Structural descriptors and information extraction from X-ray emission spectra: aqueous sulfuric acid
: Eronen, E. A.; Vladyka, A.; Sahle, Ch. J.; Niskanen, J.
Publisher: ROYAL SOC CHEMISTRY
: CAMBRIDGE
: 2024
: Physical Chemistry Chemical Physics
: PHYSICAL CHEMISTRY CHEMICAL PHYSICS
: PHYS CHEM CHEM PHYS
: 26
: 34
: 22752
: 22761
: 10
: 1463-9076
: 1463-9084
DOI: https://doi.org/10.1039/d4cp02454k
: https://doi.org/10.1039/D4CP02454K
: https://research.utu.fi/converis/portal/detail/Publication/457702042
Machine learning can reveal new insights into X-ray spectroscopy of liquids when the local atomistic environment is presented to the model in a suitable way. Many unique structural descriptor families have been developed for this purpose. We benchmark the performance of six different descriptor families using a computational data set of 24 200 sulfur K beta X-ray emission spectra of aqueous sulfuric acid simulated at six different concentrations. We train a feed-forward neural network to predict the spectra from the corresponding descriptor vectors and find that the local many-body tensor representation, smooth overlap of atomic positions and atom-centered symmetry functions excel in this comparison. We found a similar hierarchy when applying the emulator-based component analysis to identify and separate the spectrally relevant structural characteristics from the irrelevant ones. In this case, the spectra were dominantly dependent on the concentration of the system, whereas adding the second most significant degree of freedom in the decomposition allowed for distinction of the protonation state of the acid molecule.We systematically benchmark structural descriptors in machine learning and study information recoverability from X-ray emission spectra of aqueous sulfuric acid.
:
E. A. E. acknowledges Jenny and Antti Wihuri Foundation for funding. E. A. E., A. V. and J. N. acknowledge Academy of Finland for funding via project 331234. The authors acknowledge CSC – IT Center for Science, Finland, and the FGCI – Finnish Grid and Cloud Infrastructure for computational resources.
