Full-waveform inversion based on deep learning and the temporal modified and spatial optimized symplectic partitioned Runge-Kutta method

Wang, C.G., Zhou, Y.J., He, X.J., Huang, X.Y. and Lu, F., 2022. Full-waveform inversion based on deep learning and the temporal modified and spatial optimized symplectic partitioned Runge-Kutta method. Journal of Seismic Exploration, 31: 501-521. This study uses deep learning techniques to propose a full-waveform inversion (FWI) method. This method uses the Temporal Modified and Spatial Optimized Symplectic Partitioned Runge-Kutta (TMSOS) method, for the forward modeling in the FWI process. Additionally, optimizer, loss function in deep learning are utilized to perform FWI. We used recurrent neural networks in deep learning to implement the forwarding modeling method-TMSOS. This method uses the second-order MSPRK scheme and an eighth-order optimized finite difference scheme for temporal and spatial discretization, respectively, to obtain high precision with lesser computational effort. The Nadam optimizer, packaged in the Tensorflow software, is used to optimize the model parameters in this study. Additionally, Huber loss is used as the objective function of FWI. Several numerical simulations were done to verify the effectiveness of the proposed method. First, the effectiveness of the TMSOS forward modeling method was compared with the finite difference (FD) method. Then FWI was performed using the TMSOS forward modeling method for the velocity anomaly model, the third-order model, and the complex Sigsbee velocity model. Finally, the inversion results under the three loss functions were compared. The numerical results suggest that the TMSOS forward modeling method has better computational efficiency and smaller resultant numerical dispersion than the traditional FD method. The inversion results of the TMSOS method are closer to those of the actual model, with a better inversion effect. Additionally, the Huber loss function has better stability in selecting the learning rate.
- Blanch, J.O. and Robertsson, J., 2010. A modified Lax-Wendroff correction for wavepropagation in media described by Zener elements. Geophys. J. Roy. Astronom.Soc., 131: 381-386.
- Booth, D.C. and Crampin, S., 1983. The anisotropic reflectivity technique: anomalousreflected arrivals from an anisotropic upper mantle. Geophys. J. Roy. Astronom.Soc., 72: 767-782.
- Carcione, J.M., Herman, G.C. and ten Kroode, A., 2002. Seismic modeling.Geophysics, 67: 1304-1325.
- Dablain, M.A., 1986. The application of high-order differencing to the scalar waveequation. Geophysics, 51: 54-66.
- Dozat, T., 2016. Incorporating Nesterov Momentum into Adam.http://cs229.stanford.edu/proj2015/054_report.pdf.
- Elman, J.L., .1990. Finding structure in time. Cognit. Sci., 14: 179-211.
- Fuchs, K. and Miiller, G., 2010. Computation of synthetic seismograms with thereflectivity method and comparison with observations. Geophys. J. Roy.Astronom. Soc., 23: 417-433.
- Hanyga, A., 1986. Gaussian beams in anisotropic elastic media. Geophys. J. Roy.Astronom. Soc., 85: 473-504.
- He, X., Yang, D. and Wu, H., 2015. A weighted Runge-Kutta discontinuous Galerkinmethod for wavefield modelling. Geophys. J. Internat., 200: 1389-1410.
- Hrennikoff, A., 1941. Solution of problems of elasticity by the frame-work method. J.Appl. Mechan. A, 8: 169-175.
- Igel, H., Mora, P. and Riollet, B., 1995. Anisotropic wave propagation through finite-difference grids. Geophysics, 60: 1203-1216.
- Virieux, J., 1984. SH-wave propagation in heterogeneous media; velocity-stress finite-difference method. Geophysics, 49: 1933-1957.
- Virieux, J., 1986. P-SV wave propagation in heterogeneous media; velocity-stress finite-difference method. Geophysics, 51: 889-901.
- Kirkpatrick, S., Gelatt, C.D. and Vecchi, M.P., 1983. Optimization by simulatedannealing. Science, 220: 671-680.
- Komatitsch, D., Barnes, C. and Tromp, J., 2000. Simulation of anisotropic wavepropagation based upon a spectral element method. Geophysics, 65: 1251-1260.
- Lang, C., 2017. Frequency-domain full waveform inversion based on nearly analyticdiscrete methods. Ph.D. Thesis, Tsinghua University, Tsinghua.
- Liu, S., Yang, D., Lang, C., Wang, W. and Pan, Z., 2016. Modified symplectic schemeswith nearly-analytic discrete operators for acoustic wave simulations. Comput.Phys. Communic., 213: 52-63.
- Liu, S., Yang, D. and Ma, J., 2017). A modified symplectic PRK scheme for seismicwave modeling. Comput. Geosci., 99: 28-36.
- Ma, S., Li, D., Hu, T., Xing, Y. and Nai, W., 2020. Huber Loss function based onvariable step beetle antennae search algorithm with Gaussian direction. 12th
- Internat. Conf. Intellig. Human-Machine Syst. Cybernet. [HMSC).
- Ma, X., Yang, D. and Liu, F., 2011. A nearly analytic symplectically partitioned Runge—
- Kutta method for 2-D seismic wave equations. Geophys. J. Internat., 187: 480-
- Madariaga, R., 1976. Dynamics of an expanding circular fault. Bull. Seismol. Soc. Am.,66: 639-666.
- Michael, D. and Martin, K., 2006. An arbitrary high-order discontinuous Galerkinmethod for elastic waves on unstructured meshes - I. The two-dimensionalisotropic case with external source terms. Geophys. J. Internat., 167: 319-336.
- Rao, Y. and Wang, Y., 2017. Seismic waveform tomography with shot-encoding using arestarted L-BFGS algorithm. Scient. Rep., 7: 1-9.
- Riviere, B. and Wheeler, M.F., 2003. Discontinuous finite element methods for acousticand elastic wave problems. Contemp. Mathemat., 329: 271-282.
- Sen, M.K. and Stoffa, P.L., 2013. Global Optimization Methods in Geophysical
- Inversion. Cambridge University Press, Cambridge, 4: 1-22.
- Wang, S., Yang, D. and Yang, K., 2002. Compact finite difference scheme for elasticequations. J. Tsinghua Univ. (Sci. Technol.), 42: 1128-1131.
- Wang, Y., 2007. Calculation method of inversion and its application. Inst. Geol.
- Geophys., Chinese Academy of Sciences 2006 Ann. Conf., Beijing, China.
- Yang, D., 2004. An optimal nearly analytic discrete method for 2D acoustic and elasticwave equations. Bull. Seismol. Soc. Am., 94: 1982-1991.
- Yang, D., Peng, J., Lu, M. and Terlaky, T., 2006. Optimal nearly analytic discreteapproximation to the scalar wave equation. Bull. Seismol. Soc. Am., 96: 1114-
- Yang, D., Teng, J., Zhang, Z. and Liu, E., 2003. A nearly analytic discrete method foracoustic and elastic wave equations in anisotropic media. Bull. Seismol. Soc.Am., 93: 882-890.
- Zhang, J. and Yao, Z., 2013. Optimized explicit finite-difference schemes for spatialderivatives using maximum norm. J. Computat. Phys., 250: 511-526.
- Zhu, C., Byrd, R.H., Lu, P. and Nocedal, J., 1997. Algorithm 778: L-BFGS-B: Fortransubroutines for large-scale bound-constrained optimization. Acm Transact.Mathemat. Softw., 23: 550-560.