Airborne Micro-Tem and Deep Learning for Base of Sand Ultra-Resolution Mapping

A key component in the seismic exploration of sand-covered areas is the characterization of sand dune velocities and the corresponding kinematic and dynamic corrections. Standard practices are related to the mapping of the sand depositional basal surface (base of sand) followed by the application of an empirically derived sand velocity curve for correcting the kinematic distortions. The reconstruction of the base of sand surface becomes challenging when the substratum is fully covered by sand and when it presents a pre-existing uneven topographic relief resulting from sub aerial exposure and erosion. We developed a novel ultra-resolution imaging approach for the base of sand that utilizes helicopter-borne micro-transient EM to achieve a depth resolution of a few meters with continuous spatial coverage. The inversion is performed using an iterative scheme that links the deterministic inversion with deep learning driven by physics. Results indicate an ultra-resolution mapping for the base of sand that reveals a complex paleo topography for the sand depositional surface.