It is demonstrated how k nearest neighbor machine learning methods can be used to classify small-angle scattering data for the most appropriate model to use for data analysis. The results show the promise of machine learning for helping small-angle scattering practitioners translate measured data into scientific results.

It is shown that artificial neural networks can be used to predict the location and shape of neutron Bragg peaks, resulting in increased integration accuracy.

It is demonstrated that using three-dimensional profile fitting of Bragg peaks increases the accuracy and resolution of neutron crystallographic data collected from proteins and reveals new features in nuclear density maps calculated from these data.