Predicting Martian Regolith Permittivity Using Deep Learning Methods—Revisiting Southern Utopia Planitia

Abstract

China’s first Mars mission [Tianwen-1 (TW-1)] successfully touched down in the Utopia Planitia of Mars with a rover subsurface penetrating radar (RoPeR) carried for exploring the regolith dielectric properties. Hyperbolic fitting is a conventional method to infer the subsurface material relative permittivity from ground penetrating radar (GPR) data. However, it is difficult to directly extract valid hyperbolas from the RoPeR data. Inspired by the recently developed deep learning-based geophysical inversion method to estimate the subsurface wave velocities through GPR data, an improved deep learning architecture is proposed to infer the Martian regolith relative permittivity from the RoPeR data, with self-attention (SA) and cascade modules are introduced into the network. The improved cascade and SA modules can improve the inversion efficiency and mitigate the scatter-diffraction effect of the predicted results. The inverted relative permittivity from the first 60 ns of the RoPeR data demonstrates an approximate line with a mean value of 4.73 in the regolith of interest. The very limited fluctuation of relative permittivity implies that no explicit stratification existing in the investigated regolith, agreeing with the previous studies.