Scholarlink

<p>Machine learning applications in the chemical sciences, especially when based on neural networks, critically depend on the availability of large quantities of high-quality data. As they provide excellent accuracy for both charged and neutral excitations, a large dataset containing quasiparticle self-consistent GW (qs<i>G</i><i>W</i>) and Bethe-Salpeter equation (BSE) data would be highly desirable to model excited state energies and properties. In this work, we introduce a dataset for qs<i>G</i><i>W</i>-BSE excitation energies and qs<i>G</i><i>W</i> quasiparticle energies of unprecedented size. Our dataset, denoted QM9GWBSE, supplies <i>G</i><i>W</i>-BSE singlet-singlet and singlet-triplet excitation energies, corresponding transition dipole moments and oscillator strengths as well as qs<i>G</i><i>W</i> quasiparticle energies for all molecules from the popular QM9 dataset. We anticipate that QM9GWBSE will provide a solid foundation to train highly accurate machine learning models for the prediction of molecular excited state properties.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

qsGW quasiparticle and GW-BSE excitation energies of 133,885 molecules

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月10日

查看全文
  • Dario Baum,
  • Arno Förster,
  • Lucas Visscher

摘要

Machine learning applications in the chemical sciences, especially when based on neural networks, critically depend on the availability of large quantities of high-quality data. As they provide excellent accuracy for both charged and neutral excitations, a large dataset containing quasiparticle self-consistent GW (qsGW) and Bethe-Salpeter equation (BSE) data would be highly desirable to model excited state energies and properties. In this work, we introduce a dataset for qsGW-BSE excitation energies and qsGW quasiparticle energies of unprecedented size. Our dataset, denoted QM9GWBSE, supplies GW-BSE singlet-singlet and singlet-triplet excitation energies, corresponding transition dipole moments and oscillator strengths as well as qsGW quasiparticle energies for all molecules from the popular QM9 dataset. We anticipate that QM9GWBSE will provide a solid foundation to train highly accurate machine learning models for the prediction of molecular excited state properties.