Projects

Virginia Tech will develop a look-ahead sensing system based on integrated electromagnetic and seismic sensors to guide and assist drilling to lower the cost and safety concerns of undergrounding power lines. The system's sensors, in the form of radar and accelerometers, would be mounted on and behind the drill head, with complimentary distributed acoustic sensing at the surface to detect obstructions within at least 10 feet of drilling operations. Artificial intelligence capabilities would interpret the geophysical data from the sensors and provide a real-time prediction of obstacles to operators within seconds.

Three-dimensional (3D) seismic full waveform inversion (FWI) shows strong potential, but is currently too time-consuming for general use. Instead, we propose pseudo-3D (P-3D) imaging that combines multiple two-dimensional images of shear wave velocity (Vs) predicted using AI to create a 3D image of the subsurface. We evaluate the method on a real dataset, where seven lines of seismic data were used to characterize a 50 m by 30 m area to a depth of 20 m. The entire data collection and P-3D model generation took only three hours to complete by a seven-person team.