arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.02723physics.chem-phphysics.comp-ph
收藏

深度神经网络计算大量有机分子的电子密度和能量比密度泛函理论(DFT)更快

Deep Neural Network Computes Electron Densities and Energies of a Large Set of Organic Molecules Faster than Density Functional Theory (DFT)

Anton V. Sinitskiy, Vijay S. Pande

摘要:

密度泛函理论(DFT)是量子化学中的主要方法之一,它在量子化学计算的成本和精度之间提供了一个有吸引力的折衷。电子密度在密度泛函理论中起着关键作用。在这项工作中,我们将探索机器学习-更具体地说,深度神经网络(DNN)-是否可以被训练成比DFT更快地预测电子密度。首先,我们选择了一个DFT泛函和基组(PBE 0/pcS-3)的实际有效组合,并使用它来生成一个数据库的DFT解决方案超过133,000有机分子从以前公布的数据库QM 9。接下来,我们训练DNN来预测这些分子的电子密度和能量。DNN的唯一输入是在小基组(HF/cc-VDZ)中使用廉价的量子化学方法计算的近似电子密度。我们证明了DNN成功地学习了HF计算中电子相关性和小基组伪影所产生的电子密度差异。密度差异的所有定性特征,包括孤对上的局部最小值,核上的局部最大值,C-H和C-C键周围的环形形状,芳香环和环丙烷环以及CN基团周围的复杂形状等,都被DNN捕获。DNN的能量预测精度为~ 1 kcal/mol,与文献中报道的其他模型相当,但这些模型不能预测电子密度。使用DNN的计算,包括HF计算,比DFT计算花费的时间少得多(对于当前版本中的大多数QM 9分子,大约是20-30倍,并且很清楚如何进一步改进)。

英文摘要:

Density functional theory (DFT) is one of the main methods in Quantum Chemistry that offers an attractive trade off between the cost and accuracy of quantum chemical computations. The electron density plays a key role in DFT. In this work, we explore whether machine learning - more specifically, deep neural networks (DNNs) - can be trained to predict electron densities faster than DFT. First, we choose a practically efficient combination of a DFT functional and a basis set (PBE0/pcS-3) and use it to generate a database of DFT solutions for more than 133,000 organic molecules from a previously published database QM9. Next, we train a DNN to predict electron densities and energies of such molecules. The only input to the DNN is an approximate electron density computed with a cheap quantum chemical method in a small basis set (HF/cc-VDZ). We demonstrate that the DNN successfully learns differences in the electron densities arising both from electron correlation and small basis set artifacts in the HF computations. All qualitative features in density differences, including local minima on lone pairs, local maxima on nuclei, toroidal shapes around C-H and C-C bonds, complex shapes around aromatic and cyclopropane rings and CN group, etc. are captured by the DNN. Accuracy of energy predictions by the DNN is ~ 1 kcal/mol, on par with other models reported in the literature, while those models do not predict the electron density. Computations with the DNN, including HF computations, take much less time that DFT computations (by a factor of ~20-30 for most QM9 molecules in the current version, and it is clear how it could be further improved).

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。

↑