Robustness test of the <i>spacegroupMining</i> model for determining space groups from atomic pair distribution function data

Machine learning models based on convolutional neural networks have been used for predicting space groups of crystal structures from their atomic pair distribution function (PDF). However, the PDFs to train model are calculated using a fixed set parameters that reflect specific experimental conditions, and accuracy when given generated with different choices these is unknown. In this paper, we report results top-1 top-6 robust applied $r_\text{max}$, $Q_\text{max}$, $Q_\text{damp}$ displacement parameters.