Statistical Learning for End-to-End Simulations

TL;DR

This paper evaluates statistical learning methods, specifically Gaussian Process emulators, as fast and accurate alternatives to traditional interpolation for generating synthetic scenes in satellite mission simulations, reducing computation time while improving accuracy.

Contribution

It demonstrates that Gaussian Process emulators outperform linear interpolation in accuracy and efficiency for sampling radiance data in end-to-end satellite simulation models.

Findings

Gaussian Process emulators are more accurate than linear interpolation.

Emulators significantly reduce computation time.

Emulation improves scene generation quality in satellite simulations.

Abstract

End-to-end mission performance simulators (E2ES) are suitable tools to accelerate satellite mission development from concet to deployment. One core element of these E2ES is the generation of synthetic scenes that are observed by the various instruments of an Earth Observation mission. The generation of these scenes rely on Radiative Transfer Models (RTM) for the simulation of light interaction with the Earth surface and atmosphere. However, the execution of advanced RTMs is impractical due to their large computation burden. Classical interpolation and statistical emulation methods of pre-computed Look-Up Tables (LUT) are therefore common practice to generate synthetic scenes in a reasonable time. This work evaluates the accuracy and computation cost of interpolation and emulation methods to sample the input LUT variable space. The results on MONDTRAN-based top-of-atmosphere radiance data show that Gaussian Process emulators produced more accurate output spectra than linear interpolation at a fraction of its time. It is concluded that emulation can function as a fast and more accurate alternative to interpolation for LUT parameter space sampling.