Machine Learning to Predict Spectral Anisotropy in Valence-to-Core X-ray Emission Spectroscopy

TL;DR

This paper develops a machine learning model to quantitatively predict spectral anisotropy in valence-to-core X-ray emission spectroscopy using local geometric and chemical features from crystal structures, trained on a large dataset.

Contribution

It introduces a random forest model that predicts spectral anisotropy from simplified structural data, advancing beyond qualitative symmetry-based classifications.

Findings

Model accurately predicts spectral anisotropy levels.

Ligand spatial moments are key predictors.

Trained on over 10,000 structures from the Materials Project.

Abstract

Polarization analysis in x-ray spectroscopy provides an orientation dependent sensitivity to local bonding environments. For a cluster of atoms, polarization sensitivity is most often discussed through the lens of point group symmetries. However, this is a discrete, qualitative method of classifying clusters, and it does little to indicate the degree of spectral anisotropy. Here we adopt a random forest model for quantitative prediction of spectral anisotropy. Its input relies on simplified local geometric and chemical information that can be obtained from any crystal structure file. The model is trained on over 10,000 experimentally realized transition metal structures from the Materials Project, with the target being VtC-XES calculated using the real space Green's function code FEFF. We find that the model can strongly predict the degree of spectral anisotropy, with the primary factors being derived from the spatial moments of ligands in a cluster.