Finding predictive models for singlet fission by machine learning
Finding predictive models for singlet fission by machine learning
复制标题
DOI：
10.1038/s41524-022-00758-y
复制
发表时间：
2022-04
影响因子：
9.7
通讯作者：
Xingyu Liu;Xiaopeng Wang;Siyu Gao;Vincent Chang;Rithwik Tom;Maituo Yu;L. Ghiringhelli;N. Marom
中科院分区：
文献类型：
--
作者：
Xingyu Liu;Xiaopeng Wang;Siyu Gao;Vincent Chang;Rithwik Tom;Maituo Yu;L. Ghiringhelli;N. Marom
单态裂变是将一个单态激子转变为两个三态激子，可以显著提高太阳能电池的效率。经历SF的分子晶体很少。计算探索可能会加速SF材料的发现。然而，分子晶体激子性质的多体微扰理论(MBPT)计算在大规模材料筛选中是不现实的。我们使用sure-independence-screening-and-sparsifying-operator(SISSO)机器学习算法来生成计算高效的模型，该模型可以在101个多环芳烃(PAH101)的数据集上预测SF的MBPT热力学驱动力。SISSO通过迭代组合物理主要特征来生成模型。采用线性回归与交叉验证相结合的方法选择最优模型。该模型成功地预测了SF驱动力，误差小于0.2 eV。基于SISSO模型的成本、精度和分类性能，我们提出了一种层次化的材料筛选工作流程。在PAH101集合中发现了三个潜在的SF候选者。
Singlet fission (SF), the conversion of one singlet exciton into two triplet excitons, could significantly enhance solar cell efficiency. Molecular crystals that undergo SF are scarce. Computational exploration may accelerate the discovery of SF materials. However, many-body perturbation theory (MBPT) calculations of the excitonic properties of molecular crystals are impractical for large-scale materials screening. We use the sure-independence-screening-and-sparsifying-operator (SISSO) machine-learning algorithm to generate computationally efficient models that can predict the MBPT thermodynamic driving force for SF for a dataset of 101 polycyclic aromatic hydrocarbons (PAH101). SISSO generates models by iteratively combining physical primary features. The best models are selected by linear regression with cross-validation. The SISSO models successfully predict the SF driving force with errors below 0.2 eV. Based on the cost, accuracy, and classification performance of SISSO models, we propose a hierarchical materials screening workflow. Three potential SF candidates are found in the PAH101 set.