOSCIENCES

2-s2.0-85132702531

Scopus

1.University of Science and Technology of China,School of Earth and Space Sciences,Hefei,China
2.Southern University of Science and Technology,Shenzhen Key Laboratory of Deep Offshore Oil and Gas Exploration Technology,Shenzhen,China
3.Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou),Guangzhou,China
4.Southern University of Science and Technology,Department of Earth and Space Sciences,Shenzhen,China

Cao，Wenzhong,Li，Quanli,Zhang，Jie,et al. Accelerating 2D and 3D frequency-domain seismic wave modeling through interpolating frequency-domain wavefields by deep learning[J]. GEOPHYSICS,2022,87(4):T315-T328.

Cao，Wenzhong,Li，Quanli,Zhang，Jie,&Zhang，Wei.(2022).Accelerating 2D and 3D frequency-domain seismic wave modeling through interpolating frequency-domain wavefields by deep learning.GEOPHYSICS,87(4),T315-T328.

Cao，Wenzhong,et al."Accelerating 2D and 3D frequency-domain seismic wave modeling through interpolating frequency-domain wavefields by deep learning".GEOPHYSICS 87.4(2022):T315-T328.