Data integration for multiple alkali metals in predicting coordination energies based on Bayesian inference
Data integration for multiple alkali metals in predicting coordination energies based on Bayesian inference
复制标题
DOI：
10.1080/27660400.2022.2108353
复制
发表时间：
2022-09
期刊：
影响因子：
--
通讯作者：
Koki Obinata;Tomofumi Nakayama;Atsushi Ishikawa;Keitaro Sodeyama;K. Nagata;Y. Igarashi;M. Okada
中科院分区：
文献类型：
--
作者：
Koki Obinata;Tomofumi Nakayama;Atsushi Ishikawa;Keitaro Sodeyama;K. Nagata;Y. Igarashi;M. Okada
摘要利用基于第一性原理计算的数据集建立机器学习模型是探索下一代电池的重要途径。在以前的研究中，可充电二次电池数据集是通过密度泛函理论（DFT）计算构建的锂离子，然后扩展到五种碱金属离子。该数据集可以被视为由五个碱金属离子组组成，并且了解哪种方法是优选的，以构建针对每个碱金属离子的单独模型，或者通过整合数据集来构建单个模型，这是感兴趣的。我们定量评估的贝叶斯模型选择的框架中的数据集成的可能性，并表明数据集的集成是合适的。此外，使用特征选择提取新知识对于探索下一代电池也很重要。为了进一步推进知识提取，应考虑所选特征的可靠性，以避免误解。我们通过使用贝叶斯模型平均（BMA）计算特征的后验概率来评估特征选择的置信水平。我们发现，当数据数量增加时，特征选择的置信水平也会增加。图形摘要
ABSTRACT Building machine learning models using a dataset calculated by first principles calculations is an important approach to explore the next-generation batteries. In previous studies, the rechargeable secondary battery dataset was constructed for Li ion by density functional theory (DFT) calculation, and after that, extended to five alkali metal ions. This dataset can be regarded as consisting of five alkali metal ion groups, and it is one of the interests to know which approach is preferred to build individual models specialized for each alkali metal ion or build a single model by integrating the datasets. We quantitatively evaluate the possibility of data integration in the framework of Bayesian model selection and show that the integration of datasets is suitable. In addition, extracting new knowledge using feature selection is also important in exploring next-generation batteries. In order to further advance the knowledge extraction, the reliability of the selected features should be considered to avoid misinterpretation. We evaluate the confidence level of feature selection by calculating the posterior probabilities of features using Bayesian model averaging (BMA). We found that the confidence level of feature selection increases when the number of data increases. GRAPHICAL ABSTRACT