Accelerating Fourth-Generation Machine Learning Potentials Using Quasi-Linear Scaling Particle Mesh Charge Equilibration,Journal of Chemical Theory and Computation

当前位置： X-MOL 学术 › J. Chem. Theory Comput. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Accelerating Fourth-Generation Machine Learning Potentials Using Quasi-Linear Scaling Particle Mesh Charge Equilibration
Journal of Chemical Theory and Computation ( IF 5.7 ) Pub Date : 2024-08-16 , DOI: 10.1021/acs.jctc.4c00334
Moritz Gubler ₁ , Jonas A Finkler ₁ , Moritz R Schäfer _{2,

3} , Jörg Behler _{2,

3} , Stefan Goedecker ₁

Affiliation

Machine learning potentials (MLPs) have revolutionized the field of atomistic simulations by describing atomic interactions with the accuracy of electronic structure methods at a small fraction of the cost. Most current MLPs construct the energy of a system as a sum of atomic energies, which depend on information about the atomic environments provided in the form of predefined or learnable feature vectors. If, in addition, nonlocal phenomena like long-range charge transfer are important, fourth-generation MLPs need to be used, which include a charge equilibration (Qeq) step to take the global structure of the system into account. This Qeq can significantly increase the computational cost and thus can become a computational bottleneck for large systems. In this Article, we present a highly efficient formulation of Qeq that does not require the explicit computation of the Coulomb matrix elements, resulting in a quasi-linear scaling method. Moreover, our approach also allows for the efficient calculation of energy derivatives, which explicitly consider the global structure-dependence of the atomic charges as obtained from Qeq. Due to its generality, the method is not restricted to MLPs and can also be applied within a variety of other force fields.

中文翻译：

使用准线性缩放粒子网格电荷平衡加速第四代机器学习潜力

机器学习势 (MLP) 通过以电子结构方法的准确性描述原子相互作用，而成本只占一小部分，从而彻底改变了原子模拟领域。目前大多数 MLP 将系统的能量构建为原子能量的总和，这取决于以预定义或可学习特征向量的形式提供的原子环境信息。此外，如果长程电荷转移等非局域现象很重要，则需要使用第四代 MLP，其中包括电荷平衡 (Qeq) 步骤，以考虑系统的全局结构。该 Qeq 会显着增加计算成本，因此可能成为大型系统的计算瓶颈。在本文中，我们提出了一种高效的 Qeq 公式，不需要显式计算库仑矩阵元素，从而产生了准线性标度方法。此外，我们的方法还允许有效计算能量导数，它明确考虑从 Qeq 获得的原子电荷的全局结构依赖性。由于其通用性，该方法不仅限于 MLP，还可以应用于各种其他力场。

更新日期：2024-08-16

点击分享查看原文

点击收藏

公开下载

阅读更多本刊新发论文本刊介绍/投稿指南