Least-squares reverse time migration (LSRTM) aims to produce a high-quality migration image of complex geological structures. However, the weaker deep seismic reflections are often masked by the overlying strata in migration images. Therefore, it is difficult for the LSRTM to image the deeper structures. This letter proposes a phase-amplitude LSRTM (PA-LSRTM) in the time-frequency domain to improve the migration image of deep seismic reflections and subsalt structures. The PA-LSRTM is formulated as an inverse problem that minimizes the time-frequency phase-amplitude difference between the predicted and observed data. The seismic data was initially transformed into the time-frequency domain to establish a PA-LSRTM misfit. An amplitude factor was then introduced in the time-frequency misfit to weaken the weights of amplitude components. In this case, it emphasized the similarity of phase components. Furthermore, the sparsity promotion method was combined with a simultaneous source technique to increase the computational efficiency and reduce the crosstalk noise. The PA-LSRTM with sparsity promotion (SPA-LSRTM) misfit can finally be solved using a Fast Iterative Shrinkage-Thresholding Algorithm (FISTA). The numerical and marine field data tests demonstrate that the SPA-LSRTM can effectively produce a high-resolution image of deep structures.

Safety of the mine roadway constructions is controlled by geological disasters such as faults, goaves and so on. The advanced prediction has become an in-demand topic, and advanced detection method of the reflected wave is a crucial technology for advanced prediction of geological anomalies. However, due to the influence of the complex near-source seismic wavefield in the coal mine roadway, the result of wavefield separation and migration imaging is not accurate, which lead to the fact that the fine imaging of geological anomaly is difficult. A comparative analysis of wavefield separation method of kinematics and dynamics is carried out in this paper to solve this problem. A factor of principal polarization direction is introduced according to “the orthogonal difference between the propagation direction of P-wave and S-wave and the vibration direction of particle” starting from the real-time polarization analysis from three-component seismic signals. By the factor, a modified function is constructed and integrated into pre-stack diffraction migration, which put forward the polarization migration method that incorporates wavefield separation with migration imaging. The results of physical simulation and field survey in Xiangyuan coal mine in western China are as follows: The fine imaging by using advanced detection of the reflected waves in underground coal mine can be achieved by using polarization migration in linear observation system and the polarization migration has the effect of enhancing the spatial resolution.