arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1910.12752cond-mat.softcs.LGphysics.chem-ph
收藏

基于方程学习网络的解析经典密度泛函

Analytical classical density functionals from an equation learning network

Eberhard Karls Universität Tübingen(埃伯哈德·卡尔斯·图宾根大学(图宾根大学));Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所)

Shang-Chun Lin, Georg Martius, Martin Oettel

摘要:

我们探讨了使用机器学习方法获得两种模型流体,硬棒和Lennard-Jones,在一维的经典自由能泛函的解析形式的可行性。对文献[1]中提出的方程学习网络进行了适当的修改,以构造自由能量密度,自由能量密度是一组加权密度的函数,并且由少量具有灵活组合规则的基函数构成。与之前的工作2相比,这种设置大大扩大了机器学习优化中使用的函数空间,其中函数被限制为简单的多项式形式。结果,我们找到了精确硬棒泛函及其直接关联函数的一个很好的近似。对于Lennard-Jones流体,我们让网络学习(i)完全过剩自由能泛函和(ii)与粒子间吸引力相关的过剩自由能泛函。这两个泛函显示出良好的协议与模拟的密度分布的热力学参数的内部和外部的训练区域。

英文摘要:

We explore the feasibility of using machine learning methods to obtain an analytic form of the classical free energy functional for two model fluids, hard rods and Lennard--Jones, in one dimension . The Equation Learning Network proposed in Ref. 1 is suitably modified to construct free energy densities which are functions of a set of weighted densities and which are built from a small number of basis functions with flexible combination rules. This setup considerably enlarges the functional space used in the machine learning optimization as compared to previous work 2 where the functional is limited to a simple polynomial form. As a result, we find a good approximation for the exact hard rod functional and its direct correlation function. For the Lennard--Jones fluid, we let the network learn (i) the full excess free energy functional and (ii) the excess free energy functional related to interparticle attractions. Both functionals show a good agreement with simulated density profiles for thermodynamic parameters inside and outside the training region.

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。

↑