Machine learning prediction of accurate atomization energies of organic molecules from low-fidelity quantum chemical calculations
Machine learning prediction of accurate atomization energies of organic molecules from low-fidelity quantum chemical calculations
复制标题
DOI：
10.1557/mrc.2019.107
复制
发表时间：
2019-06
影响因子：
1.9
通讯作者：
Logan T. Ward;B. Blaiszik;Ian T. Foster;R. Assary;B. Narayanan;L. Curtiss
中科院分区：
文献类型：
--
作者：
Logan T. Ward;B. Blaiszik;Ian T. Foster;R. Assary;B. Narayanan;L. Curtiss
最近的研究说明了机器学习（ML）如何用于绕过分子建模的核心挑战：准确性和计算成本之间的权衡。在这里，我们评估了多种ML方法来预测有机分子的原子化能。我们得到的模型学习了低保真度B3 LYP和高精度G4 MP2原子化能量之间的差异，并预测G4 MP2原子化能量为0.005 eV（平均绝对误差）对于少于9个重原子的分子（训练集117，232个条目，测试集13，026个条目）和0.012eV，用于具有10至14个重原子的66个分子的小集合。我们的两个最佳模型具有不同的精度/速度权衡，能够有效预测大分子的G4 MP2能级能量，并可通过简单的Web界面获得。
Recent studies illustrate how machine learning (ML) can be used to bypass a core challenge of molecular modeling: the trade-off between accuracy and computational cost. Here, we assess multiple ML approaches for predicting the atomization energy of organic molecules. Our resulting models learn the difference between low-fidelity, B3LYP, and high-accuracy, G4MP2, atomization energies and predict the G4MP2 atomization energy to 0.005 eV (mean absolute error) for molecules with less than nine heavy atoms (training set of 117,232 entries, test set 13,026) and 0.012 eV for a small set of 66 molecules with between 10 and 14 heavy atoms. Our two best models, which have different accuracy/speed trade-offs, enable the efficient prediction of G4MP2-level energies for large molecules and are available through a simple web interface.