论文标题
机器学习辅助钠和锂的超级离子导体中离子电导率的跨域预测
Machine-learning assisted cross-domain prediction of ionic conductivity in sodium and lithium-based superionic conductors
论文作者
论文摘要
固态锂和钠离子电池利用固体离子将化合物作为电解质。但是，此类材料的离子电导率往往低于其液体对应物，因此需要进行研究工作，以寻找合适的替代方法。电解质筛选的过程通常基于域专业知识和反复试验的混合物，它们都是时间和资源密集型的。数据驱动和机器学习方法最近脱颖而出，以加速学习。在这项工作中，我们提出了一种简单的基于机器学习的方法，以预测钠和锂基化合物的离子电导率。我们主要使用可从单位单元格上的列表信息和目标化合物组件的原子特性衍生的理论元素特征描述符，在有限的70个Nasicon餐具的有限数据集中，我们设计了一个基于逻辑回归的模型，能够以较差的超级离子导体和良好的超级离子导体与82％以上的交叉交换精度区分。此外，我们证明了这种系统如何以相同精度在基于锂的示例上进行跨域分类，尽管在训练过程中被引入零基于锂的化合物。通过基于系统的置换评估过程，我们将所考虑特征的数量从47减少到7，减少了83％以上，同时改善了模型性能。还讨论了不同电子和结构特征对整体离子电导率的贡献，并与文献中公认的理论形成鲜明对比。我们的结果表明，通过使用现有数据，这种简单但可解释的工具的实用性为将潜在候选物作为固态电解质的初步筛选提供了机会。
Solid state lithium- and sodium-ion batteries utilize solid ionicly conducting compounds as electrolytes. However, the ionic conductivity of such materials tends to be lower than their liquid counterparts, necessitating research efforts into finding suitable alternatives. The process of electrolyte screening is often based on a mixture of domain expertise and trial-and-error, both of which are time and resource-intensive. Data-driven and machine learning approaches have recently come to the fore to accelerate learnings towards discovery. In this work, we present a simple machine-learning based approach to predict the ionic conductivity of sodium and lithium-based SICON compounds. Using primarily theoretical elemental feature descriptors derivable from tabulated information on the unit cell and the atomic properties of the components of a target compound on a limited dataset of 70 NASICON-examples, we have designed a logistic regression-based model capable of distinguishing between poor and good superionic conductors with a cross-validation accuracy of over 82%. Moreover, we demonstrate how such a system is capable of cross-domain classification on lithium-based examples at the same accuracy, despite being introduced to zero lithium-based compounds during training. Through a systematic permutation-based evaluation process, we reduced the number of considered features from 47 to 7, reduction of over 83%, while simultaneously improving model performance. The contributions of different electronic and structural features to overall ionic conductivity is also discussed, and contrasted with accepted theories in literature. Our results demonstrate the utility of such a simple, yet interpretable tool provides opportunities for initial screening of potential candidates as solid-state electrolytes through the use of existing data.
