首 页
滚动信息 更多 >>
本刊2022年SCI影响因子9.7 (2023年6月发布) (2023-10-23)
本刊2021年SCI影响因子12.256 (2022-07-07)
npj Computational Materials 2019年影响因子达到9... (2020-07-04)
npj Computational Materials获得第一个SCI影响因... (2018-09-07)
英文刊《npj Computational Materials(计算材料学... (2017-05-15)
快捷服务
最新文章 研究综述
过刊浏览 作者须知
期刊编辑 审稿须知
相关链接
· 在线投稿
会议信息
友情链接
  中国科学院上海硅酸盐研究所
  无机材料学报
  OQMD数据库
近期文章
Machine learning hydrogen adsorption on nanoclusters through structural descriptors (基于结构描述符机器学习纳米团簇上的氢吸附)
发布时间:2018-08-13

Machine learning hydrogen adsorption on nanoclusters through structural descriptors (基于结构描述符机器学习纳米团簇上的氢吸附)
Marc O. J. J?gerEiaki V. MorookaFilippo Federici CanovaLauri Himanen&Adam S. Foster
npj Computational Materials 4:37 (2018)
doi:s41524-018-0096-5
Published online:19 july 2018
Abstract| Full Text | PDF OPEN

摘要:纳米团簇析氢反应的催化活性取决于氢吸附位点的结构。借助于描述符(descriptor),机器学习可以降低模拟这些吸附位点的工作量。我们分析了目前最先进的结构描述符,即原子位置平滑重叠、多体张量表象和原子中心对称函数等用于机器学习预测纳米团簇表面的氢吸附(自由)能的可靠性。以二维材料二硫化钼和铜-金合金团簇作为测试体系,扫描了纳米团簇表面的氢吸附的势能面,用于比较不同描述符在核岭回归下准确性。基于包含91个二硫化钼纳米团簇和24个铜-金合金纳米团簇数据集的研究,我们发现同时对所有团簇而不是分开针对每一种团簇来开展机器学习,可以降低预测的平均绝对误差。采用局域描述符原子位置平滑重叠可以解释吸附能的计算结果,而与全局描述符多体张量表象相结合并没有提高整体精度。我们认为,将不同纳米团簇的数据合并,可以显著减少势能面拟合的工作量   

Abstract:Catalytic activity of the hydrogen evolution reaction on nanoclusters depends on diverse adsorption site structures.Machine learning reduces the cost for modelling those sites with the aid of descriptors. We analysed the performance of state-of-the-art structural descriptors Smooth Overlap of Atomic Positions, Many-Body Tensor Representation and Atom-Centered Symmetry Functions while predicting the hydrogen adsorption (free) energy on the surface of nanoclusters. The 2D-material molybdenum disulphide and the alloy copper–gold functioned as test systems. Potential energy scans of hydrogen on the cluster surfaces were conducted to compare the accuracy of the descriptors in kernel ridge regression. By having recourse to data sets of 91 molybdenum disulphide clusters and 24 copper–gold clusters, we found that the mean absolute error could be reduced by machine learning on different clusters simultaneously rather than separately. The adsorption energy was explained by the local descriptor Smooth Overlap of Atomic Positions, combining it with the global descriptor Many-Body Tensor Representation did not improve the overall accuracy. We concluded that fitting of potential energy surfaces could be reduced significantly by merging data from different nanoclusters. 

Editorial Summary

Machine learning: hydrogen adsorption energy on nanocluster surfaces (机器学习:纳米团簇表面的氢吸附能) 

本研究分析了用于机器学习纳米系统催化析氢反应的描述符的准确性和效率。由芬兰阿尔托大学Adam Foster领导的团队分析了3种结构描述符,即原子位置平滑重叠(SOAP)、多体张量表示(MBTR)和原子中心对称函数(ACSF)用于研究与催化应用相关的纳米团簇表面氢吸附自由能的可靠性。这些描述符之前被设计用于描述分子和晶体,其在团簇体系中的可用性目前尚不清楚。应用原子级厚度的MoS2和AuxCuy合金团簇作为测试系统,本研究评估了这些描述符用于核岭回归的准确性。通过对91个MoS 2纳米团簇和24个AuxCuy纳米团簇组成的数据集的分析表明,SOAP相比其他描述符具有显著优越的预测性能,可以作为吸附能预测的候选工具。

The accuracy and efficiency of descriptors for machine learning are tested for hydrogen evolution reaction in nanocatalytic systems. A team led by Adam Foster at Aalto University analysed the performance of SOAP, MBTR and ACSF structural descriptors used to gain insight to the free energy of hydrogen adsorption on the surface of nanoclusters relevant to catalysis applications. Using atomically thin MoS2 and AuxCuy metallic alloys as test systems, the accuracy of the predictors was evaluated when used as features in kernel ridge regression. Analysis on a dataset of 91 MoS2 clusters and 24 AuxCuy clusters (x?+?y?=?13) indicated that while none of the descriptors which had been designed for molecules and crystals was optimized for nanoclusters, SOAP performed significantly better, making it a more suitable candidate for adsorption energy prediction.

 
【打印本页】【关闭本页】
版权所有 © 中国科学院上海硅酸盐研究所  沪ICP备05005480号-1    沪公网安备 31010502006565号
地址:上海市长宁区定西路1295号 邮政编码:200050