Department of Physics, University of Toyama, Japan.
Toyama Prefectural University, Japan.
J Synchrotron Radiat. 2020 Jul 1;27(Pt 4):1069-1073. doi: 10.1107/S1600577520005767. Epub 2020 May 20.
Grazing-incidence small-angle X-ray scattering (GISAXS) patterns have multiple superimposed contributions from the shape of the nanoscale structure, the coupling between the particles, the partial pair correlation, and the layer geometry. Therefore, it is not easy to identify the model manually from the huge amounts of combinations. The convolutional neural network (CNN), which is one of the artificial neural networks, can find regularities to classify patterns from large amounts of combinations. CNN was applied to classify GISAXS patterns, focusing on the shape of the nanoparticles. The network found regularities from the GISAXS patterns and showed a success rate of about 90% for the classification. This method can efficiently classify a large amount of experimental GISAXS patterns according to a set of model shapes and their combinations.
掠入射小角 X 射线散射（GISAXS）图谱具有来自纳米级结构形状、颗粒间耦合、部分配对相关和层几何形状的多种叠加贡献。因此，从大量组合中手动识别模型并不容易。卷积神经网络（CNN）是人工神经网络之一，它可以从大量组合中找到规律来对模式进行分类。CNN 被应用于分类 GISAXS 模式，重点是纳米颗粒的形状。该网络从 GISAXS 模式中发现了规律，并在分类方面取得了约 90%的成功率。这种方法可以根据一组模型形状及其组合，有效地对大量实验 GISAXS 图谱进行分类。
