arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.04810cond-mat.mtrl-scics.LG
收藏

AlphaCrystal-II:利用深度学习基于距离矩阵的晶体结构预测

AlphaCrystal-II: Distance matrix based crystal structure prediction using deep learning

University of Southern Maine(南缅因大学);University of South Carolina(南卡罗来纳大学);Guizhou University of Finance and Economics(贵州财经大学)

Yuqi Song, Rongzhi Dong, Lai Wei, Qin Li, Jianjun Hu

AI总结:

针对从头算 CSP 成本高昂的问题,本文提出 AlphaCrystal-II,通过深度学习从已知晶体中学习原子间相互作用、预测距离矩阵并重建三维结构,实验验证了其有效性与可靠性。

摘要:

稳定晶体结构的计算预测对大规模发现新型功能材料具有深远影响。然而,仅根据材料的组成或化学式预测晶体结构是一项前景广阔但颇具挑战性的任务,因为传统的从头算晶体结构预测(CSP)方法依赖耗时的全局搜索和第一性原理自由能计算。受近期深度学习方法在蛋白质结构预测中取得成功的启发——这些方法利用成对氨基酸相互作用来描述三维结构——我们提出了 AlphaCrystal-II,这是一种新颖的基于知识的解决方案,利用现有已知晶体结构中丰富的原子间相互作用模式。AlphaCrystal-II 预测目标晶体材料的原子距离矩阵,并利用该矩阵重建其三维晶体结构。通过利用已知晶体结构中大量的原子间关系,我们的方法经全面实验证明在结构预测方面具有显著的有效性和可靠性。本工作凸显了数据驱动方法在加速发现和设计具有定制性能的新材料方面的潜力。

英文摘要:

Computational prediction of stable crystal structures has a profound impact on the large-scale discovery of novel functional materials. However, predicting the crystal structure solely from a material's composition or formula is a promising yet challenging task, as traditional ab initio crystal structure prediction (CSP) methods rely on time-consuming global searches and first-principles free energy calculations. Inspired by the recent success of deep learning approaches in protein structure prediction, which utilize pairwise amino acid interactions to describe 3D structures, we present AlphaCrystal-II, a novel knowledge-based solution that exploits the abundant inter-atomic interaction patterns found in existing known crystal structures. AlphaCrystal-II predicts the atomic distance matrix of a target crystal material and employs this matrix to reconstruct its 3D crystal structure. By leveraging the wealth of inter-atomic relationships of known crystal structures, our approach demonstrates remarkable effectiveness and reliability in structure prediction through comprehensive experiments. This work highlights the potential of data-driven methods in accelerating the discovery and design of new materials with tailored properties.

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。

↑