A method is presented for predicting the space group of a structure given a calculated or measured atomic pair distribution function (PDF) from that structure. The method utilizes machine learning models trained on more than 100 000 PDFs calculated from structures in the 45 most heavily represented space groups. In particular, a convolutional neural network (CNN) model is presented which yields a promising result in that it correctly identifies the space group among the top-6 estimates 91.9% of the time. The CNN model also successfully identifies space groups for 12 out of 15 experimental PDFs. Interesting aspects of the failed estimates are discussed, which indicate that the CNN is failing in similar ways as conventional indexing algorithms applied to conventional powder diffraction data. This preliminary success of the CNN model shows the possibility of model-independent assessment of PDF data on a wide class of materials.

中文翻译：

---

使用机器学习方法从原子对分布函数确定结构的空间群

提出了一种在给定计算或测量的结构原子对分布函数（PDF）的情况下预测该结构的空间群的方法。该方法利用机器学习模型，该模型根据 45 个最具代表性的空间组中的结构计算出的 100,000 多个 PDF 进行训练。特别是，提出了一种卷积神经网络 (CNN) 模型，该模型产生了令人鼓舞的结果，因为它在 91.9% 的时间内正确识别了前 6 个估计中的空间群。CNN 模型还成功识别了 15 个实验 PDF 中的 12 个空间群。讨论了失败估计的有趣方面，这表明 CNN 的失败方式与应用于传统粉末衍射数据的传统索引算法类似。CNN 模型的初步成功表明了对多种材料上的 PDF 数据进行独立于模型评估的可能性。