Well-Guided Multisource Elastic Full-Waveform Inversion

Full-waveform inversion (FWI) has been considered one of the most promising approaches to estimating high-resolution subsurface parameters, which takes advantage of the kinematics and dynamics information of seismic data. However, FWI is greatly dependent on the accuracy of the initial model and vulnerable to the issue of local minimum. Moreover, the multisource and multiparameter crosstalk artifacts make multisource elastic FWI (MS-EFWI) more likely to trap into a suboptimal inversion result. To remedy this defect, this study proposes an efficient EFWI paradigm that combines the crosstalk-free MS-EFWI method and a well-guided initial model-building algorithm. Specifically, we apply a harmonic wavelet encoding technology to MS-EFWI, by which the multisource wavefields can be completely deblended without crosstalk noise. The well-guided structure-oriented interpolation, with the aid of the dip information derived from the initial migration images, is designed to build a satisfactory initial model and, therefore, reduce the risk of cycle skipping. Numerical examples based on the 2-D overthrust model and the Marmousi model further demonstrate the feasibility and robustness of the proposed method with a relatively little number of iterations.