Huang Si-Da, Shang Cheng, Zhang Xiao-Jie, Liu Zhi-Pan
Collaborative Innovation Center of Chemistry for Energy Material , Key Laboratory of Computational Physical Science (Ministry of Education) , Shanghai Key Laboratory of Molecular Catalysis and Innovative Materials , Department of Chemistry , Fudan University , Shanghai 200433 , China . Email:
Chem Sci. 2017 Sep 1;8(9):6327-6337. doi: 10.1039/c7sc01459g. Epub 2017 Jun 30.
While the underlying potential energy surface (PES) determines the structure and other properties of a material, it has been frustrating to predict new materials from theory even with the advent of supercomputing facilities. The accuracy of the PES and the efficiency of PES sampling are two major bottlenecks, not least because of the great complexity of the material PES. This work introduces a "Global-to-Global" approach for material discovery by combining for the first time a global optimization method with neural network (NN) techniques. The novel global optimization method, named the stochastic surface walking (SSW) method, is carried out massively in parallel for generating a global training data set, the fitting of which by the atom-centered NN produces a multi-dimensional global PES; the subsequent SSW exploration of large systems with the analytical NN PES can provide key information on the thermodynamics and kinetics stability of unknown phases identified from global PESs. We describe in detail the current implementation of the SSW-NN method with particular focuses on the size of the global data set and the simultaneous energy/force/stress NN training procedure. An important functional material, TiO, is utilized as an example to demonstrate the automated global data set generation, the improved NN training procedure and the application in material discovery. Two new TiO porous crystal structures are identified, which have similar thermodynamics stability to the common TiO rutile phase and the kinetics stability for one of them is further proved from SSW pathway sampling. As a general tool for material simulation, the SSW-NN method provides an efficient and predictive platform for large-scale computational material screening.
虽然潜在的势能面（PES）决定了材料的结构和其他性质，但即便有了超级计算设备，从理论上预测新材料仍然令人沮丧。PES的准确性和PES采样的效率是两个主要瓶颈，尤其是因为材料PES的复杂性很高。这项工作首次将全局优化方法与神经网络（NN）技术相结合，引入了一种用于材料发现的“全局到全局”方法。这种新颖的全局优化方法称为随机表面行走（SSW）方法，它大规模并行执行以生成全局训练数据集，以原子为中心的NN对其进行拟合可生成多维全局PES；随后使用解析NN PES对大型系统进行SSW探索，可以提供有关从全局PES中识别出的未知相的热力学和动力学稳定性的关键信息。我们详细描述了SSW-NN方法的当前实现方式，特别关注全局数据集的大小以及能量/力/应力NN的同步训练过程。以一种重要的功能材料TiO为例，展示了自动全局数据集生成、改进的NN训练过程以及在材料发现中的应用。确定了两种新的TiO多孔晶体结构，它们与常见的TiO金红石相具有相似的热力学稳定性，并且通过SSW路径采样进一步证明了其中一种的动力学稳定性。作为材料模拟的通用工具，SSW-NN方法为大规模计算材料筛选提供了一个高效且具有预测性的平台。
