Li Zhenwei, Kermode James R, De Vita Alessandro
King's College London, Physics Department, Strand, London WC2R 2LS, United Kingdom.
Warwick Centre for Predictive Modelling, School of Engineering, University of Warwick, Coventry CV4 7AL, United Kingdom.
Phys Rev Lett. 2015 Mar 6;114(9):096405. doi: 10.1103/PhysRevLett.114.096405.
We present a molecular dynamics scheme which combines first-principles and machine-learning (ML) techniques in a single information-efficient approach. Forces on atoms are either predicted by Bayesian inference or, if necessary, computed by on-the-fly quantum-mechanical (QM) calculations and added to a growing ML database, whose completeness is, thus, never required. As a result, the scheme is accurate and general, while progressively fewer QM calls are needed when a new chemical process is encountered for the second and subsequent times, as demonstrated by tests on crystalline and molten silicon.
我们提出了一种分子动力学方案，该方案以一种信息高效的单一方法将第一性原理和机器学习（ML）技术结合起来。原子上的力要么通过贝叶斯推理预测，要么在必要时通过即时量子力学（QM）计算得出，并添加到一个不断增长的ML数据库中，因此，该数据库的完整性并非必需。结果，该方案既准确又通用，而且如对晶体硅和熔融硅的测试所示，当第二次及后续遇到新的化学过程时，所需的QM调用会越来越少。
