Iterative Multiparameter Elastic Waveform Inversion Using Prestack Time Imaging and Kirchhoff approximation

Hassan Khaniani

ABSTRACT

This thesis proposes a “standard strategy” for iterative inversion of elastic properties from the seismic reflection data. The term “standard” refers to the current hands-on commercial techniques that are used for the seismic imaging and inverse problem. The method is established to reduce the computation time associated with elastic Full Waveform Inversion (FWI) methods. It makes use of AVO analysis, prestack time migration and corresponding forward modeling in an iterative scheme.

The main objective is to describe the iterative inversion procedure used in seismic reflection data using simplified mathematical expression and their numerical applications. The frame work of the inversion is similar to (FWI) method but with less computational costs. The reduction of computational costs depends on the data conditioning (with or without multiple data), the level of the complexity of geological model and acquisition condition such as Signal to Noise Ratio (SNR). Many processing methods consider multiple events as noise and remove it from the data. This is the motivation for reducing the computational cost associated with Finite Difference Time Domain (FDTD) forward modeling and Reverse Time Migration (RTM)-based techniques. Therefore, a one-way solution of the wave equation for inversion is implemented.

While less computationally intensive depth imaging methods are available by iterative coupling of ray theory and the Born approximation, it is shown that we can further reduce the cost of inversion by dropping the cost of ray tracing for traveltime estimation in a way similar to standard Prestack Time Migration (PSTM) and the corresponding forward modeling. This requires the model to have smooth lateral variations in elastic properties, so that the traveltime of the scatterpoints can be approximated by a Double Square Root (DSR) equation.

To represent a more realistic and stable solution of the inverse problem, while considering the phase of supercritical angles, the boundary condition of the wave equation is set up along reflection surfaces. Hence, the surface integral Kirchhoff approximation is used as a mathematical framework instead of the volume integral of the Born approximation.

In addition, I study the feasibility of iterative coupling of ray theory with the Kirchhoff approximation for inversion. For the amplitude considerations, the direct relationship between the scattering potential of the Born approximation with the reflectivity function of the asymptotic iii Kirchhoff approximation for elastic waves is used. Therefore, I use the linearized Zoeppritz approximation of Aki and Richards (1980) for computation of the forward modeling and migration operators as well as gradient function from Amplitude vs Offset (AVO) inversion.

The multiparameter elastic inversion approach is applicable to all types of reflected wavefields such as P-to-P, P-to-S, S-to-S and S-to-P. Traveltime estimation of forward modeling and migration/inversion operators are based on the DSR equation. All operators involved in inversion, including the background model for DSR and AVO are updated at each iteration. The migration/inversion procedure maps the mode converted waves to the traveltime of incident waves which fixes the registration problem of events that travel from source to scatter point. The inversion of the reflected P-to-P and P-to-S synthetic and field data are provided for the numerical examples.

This approach is applicable for complex structures however, to estimate the traveltime of scatterpoints, ray tracing can be added to the algorithm. For such a medium, the scatterpoint traveltime approximations from the PSTM, is compared to the PSDM approach using numerical analysis of ray- and FDTD-based modeling.

In part of this thesis, I further improve the conventional velocity analysis of Common Scatter Point (CSP) gathers by including the tilt effects. I show that travel time response of scatter points beneath a dipping interface experiences an additional linear time shift. The normal hyperbolic shape of travel time in a CSP gather becomes tilted, causing inaccuracy in velocity analysis. The focusing of the separated energy in the semblance plots is enhanced by removing the tilt effects. As a result, the accuracy of migration velocity inversion is enhanced and the focusing of output images of time migration is improved.

View full article as PDF (6.33 Mb)