Toward Effective Utilization of Methane: Machine Learning Prediction of Adsorption Energies on Metal Alloys
Toward Effective Utilization of Methane: Machine Learning Prediction of Adsorption Energies on Metal Alloys
复制标题
DOI：
10.1021/acs.jpcc.7b12670
复制
发表时间：
2018-03
影响因子：
3.7
通讯作者：
Takashi Toyao;Keisuke Suzuki;Shoma Kikuchi;S. Takakusagi;K. Shimizu;Ichigaku Takigawa
中科院分区：
文献类型：
--
作者：
Takashi Toyao;Keisuke Suzuki;Shoma Kikuchi;S. Takakusagi;K. Shimizu;Ichigaku Takigawa
用于发现用于特定应用的新材料的过程通常利用大型化合物文库的筛选。在这种方法中，化合物的性能与称为描述符的元素的性质相关。在下面描述的努力中，我们开发了一种简单有效的机器学习（ML）模型，用于预测CH 4相关物种（即，CH 3、CH 2、CH、C和H）在Cu基合金上的吸附能。开发的ML模型预测DFT计算的吸附能与12个描述符，这是现成的值为选定的元素。使用统计交叉验证定量评估了四种回归方法（普通最小二乘线性回归（OLR），随机森林回归（RFR），梯度提升回归（GBR）和额外树回归（ETR））的预测精度，这些回归方法具有不同数量的描述符和不同的测试集/训练集比率。在四种回归方法中，我们发现...
The process employed to discover new materials for specific applications typically utilizes screening of large compound libraries. In this approach, the performance of a compound is correlated to the properties of elements referred to as descriptors. In the effort described below, we developed a simple and efficient machine learning (ML) model for predicting adsorption energies of CH4 related species, namely, CH3, CH2, CH, C, and H on the Cu-based alloys. The developed ML model predicted the DFT-calculated adsorption energies with 12 descriptors, which are readily available values for the selected elements. The predictive accuracy of four regression methods (ordinary linear regression by least-squares (OLR), random forest regression (RFR), gradient boosting regression (GBR), and extra tree regression (ETR)) with different numbers of descriptors and different test-set/training-set ratios was quantitatively evaluated using statistical cross validations. Among four types of regression methods, we have found ...