期刊
JOURNAL OF PHYSICAL CHEMISTRY LETTERS
卷 12, 期 31, 页码 7423-7430出版社
AMER CHEMICAL SOC
DOI: 10.1021/acs.jpclett.1c01939
关键词
-
类别
资金
- National Key Research and Development Program of China [2018YFB0704400]
- Science and Technology Commission of Shanghai Municipality [18520723500]
By combining machine learning with the SHAP approach, a strategy was proposed to accelerate the discovery of potential HOIPs, revealing key guidelines for the formability of materials in the HOIP structure.
Predicting the formability of perovskite structure for hybrid organic-inorganic perovskites (HOIPs) is a prominent challenge in the search for the required materials from a huge search space. Here, we propose an interpretable strategy combining machine learning with a shapley additive explanations (SHAP) approach to accelerate the discovery of potential HOIPs. According to the prediction of the best classification model, top-198 nontoxic candidates with a probability of formability (P-f) of >0.99 are screened from 18560 virtual samples. The SHAP analysis reveals that the radius and lattice constant of the B site (r(B) and LCB) are positively related to formability, while the ionic radius of the A site (r(A)), the tolerant factor (t), and the first ionization energy of the B site (I-1B) have negative relations. The significant finding is that stricter ranges of t (0.84-1.12) and improved tolerant factor tau (critical value of 6.20) do exist for HOIPs, which are different from inorganic perovskites, providing a simple and fast assessment in the design of materials with an HOIP structure.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据