arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1504.01966physics.chem-ph
收藏

TDDFT电子光谱与化学空间机器学习

Electronic Spectra from TDDFT and Machine Learning in Chemical Space

Raghunathan Ramakrishnan, Mia Hartmann, Enrico Tapavicza, O. Anatole von Lilienfeld

摘要:

时间依赖密度泛函理论(DFT)由于其良好的计算效率,使得能够以高通量的方式跨化学空间预测电子光谱。然而,它的预测可能相当不准确。我们用机器学习模型解决了这个问题,该模型是在参考二阶近似耦合簇单和双(CC 2)谱与TDDFT对应谱,甚至与DFT间隙的偏差上训练的。我们将这种方法应用于超过2万个具有多达8个CONF原子的合成可行的小有机分子的低位单重-单重垂直电子光谱。预测误差作为训练集大小的函数单调衰减。对于1万个分子的训练集,对于其余分子,CC 2激发能可以再现到$\pm$ 0.1 eV内。通过发色团计数分析我们的光谱数据库表明,可以实现更高的精度。基于收集到的证据,我们讨论了与高位光谱和跃迁强度的数据驱动建模相关的开放性挑战。

英文摘要:

Due to its favorable computational efficiency time-dependent (TD) density functional theory (DFT) enables the prediction of electronic spectra in a high-throughput manner across chemical space. Its predictions, however, can be quite inaccurate. We resolve this issue with machine learning models trained on deviations of reference second-order approximate coupled-cluster singles and doubles (CC2) spectra from TDDFT counterparts, or even from DFT gap. We applied this approach to low-lying singlet-singlet vertical electronic spectra of over 20 thousand synthetically feasible small organic molecules with up to eight CONF atoms. The prediction errors decay monotonously as a function of training set size. For a training set of 10 thousand molecules, CC2 excitation energies can be reproduced to within $\pm$0.1 eV for the remaining molecules. Analysis of our spectral database via chromophore counting suggests that even higher accuracies can be achieved. Based on the evidence collected, we discuss open challenges associated with data-driven modeling of high-lying spectra, and transition intensities.

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。

↑