Singraber Andreas, Morawietz Tobias, Behler Jörg, Dellago Christoph
Faculty of Physics , University of Vienna , Boltzmanngasse 5 , Vienna , Austria.
Department of Chemistry , Stanford University , Stanford , California 94305 , United States.
J Chem Theory Comput. 2019 May 14;15(5):3075-3092. doi: 10.1021/acs.jctc.8b01092. Epub 2019 Apr 29.
Over the past years high-dimensional neural network potentials (HDNNPs), fitted to accurately reproduce ab initio potential energy surfaces, have become a powerful tool in chemistry, physics and materials science. Here, we focus on the training of the neural networks that lies at the heart of the HDNNP method. We present an efficient approach for optimizing the weight parameters of the neural network via multistream Kalman filtering, using potential energies and forces as reference data. In this procedure, the choice of the free parameters of the Kalman filter can have a significant impact on the fit quality. Carrying out a large parameter study, we determine optimal settings and demonstrate how to optimize training results of HDNNPs. Moreover, we illustrate our HDNNP training approach by revisiting previously presented fits for water and developing a new potential for copper sulfide. This material, accessible in computer simulations so far only via first-principles methods, forms a particularly complex solid structure at low temperatures and undergoes a phase transition to a superionic state upon heating. Analyzing MD simulations carried out with the CuS HDNNP, we confirm that the underlying ab initio reference method indeed reproduces this behavior.
在过去几年中，为精确再现从头算势能面而拟合的高维神经网络势（HDNNP）已成为化学、物理和材料科学领域的强大工具。在此，我们聚焦于HDNNP方法核心的神经网络训练。我们提出一种通过多流卡尔曼滤波优化神经网络权重参数的有效方法，使用势能和力作为参考数据。在此过程中，卡尔曼滤波器自由参数的选择会对拟合质量产生重大影响。通过进行大量参数研究，我们确定了最佳设置，并展示了如何优化HDNNP的训练结果。此外，我们通过重新审视之前给出的水的拟合以及开发一种新的硫化铜势能来阐述我们的HDNNP训练方法。这种材料到目前为止在计算机模拟中只能通过第一性原理方法获得，在低温下形成特别复杂的固体结构，并在加热时经历向超离子态的相变。通过分析使用CuS HDNNP进行的分子动力学模拟，我们证实基础的从头算参考方法确实再现了这种行为。
