Towards Structural Reconstruction from X-Ray Spectra

Abstract

We report a statistical analysis of Ge K-edge X-ray emission spectra simulated for amorphous GeO${}_2$ at elevated pressures. We find that employing machine learning approaches we can reliably predict the statistical moments of the K${\beta }^{\prime \prime }$ and K${\beta }_2$ peaks in the spectrum from the Coulomb matrix descriptor with a training set of $\sim 10^4$ samples. Spectral-significance-guided dimensionality reduction techniques allow us to construct an approximate inverse mapping from spectral moments to pseudo-Coulomb matrices. When applying this to the moments of the ensemble-mean spectrum, we obtain distances from the active site that match closely to those of the ensemble mean and which moreover reproduce the pressure-induced coordination change in amorphous GeO${}_2$. With this approach utilizing emulator-based component analysis, we are able to filter out the artificially complete structural information available from simulated snapshots, and quantitatively analyse structural changes that can be inferred from the changes in the K$\beta$ emission spectrum alone.

References in corpus (3)

• Classification of Local Chemical Environments from X-ray Absorption Spectra using Supervised Machine Learning
• Emulator-based Decomposition for Structural Sensitivity of Core-level Spectra
• Machine learning in interpretation of electronic core-level spectra

Cited by in corpus (4)

• Information Bottleneck in Peptide Conformation Determination by X-ray Absorption Spectroscopy
• Structural Descriptors and Information Extraction from X-ray Emission Spectra: Aqueous Sulfuric Acid
• Implementation of the Emulator-based Component Analysis
• Encoder-Decoder Neural Networks in Interpretation of X-ray Spectra