arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.13844cond-mat.mtrl-scicond-mat.dis-nn
收藏

通过端到端可微原子模拟进行力场优化

Force field optimization by end-to-end differentiable atomistic simulation

Abhijeet S. Gangan, Samuel S. Schoenholz, Ekin Dogus Cubuk, Mathieu Bauchy, N. M. Anoop Krishnan

AI总结:

提出基于自动微分的端到端可微原子模拟框架,通过解析计算梯度优化力场参数,能准确再现弹性、振动等复杂材料性质并提升泛化能力。

摘要:

原子模拟的准确性取决于力场的精度。传统数值方法通常难以优化经验力场参数以再现目标性质。近期方法依赖基于第一性原理模拟的力和能量来训练这些力场。然而,这些方法能否捕捉复杂的材料响应(如振动或弹性质)尚不明确。为此,我们引入一个框架,采用内环模拟和外环优化,利用自动微分通过解析计算模拟梯度来进行性质预测和力场优化。我们通过优化硅体系的经典Stillinger-Weber和EDIP势以再现弹性常数、振动态密度和声子色散来验证该方法。我们还展示了如何使用自动微分微调机器学习势以再现任意目标性质(如径向分布函数)。有趣的是,所得力场比在能量和力上微调的力场表现出更高的精度和对未见温度的泛化能力。最后,我们展示了该方法扩展至多目标性质力场优化。总体而言,可微模拟通过解析计算梯度,为理解物理系统和材料的理论探索与实际应用提供了强大工具。

英文摘要:

The accuracy of atomistic simulations depends on the precision of force fields. Traditional numerical methods often struggle to optimize the empirical force field parameters for reproducing target properties. Recent approaches rely on training these force fields based on forces and energies from first-principle simulations. However, it is unclear whether these approaches will enable capturing complex material responses such as vibrational, or elastic properties. To this extent, we introduce a framework, employing inner loop simulations and outer loop optimization, that exploits automatic differentiation for both property prediction and force-field optimization by computing gradients of the simulation analytically. We demonstrate the approach by optimizing classical Stillinger-Weber and EDIP potentials for silicon systems to reproduce the elastic constants, vibrational density of states, and phonon dispersion. We also demonstrate how a machine-learned potential can be fine-tuned using automatic differentiation to reproduce any target property such as radial distribution functions. Interestingly, the resulting force field exhibits improved accuracy and generalizability to unseen temperatures than those fine-tuned on energies and forces. Finally, we demonstrate the extension of the approach to optimize the force fields towards multiple target properties. Altogether, differentiable simulations, through the analytical computation of their gradients, offer a powerful tool for both theoretical exploration and practical applications toward understanding physical systems and materials.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑