通过Taylor展开包含原子力的ANN势的有效训练及其在水和过渡金属氧化物中的应用
Efficient Training of ANN Potentials by Including Atomic Forces via Taylor Expansion and Application to Water and a Transition-Metal Oxide
摘要：
人工神经网络（ANN）的潜力，使有效的大规模复杂材料的原子模型与第一原理的精度。对于分子动力学模拟，准确的能量和原子间力是先决条件，但同时训练ANN势能对来自电子结构计算的能量和力的计算要求很高。在这里，我们介绍了一种有效的替代方法，用于训练的ANN潜力的能量和力的信息的基础上外推的总能量通过泰勒展开。通过将力信息转换为近似能量，可以避免传统力训练方法所表现出的与原子数量的二次缩放，这使得能够在包含复杂原子结构的参考数据集上进行训练。我们证明了不同的材料系统，集群的水分子，散装液态水，和锂过渡金属氧化物，所提出的部队训练方法提供了实质性的改进方案，训练的能量。包括用于训练的力信息减小了ANN势构造所需的参考数据集的大小，增加了势的可转移性，并且总体上提高了力预测精度。对于一组水簇，泰勒展开方法与对所有力分量的显式训练相比，以小得多的计算成本实现了约50%的力误差改进。因此，替代力训练方法简化了一般人工神经网络潜力的预测准确的能量和不同类型的材料的原子间的力量，如这里所示的水和过渡金属氧化物。
英文摘要：
Artificial neural network (ANN) potentials enable the efficient large-scale atomistic modeling of complex materials with near first-principles accuracy. For molecular dynamics simulations, accurate energies and interatomic forces are a prerequisite, but training ANN potentials simultaneously on energies and forces from electronic structure calculations is computationally demanding. Here, we introduce an efficient alternative method for the training of ANN potentials on energy and force information based on an extrapolation of the total energy via a Taylor expansion. By translating the force information to approximate energies, the quadratic scaling with the number of atoms exhibited by conventional force-training methods can be avoided, which enables the training on reference data sets containing complex atomic structures. We demonstrate for different materials systems, clusters of water molecules, bulk liquid water, and a lithium transition-metal oxide, that the proposed force-training approach provides substantial improvements over schemes that train on energies only. Including force information for training reduces the size of the reference data sets required for ANN potential construction, increases the transferability of the potential, and generally improves the force prediction accuracy. For a set of water clusters, the Taylor-expansion approach achieves around 50% of the force error improvement compared to the explicit training on all force components, at a much smaller computational cost. The alternative force training approach thus simplifies the construction of general ANN potentials for the prediction of accurate energies and interatomic forces for diverse types of materials, as demonstrated here for water and a transition-metal oxide.
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。
