Diffraction wave could be sensitive to the subsurface discontinuity, such as fractures or faults. This research aims to develop innovative technique to separate and image the diffraction waves from conventional reflection waves.

Multicomponent seismic datasets, such as PS (downgoing P-wave and upgoing S-wave), offer significant advantages over conventional PP (downgoing and upgoing P-wave) data for subsurface characterization. By integrating PP with PS data, a more complete understanding of the subsurface can be achieved. However, effective use of these datasets depends on registration, a process used to align different wavefields. Successful registration brings multicomponent seismic datasets into a common time domain, typically that of PP. This task becomes particularly challenging when misalignments are large, the data contain noise, or the frequency and phase content vary. In this study, we present a supervised deep learning method to estimate time shifts between stacked PP and PS data. A detailed workflow is introduced for registering PP and PS data, which begins by stretching and squeezing PP and PS datasets using a variable Vp/Vs ratio to create training data with time-shift labels. We then develop a modified version of the Recurrent All-Pairs Field Transforms (RAFT) deep learning architecture, which formulates optical flow estimation to predict time shifts. The model is trained using an L1 loss between predicted and true shift fields. Finally, we apply the workflow to the Big Sky multicomponent dataset, demonstrating its effectiveness and feasibility for registering PP and PS seismic data.

This research aims to use PP, PS, SS multicomponent seismic datasets to detect and characterize the subsurface features with strong anisotropic elasticity, such as fractures. 

This research aims to use rock physics and machine learning techniques to estimate geomechanical or petrophysical properties of unconventional reservoir. We are working on the estimation of the TOC and Brittleness of the Tuscaloosa Marine Shale by using machine learning technique.  

Time-lapse seismic surveys refer to repeated seismic surveys, which can help to capture the subsurface rock properties changes. However, it could be very difficult to keep the consistence of the repeated surveys with baseline survey, which could cause problematic utilization of the time-lapse seismic data. We plan to improve the reliability of the time-lapse seismic analysis, especially two kinds of seismic attributes: amplitude and travel-time.