Towards structural reconstruction from X-ray spectra

We report a statistical analysis of Ge K-edge X-ray emission spectra simulated for amorphous GeO2 at elevated pressures. We find that employing machine learning approaches we can reliably predict the statistical moments of the K beta '' and K beta(2) peaks in the spectrum from the Coulomb matrix descriptor with a training set of similar to 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 GeO2. 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.

Automated summary

We demonstrate that machine learning can be used to predict statistical properties of Ge K-edge X-ray emission spectra for amorphous GeO2 at elevated pressures. By reducing the dimensionality of the spectra and mapping them to pseudo-Coulomb matrices, we are able to accurately determine distances from the active site and reproduce pressure-induced coordination changes. Our approach filters out artificial structural information and allows for quantitative analysis of structural changes inferred solely from changes in the K beta emission spectrum.