Fritz-Haber-Institut der Max-Planck-Gesellschaft, 14195, Berlin-Dahlem, Germany.
Nat Commun. 2021 Oct 29;12(1):6234. doi: 10.1038/s41467-021-26511-5.
Due to their ability to recognize complex patterns, neural networks can drive a paradigm shift in the analysis of materials science data. Here, we introduce ARISE, a crystal-structure identification method based on Bayesian deep learning. As a major step forward, ARISE is robust to structural noise and can treat more than 100 crystal structures, a number that can be extended on demand. While being trained on ideal structures only, ARISE correctly characterizes strongly perturbed single- and polycrystalline systems, from both synthetic and experimental resources. The probabilistic nature of the Bayesian-deep-learning model allows to obtain principled uncertainty estimates, which are found to be correlated with crystalline order of metallic nanoparticles in electron tomography experiments. Applying unsupervised learning to the internal neural-network representations reveals grain boundaries and (unapparent) structural regions sharing easily interpretable geometrical properties. This work enables the hitherto hindered analysis of noisy atomic structural data from computations or experiments.
由于能够识别复杂模式，神经网络可以推动材料科学数据分析的范式转变。在这里，我们引入了基于贝叶斯深度学习的晶体结构识别方法 ARISE。作为一个重大的进步，ARISE 对结构噪声具有鲁棒性，并且可以处理超过 100 种晶体结构，这个数量可以根据需要进行扩展。虽然只在理想结构上进行训练，但 ARISE 可以正确地描述从合成和实验资源中获得的受到强烈干扰的单晶和多晶系统。贝叶斯深度学习模型的概率性质允许获得有原则的不确定性估计，这些估计与电子断层扫描实验中金属纳米粒子的晶体有序性相关。对内部神经网络表示进行无监督学习揭示了晶界和（不明显）具有易于解释的几何性质的结构区域。这项工作使得以前由于噪声而受到阻碍的来自计算或实验的原子结构数据的分析成为可能。
