Saved in:
Bibliographic Details
Main Authors: Corso, Jordy Dal, Kofler, Annalena, Cortellazzi, Marco, Bruzzone, Lorenzo, Schölkopf, Bernhard
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.08179
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910202467450880
author Corso, Jordy Dal
Kofler, Annalena
Cortellazzi, Marco
Bruzzone, Lorenzo
Schölkopf, Bernhard
author_facet Corso, Jordy Dal
Kofler, Annalena
Cortellazzi, Marco
Bruzzone, Lorenzo
Schölkopf, Bernhard
contents Radar sounders are electromagnetic instruments that can probe deep into the subsurface of Earth and other planetary bodies by processing the echo of transmitted radar waves. Conventional approaches for analyzing such data rely on approximate assumptions and often produce point estimates that ignore parameter correlations as well as galactic and measurement noise. We propose a simulation-based inference approach to terrain parameter inversion from radar sounder data, where synthetic observations from a GPU-based simulator are used to train a neural network-based density estimator for neural posterior estimation (NPE). By explicitly conditioning on reference surface assumptions, the proposed framework allows systematic evaluation of posterior robustness to reference surface variability. We demonstrate that our NPE model is well calibrated on simulated data and transferable to real Mars radar profiles, where we analyze terrain parameters using literature-informed reference values.
format Preprint
id arxiv_https___arxiv_org_abs_2605_08179
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Neural Posterior Estimation of Terrain Parameters from Radar Sounder Data
Corso, Jordy Dal
Kofler, Annalena
Cortellazzi, Marco
Bruzzone, Lorenzo
Schölkopf, Bernhard
Signal Processing
Instrumentation and Methods for Astrophysics
Machine Learning
Radar sounders are electromagnetic instruments that can probe deep into the subsurface of Earth and other planetary bodies by processing the echo of transmitted radar waves. Conventional approaches for analyzing such data rely on approximate assumptions and often produce point estimates that ignore parameter correlations as well as galactic and measurement noise. We propose a simulation-based inference approach to terrain parameter inversion from radar sounder data, where synthetic observations from a GPU-based simulator are used to train a neural network-based density estimator for neural posterior estimation (NPE). By explicitly conditioning on reference surface assumptions, the proposed framework allows systematic evaluation of posterior robustness to reference surface variability. We demonstrate that our NPE model is well calibrated on simulated data and transferable to real Mars radar profiles, where we analyze terrain parameters using literature-informed reference values.
title Neural Posterior Estimation of Terrain Parameters from Radar Sounder Data
topic Signal Processing
Instrumentation and Methods for Astrophysics
Machine Learning
url https://arxiv.org/abs/2605.08179