arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1901.05417physics.chem-phcs.ETphysics.comp-ph
收藏

在虚拟现实中使用交互式量子化学训练神经网络学习反应性势能面

Training neural nets to learn reactive potential energy surfaces using interactive quantum chemistry in virtual reality

Silvia Amabilino, Lars A. Bratholm, Simon J. Bennie, Alain C. Vaucher, Markus Reiher, David R. Glowacki

摘要:

虽然许多计算工作流的主要瓶颈在不久前还受到处理能力的限制,但机器学习技术的兴起导致了范式转变,这使得与数据策展相关的问题越来越重要-即,数据大小、质量、偏差、格式和覆盖范围。越来越多的数据相关问题与用于处理和学习数据的算法方法同样重要。在这里,我们介绍了一个开源的GPU加速神经网络(NN)框架学习反应势能面(PES),并研究使用实时交互式从头计算分子动力学在虚拟现实(iMD-VR)作为一种新的策略,快速采样的几何形状沿反应路径,可用于训练神经网络学习反应PES。专注于CN自由基与异戊烷的夺氢反应,我们比较了使用iMD-VR数据训练的NN与使用更传统的方法训练的NN的性能,即分子动力学(MD)被约束为沿着夺氢反应坐标对预定义的点网格进行采样。使用iMD-VR数据训练的NN和使用受约束MD数据训练的NN都再现了反应性PES的重要定性特征,例如抽象的低和早期障碍。量化,学习对训练数据集敏感。我们的研究结果表明,使用量子化学iMD-VR机器获得的用户采样结构能够在最小能量路径(MEP)附近进行更好的采样。因此,在iMD-VR数据上训练的NN很好地预测了MEP附近的能量,但对“偏离路径”结构的能量预测得不太好。在约束MD数据上训练的NN在预测“偏离路径”结构的能量方面做得更好,因为它在其训练集中包括许多这样的结构。

英文摘要:

Whilst the primary bottleneck to a number of computational workflows was not so long ago limited by processing power, the rise of machine learning technologies has resulted in a paradigm shift which places increasing value on issues related to data curation - i.e., data size, quality, bias, format, and coverage. Increasingly, data-related issues are equally as important as the algorithmic methods used to process and learn from the data. Here we introduce an open source GPU-accelerated neural network (NN) framework for learning reactive potential energy surfaces (PESs), and investigate the use of real-time interactive ab initio molecular dynamics in virtual reality (iMD-VR) as a new strategy for rapidly sampling geometries along reaction pathways which can be used to train NNs to learn reactive PESs. Focussing on hydrogen abstraction reactions of CN radical with isopentane, we compare the performance of NNs trained using iMD-VR data versus NNs trained using a more traditional method, namely molecular dynamics (MD) constrained to sample a predefined grid of points along hydrogen abstraction reaction coordinates. Both the NN trained using iMD-VR data and the NN trained using the constrained MD data reproduce important qualitative features of the reactive PESs, such as a low and early barrier to abstraction. Quantitatively, learning is sensitive to the training dataset. Our results show that user-sampled structures obtained with the quantum chemical iMD-VR machinery enable better sampling in the vicinity of the minimum energy path (MEP). As a result, the NN trained on the iMD-VR data does very well predicting energies in the vicinity of the MEP, but less well predicting energies for 'off-path' structures. The NN trained on the constrained MD data does better in predicting energies for 'off-path' structures, given that it included a number of such structures in its training set.

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。

↑