NewtonNet: a Newtonian message passing network for deep learning of interatomic potentials and forces.

NewtonNet: a Newtonian message passing network for deep learning of interatomic potentials and forces.
复制标题

DOI:
10.1039/d2dd00008c
复制
发表时间:
2022-06-13
期刊:
DIGITAL DISCOVERY
影响因子:
--
通讯作者:
Head-Gordon, Teresa
Head-Gordon, Teresa
中科院分区:
其他
文献类型:
--
作者:
Haghighatlari, Mojtaba;Li, Jie;Guan, Xingyi;Zhang, Oufan;Das, Akshaya;Stein, Christopher J.;Heidar-Zadeh, Farnaz;Liu, Meili;Head-Gordon, Martin;Bertels, Luke;Hao, Hongxia;Leven, Itai;Head-Gordon, Teresa

文献摘要

参考文献

被引文献

相似文献

我们报告了一个新的深度学习消息传递网络,它从牛顿运动方程中获得灵感来学习原子间的势和力。利用来自可训练力向量的方向信息和受牛顿物理学启发的物理注入算子的优势,整个模型保持旋转等变,并且通过更多可解释的物理特征来推断多体相互作用。我们测试了NewtonNet对几个反应性和非反应性的高质量从头算数据集的预测,包括单个小分子、大组化学多样性分子、甲烷和氢燃烧反应,在能量和力方面实现了最先进的测试性能,数据和计算效率远远高于其他深度学习模型。我们报告了一个新的深度学习消息传递网络,它从牛顿运动方程中获得灵感来学习原子间的势和力。
We report a new deep learning message passing network that takes inspiration from Newton's equations of motion to learn interatomic potentials and forces. With the advantage of directional information from trainable force vectors, and physics-infused operators that are inspired by Newtonian physics, the entire model remains rotationally equivariant, and many-body interactions are inferred by more interpretable physical features. We test NewtonNet on the prediction of several reactive and non-reactive high quality ab initio data sets including single small molecules, a large set of chemically diverse molecules, and methane and hydrogen combustion reactions, achieving state-of-the-art test performance on energies and forces with far greater data and computational efficiency than other deep learning models. We report a new deep learning message passing network that takes inspiration from Newton's equations of motion to learn interatomic potentials and forces.
DOI: 10.1063/1.5126701
发表时间: 2020-01-31
影响因子: 4.4
作者:
Christensen, Anders S.;Bratholm, Lars A.;von Lilienfeld, O. Anatole
通讯作者: von Lilienfeld, O. Anatole
DOI: 10.1002/kin.20026
发表时间: 2004-10-01
影响因子: 1.5
作者:
Li, J;Zhao, ZW;Dryer, FL
通讯作者: Dryer, FL
DOI: 10.1039/d1dd00008j
发表时间: 2022-04-11
期刊: DIGITAL DISCOVERY
影响因子: --
作者:
Bash, Daniil;Chenardy, Frederick Hubert;Hippalgaonkar, Kedar
通讯作者: Hippalgaonkar, Kedar
DOI: 10.1039/d1dd00018g
发表时间: 2022-04-11
期刊: DIGITAL DISCOVERY
影响因子: --
作者:
de Lomana, Marina Garcia;Svensson, Fredrik;Kirchmair, Johannes
通讯作者: Kirchmair, Johannes
DOI: 10.1016/j.cpc.2019.02.007
发表时间: 2019-07-01
影响因子: 6.3
作者:
Chmiela, Stefan;Sauceda, Huziel E.;Tkatchenko, Alexandre
通讯作者: Tkatchenko, Alexandre