Encoder-Decoder Neural Networks in Interpretation of X-ray Spectra
This work addresses the challenge of interpreting complex X-ray spectra for researchers in spectroscopy, though it is incremental as it builds on existing methods like ECA.
The study tackled the problem of interpreting X-ray spectroscopic data by comparing encoder-decoder neural networks (EDNN) with emulator-based component analysis (ECA), finding that EDNN outperformed ECA in covered target variable variance but had issues with interpreting latent variables physically, leading to a hybrid network that combined linear projection from ECA to improve interpretability.
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.