Encoder-Decoder Neural Networks in Interpretation of X-ray Spectra

TL;DR

This paper explores the use of encoder-decoder neural networks for interpreting simulated X-ray spectra, aiming to identify key structural features, and proposes a hybrid approach to improve interpretability while maintaining performance.

Contribution

It demonstrates the effectiveness of EDNNs in spectral emulation, compares them with emulator-based component analysis, and introduces a hybrid model for better interpretability.

Findings

EDNN outperforms ECA in variance coverage

Latent variables are challenging to interpret physically

Hybrid model maintains interpretability and performance

Abstract

Encoder--decoder neural networks (EDNN) condense information most relevant to the output of the feedforward network to activation values at a bottleneck layer. We study the use of this architecture in emulation and interpretation of simulated X-ray spectroscopic data with the aim to identify key structural characteristics for the spectra, previously studied using emulator-based component analysis (ECA). We find an EDNN to outperform ECA in covered target variable variance, but also discover complications in interpreting the latent variables in physical terms. As a compromise of the benefits of these two approaches, we develop a network where the linear projection of ECA is used, thus maintaining the beneficial characteristics of vector expansion from the latent variables for their interpretation. These results underline the necessity of information recovery after its condensation and identification of decisive structural degrees of freedom for the output spectra for a justified interpretation.