Convergence acceleration in machine learning potentials for atomistic simulations
Convergence acceleration in machine learning potentials for atomistic simulations
复制标题
DOI：
10.1039/d1dd00005e
复制
发表时间：
2022-02-14
期刊：
影响因子：
--
通讯作者：
Saidi, Wissam A.
中科院分区：
文献类型：
--
作者：
Bayerl, Dylan;Andolina, Christopher M.;Saidi, Wissam A.
用于原子模拟的机器学习势（MLP）对材料建模具有巨大的前瞻性影响，提供了比密度泛函理论（DFT）计算快几个数量级的速度，而不会明显牺牲材料特性预测的准确性。然而，生成训练MLP所需的大型数据集是令人生畏的。在这里，我们表明，基于MLP的材料属性预测收敛速度更快的精度布里渊区积分比基于DFT的属性预测。我们证明，这种现象是强大的不同金属系统的材料性能。此外，我们还提供了统计误差度量，以准确地确定MLP的DFT训练数据集所需的先验精度水平，以确保材料性能预测的加速收敛，从而显着降低MLP开发的计算费用。用于原子模拟的机器学习潜力（MLP）对材料建模具有巨大的潜在影响，在不明显牺牲材料性能预测准确性的情况下，提供了比密度泛函理论模拟高几个数量级的加速。
Machine learning potentials (MLPs) for atomistic simulations have an enormous prospective impact on materials modeling, offering orders of magnitude speedup over density functional theory (DFT) calculations without appreciably sacrificing accuracy in the prediction of material properties. However, the generation of large datasets needed for training MLPs is daunting. Herein, we show that MLP-based material property predictions converge faster with respect to precision for Brillouin zone integrations than DFT-based property predictions. We demonstrate that this phenomenon is robust across material properties for different metallic systems. Further, we provide statistical error metrics to accurately determine a priori the precision level required of DFT training datasets for MLPs to ensure accelerated convergence of material property predictions, thus significantly reducing the computational expense of MLP development.Machine learning potentials (MLPs) for atomistic simulations have an enormous prospective impact on materials modeling, offering orders of magnitude speedup over density functional theory simulations without appreciably sacrificing accuracy of material property prediction.