BIGDML：实现材料的精确机器学习力场
BIGDML: Towards Exact Machine Learning Force Fields for Materials
摘要：
机器学习力场（MLFF）应该是准确的，计算和数据有效的，并适用于分子，材料及其界面。目前，MLFF通常会引入权衡，将其实际适用性限制在化学空间的小子集或需要详尽的数据集进行训练。在这里，我们介绍了Bravais启发的连续域机器学习（BIGDML）方法，并展示了它使用仅10-200个几何形状的训练集构建可靠力场的能力，这些几何形状适用于包括原始和含缺陷的2D和3D半导体和金属以及表面上化学吸附和物理吸附的原子和分子吸附物的材料。BIGDML模型采用了给定材料的完整相关对称群，不假设人工原子类型或原子相互作用的局部化，并且对于扩展的材料集表现出高数据效率和最先进的能量精度（误差大大低于1 meV/原子）。广泛的路径积分分子动力学与BIGDML模型进行演示的违反直觉的本地化的苯-石墨烯动力学引起的核量子效应，并允许合理化的Arrhenius行为的氢扩散系数在Pd晶体在很宽的温度范围内。
英文摘要：
Machine-learning force fields (MLFF) should be accurate, computationally and data efficient, and applicable to molecules, materials, and interfaces thereof. Currently, MLFFs often introduce tradeoffs that restrict their practical applicability to small subsets of chemical space or require exhaustive datasets for training. Here, we introduce the Bravais-Inspired Gradient-Domain Machine Learning (BIGDML) approach and demonstrate its ability to construct reliable force fields using a training set with just 10-200 geometries for materials including pristine and defect-containing 2D and 3D semiconductors and metals, as well as chemisorbed and physisorbed atomic and molecular adsorbates on surfaces. The BIGDML model employs the full relevant symmetry group for a given material, does not assume artificial atom types or localization of atomic interactions and exhibits high data efficiency and state-of-the-art energy accuracies (errors substantially below 1 meV per atom) for an extended set of materials. Extensive path-integral molecular dynamics carried out with BIGDML models demonstrate the counterintuitive localization of benzene--graphene dynamics induced by nuclear quantum effects and allow to rationalize the Arrhenius behavior of hydrogen diffusion coefficient in a Pd crystal for a wide range of temperatures.
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。
