arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.17002physics.chem-ph
收藏

用机器学习的交换泛函解决带隙问题

Addressing the Band Gap Problem with a Machine-Learned Exchange Functional

Kyle Bystrom, Stefano Falletta, Boris Kozinsky

AI总结:

本研究基于高斯过程机器学习密度泛函并引入密度矩阵非局域特征,训练出精确交换能泛函,解决了DFT带隙低估问题,并能准确预测分子能隙与固体极化子形成能,具有良好的可转移性。

摘要:

带隙的系统低估是半局域密度泛函理论(DFT)中最根本的挑战之一。除了阻碍将DFT应用于预测电子特性外,带隙问题还与自相互作用和离域误差密切相关,这使得用DFT研究电荷转移机制变得困难。。在本研究中,我们提出了两项关键创新来解决带隙问题。首先,我们设计了一种基于高斯过程机器学习密度泛函的方法,以显式拟合单粒子能级。其次,我们引入了密度矩阵的新型非局域特征,这些特征具有足够的表示力以拟合这些单粒子能级。结合这些进展,我们训练了一种机器学习泛函用于精确交换能,该泛函能预测的分子能隙和多种分子的反应能与参考杂化DFT计算高度一致。此外,尽管仅在分子数据上训练,我们的模型仍能能合理预测固体中极化子的形成能,这展示了了其模型的可转移性和稳健性。我们的方法可直接推广到完整的交换相关泛函,,为预测分子和材料的电子特性设计新型最先进的泛函铺平了道路。

英文摘要:

The systematic underestimation of band gaps is one of the most fundamental challenges in semilocal density functional theory (DFT). In addition to hindering the application of DFT to predicting electronic properties, the band gap problem is intimately related to self-interaction and delocalization errors, which make the study of charge transfer mechanisms with DFT difficult. In this work, we present two key innovations to address the band gap problem. First, we design an approach for machine learning density functionals based on Gaussian processes to explicitly fit single-particle energy levels. Second, we introduce novel nonlocal features of the density matrix that are expressive enough to fit these single-particle levels. Combining these developments, we train a machine-learned functional for the exact exchange energy that predicts molecular energy gaps and reaction energies of a wide range of molecules in excellent agreement with reference hybrid DFT calculations. In addition, while being trained solely on molecular data, our model predicts reasonable formation energies of polarons in solids, showcasing its transferability and robustness. Our approach generalizes straightforwardly to full exchange-correlation functionals, thus paving the way to the design of novel state-of-the-art functionals for the prediction of electronic properties of molecules and materials.

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。

↑