Deep learning for x-ray or neutron scattering under grazing-incidence: extraction of distributions

Grazing-incidence small-angle scattering (GISAS) is a technique of significant importance for the investigation of thin multilayered films containing nano-sized objects. It provides morphology information averaged over the sample area. However, this averaging together with multiple reflections and the well-known phase problem make the data analysis challenging and time consuming. In the present paper we show that densely connected neural networks (DenseNets) can be applied for GISAS data analysis and deliver fast and plausible results. The extraction of the rotational distributions of hexagonal nanoparticle arrangements is taken as a case study.

Automated summary

GISAS is an important technique for studying thin multilayered films containing nano-sized objects, providing morphology information averaged over the sample area. However, the data analysis is challenging due to averaging, multiple reflections, and the phase problem. This paper demonstrates that DenseNets can be used for GISAS data analysis to deliver fast and plausible results, using the rotational distributions of hexagonal nanoparticle arrangements as a case study.