Using principal component analysis for neural network high-dimensional potential energy surface
Using principal component analysis for neural network high-dimensional potential energy surface
复制标题
DOI：
10.1063/5.0009264
复制
发表时间：
2020-06-21
影响因子：
4.4
通讯作者：
Sisourat, Nicolas
中科院分区：
文献类型：
--
作者：
Casier, Bastien;Carniato, Stephane;Sisourat, Nicolas
势能面（PES）在我们理解化学反应中起着核心作用。尽管有效的电子结构方法和代码的发展令人印象深刻，这样的计算仍然是一个困难的任务，为大多数相关系统。在这种情况下，人工神经网络（NN）是有前途的候选人，构建PES的范围广泛的系统。然而，选择合适的分子描述符仍然是这些算法的瓶颈。在这项工作中，我们表明，主成分分析（PCA）是一个强大的工具，准备一组最佳的描述符，并建立一个有效的NN：该协议导致大幅改善的NN在学习和预测PES。此外，PCA提供了减小输入空间的大小的手段（即，描述符的数量）而不损失准确性。作为一个例子，我们应用这种新的方法来计算的高维PES描述酮-烯醇互变异构反应发生在丙酮分子。
Potential energy surfaces (PESs) play a central role in our understanding of chemical reactions. Despite the impressive development of efficient electronic structure methods and codes, such computations still remain a difficult task for the majority of relevant systems. In this context, artificial neural networks (NNs) are promising candidates to construct the PES for a wide range of systems. However, the choice of suitable molecular descriptors remains a bottleneck for these algorithms. In this work, we show that a principal component analysis (PCA) is a powerful tool to prepare an optimal set of descriptors and to build an efficient NN: this protocol leads to a substantial improvement of the NNs in learning and predicting a PES. Furthermore, the PCA provides a means to reduce the size of the input space (i.e., number of descriptors) without losing accuracy. As an example, we applied this novel approach to the computation of the high-dimensional PES describing the keto-enol tautomerism reaction occurring in the acetone molecule.