arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2210.07930physics.chem-phcond-mat.mtrl-scics.LG
收藏

纳米金刚石的机器学习前沿轨道能

Machine learning frontier orbital energies of nanodiamonds

Helmholtz-Zentrum Berlin für Materialien und Energie GmbH(亥姆霍兹柏林材料与能源研究中心);Freie Universität Berlin(柏林自由大学);Albert-Ludwigs-Universität Freiburg(阿尔伯特-路德维希-弗莱堡大学);Microsoft Research AI4Science(微软研究院AI4Science);Rice University(莱斯大学)

Thorren Kirschbaum, Börries von Seggern, Joachim Dzubiella, Annika Bande, Frank Noé

AI总结:

引入含5,089个结构的ND5k数据集,通过DFTB和DFT计算前沿轨道能,发现等变图神经网络PaiNN在插值与外推预测任务中表现最佳。

摘要:

纳米金刚石具有广泛的应用,包括催化、传感、摩擦学和生物医学。为了通过机器学习促进纳米金刚石设计,我们引入了新数据集ND5k,包含5,089个金刚烷和纳米金刚石结构及其前沿轨道能。ND5k结构通过紧束缚密度泛函理论(DFTB)优化,其前沿轨道能使用带PBE0泛函的密度泛函理论(DFT)计算。我们还比较了近期机器学习模型在预测与训练结构相似的前沿轨道能方面的表现(在ND5k上的插值),并测试了它们将预测外推至更大结构的能力。在插值和外推任务中,我们发现使用等变图神经网络PaiNN的效果最佳。第二好的结果由使用本文提出的定制原子描述符集的消息传递神经网络实现。

英文摘要:

Nanodiamonds have a wide range of applications including catalysis, sensing, tribology and biomedicine. To leverage nanodiamond design via machine learning, we introduce the new dataset ND5k, consisting of 5,089 diamondoid and nanodiamond structures and their frontier orbital energies. ND5k structures are optimized via tight-binding density functional theory (DFTB) and their frontier orbital energies are computed using density functional theory (DFT) with the PBE0 hybrid functional. We also compare recent machine learning models for predicting frontier orbital energies for similar structures as they have been trained on (interpolation on ND5k), and we test their abilities to extrapolate predictions to larger structures. For both the interpolation and extrapolation task, we find best performance using the equivariant graph neural network PaiNN. The second best results are achieved with a message passing neural network using a tailored set of atomic descriptors proposed here.

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。

↑