Deep Learning Method for Martian Atmosphere Reconstruction

Abstract

The reconstruction of atmospheric properties encountered during Mars entry trajectories is a crucial element of post-flight mission analysis. We propose a deep learning architecture using a Long Short-Term Memory Network (LSTM) for the reconstruction of Martian density and wind profiles from inertial measurements and guidance commands. The LSTM is trained on a large set of Mars entry trajectories controlled through the Fully Numerical Predictor-corrector Entry Guidance (FNPEG) algorithm, with density and wind from the Mars Global Reference Atmospheric Model (GRAM) 2010. We examine the training of the network, ensuring that the LSTM generalizes well to samples not present in the training set, and assess the performance of the network on a separate training set. The errors of the reconstructed density and wind