LC-GAP: Localized Coulomb Descriptors for the Gaussian Approximation Potential

LC-GAP: Localized Coulomb Descriptors for the Gaussian Approximation Potential
复制标题

LC-GAP:高斯近似势的局域库仑描述符

DOI:
--
复制
发表时间:
2016
期刊:
Scientific Computing and Algorithms in Industrial Simulations
影响因子:
--
通讯作者:
Sonja Mathias
Sonja Mathias
中科院分区:
--
文献类型:
--
作者:
James Barker;J. Bulin;J. Hamaekers;Sonja Mathias

文献摘要

参考文献

被引文献

相似文献

我们介绍了一类新的局域化的原子环境表示的基础上的库仑矩阵。通过将这些函数与高斯近似势方法相结合,我们提出了LC-GAP,一种通过机器学习(ML)生成原子势的新系统。对QM 7、QM 7 b和GDB 9生物分子数据集的测试表明,LC-GAP产生的电势可以成功预测比用于训练化学准确性的分子更大的分子的原子化能量,并且(在QM 7 b的情况下)也可以用于预测一系列其他原子性质,其准确性与最近的文献一致。由于表现最好的表示在局部原子环境中的原子数量中仅具有线性维度,因此与类似的基于库仑矩阵的方法相比,这表示预测精度和计算成本都有所提高。
We introduce a novel class of localized atomic environment representations based upon the Coulomb matrix. By combining these functions with the Gaussian approximation potential approach, we present LC-GAP, a new system for generating atomic potentials through machine learning (ML). Tests on the QM7, QM7b and GDB9 biomolecular datasets demonstrate that potentials created with LC-GAP can successfully predict atomization energies for molecules larger than those used for training to chemical accuracy, and can (in the case of QM7b) also be used to predict a range of other atomic properties with accuracy in line with the recent literature. As the best-performing representation has only linear dimensionality in the number of atoms in a local atomic environment, this represents an improvement in both prediction accuracy and computational cost when compared to similar Coulomb matrix-based methods.
DOI: 10.1103/physrevb.87.184115
发表时间: 2013-05-28
期刊: PHYSICAL REVIEW B
影响因子: 3.7
作者:
Bartok, Albert P.;Kondor, Risi;Csanyi, Gabor
通讯作者: Csanyi, Gabor
DOI: 10.1021/acs.jpclett.5b00831
发表时间: 2015-06-18
影响因子: 5.7
作者:
Hansen, Katja;Biegler, Franziska;Ramakrishnan, Raghunathan;Pronobis, Wiktor;von Lilienfeld, O. Anatole;Mueller, Klaus-Robert;Tkatchenko, Alexandre
通讯作者: Tkatchenko, Alexandre
DOI: 10.1021/ct400195d
发表时间: 2013-08-01
影响因子: 5.5
作者:
Hansen, Katja;Montavon, Gregoire;Mueller, Klaus-Robert
通讯作者: Mueller, Klaus-Robert
DOI: 10.1103/physrevlett.104.136403
发表时间: 2010-04-02
影响因子: 8.6
作者:
Bartok, Albert P.;Payne, Mike C.;Csanyi, Gabor
通讯作者: Csanyi, Gabor