arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.08348cond-mat.mtrl-scics.LGphysics.atm-clus
收藏

用原子线图神经网络(ALIGNN)预测晶体化合物的电子态密度

Prediction of the electron density of states for crystalline compounds with Atomistic Line Graph Neural Networks (ALIGNN)

Georgia Institute of Technology(佐治亚理工学院);National Institute of Standards and Technology(美国国家标准与技术研究院);Theiss Research(泰斯研究公司)

Prathik R Kaundinya, Kamal Choudhary, Surya R. Kalidindi

摘要:

基于机器学习(ML)的模型极大地增强了传统的材料发现和设计流程。具体而言,近年来,用于材料属性预测的替代ML模型已经证明了在预测离散标量值目标属性方面的成功,其DFT计算值的合理准确性。然而,由于目标的复杂性和可用训练数据的有限量,诸如电子态密度(DOS)的光谱目标的准确预测提出了更具挑战性的问题。在这项研究中,我们提出了一个扩展的最近开发的原子线图神经网络(ALIGNN),以准确地预测DOS的一个大的材料单元格结构,训练到公开可用的JARVIS-DFT数据集。此外,我们评估两种方法的目标量的表示-一个直接的离散化频谱,和使用自动编码器获得的压缩低维表示。通过这项工作,我们展示了基于图形的特征化和建模方法在预测复杂目标中的实用性,这些目标取决于材料结构的化学和方向特性。

英文摘要:

Machine learning (ML) based models have greatly enhanced the traditional materials discovery and design pipeline. Specifically, in recent years, surrogate ML models for material property prediction have demonstrated success in predicting discrete scalar-valued target properties to within reasonable accuracy of their DFT-computed values. However, accurate prediction of spectral targets such as the electron Density of States (DOS) poses a much more challenging problem due to the complexity of the target, and the limited amount of available training data. In this study, we present an extension of the recently developed Atomistic Line Graph Neural Network (ALIGNN) to accurately predict DOS of a large set of material unit cell structures, trained to the publicly available JARVIS-DFT dataset. Furthermore, we evaluate two methods of representation of the target quantity - a direct discretized spectrum, and a compressed low-dimensional representation obtained using an autoencoder. Through this work, we demonstrate the utility of graph-based featurization and modeling methods in the prediction of complex targets that depend on both chemistry and directional characteristics of material structures.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑