Predicting the formation of fractionally doped perovskite oxides by a function-confined machine learning method
Predicting the formation of fractionally doped perovskite oxides by a function-confined machine learning method
复制标题
DOI：
10.1038/s43246-022-00269-9
复制
发表时间：
2022-07
影响因子：
7.8
通讯作者：
X. Zhai;Fei Ding;Zeyu Zhao;Aaron Santomauro;Feng Luo;J. Tong
中科院分区：
文献类型：
--
作者：
X. Zhai;Fei Ding;Zeyu Zhao;Aaron Santomauro;Feng Luo;J. Tong
分数掺杂的钙钛矿氧化物（FDPO）已经展示了普遍的应用，例如能量转换、存储和收集、催化、传感器、超导体、铁电体、压电体、磁性和发光。因此，非常需要一种准确、成本有效且易于使用的方法来发现新的组合物。在这里，我们开发了一种功能受限的机器学习方法，从有限的实验数据中发现具有高预测精度的新FDPO。通过专注于一个特定的应用，即太阳能热化学制氢，我们收集了632个训练数据，并定义了21个理想的功能。我们的梯度提升分类器模型实现了95.4%的高预测准确率和0.921的高F1得分。此外，当从现有的文献中额外的36个实验数据进行验证时，该模型显示出94.4%的预测准确度。在这种机器学习方法的帮助下，我们确定并合成了11种新的FDPO组合物，其中7种与太阳能热化学制氢相关。我们相信这种受限的机器学习方法可以用于从有限的数据中发现具有其他特定应用目的的FDPO。
Fractionally doped perovskites oxides (FDPOs) have demonstrated ubiquitous applications such as energy conversion, storage and harvesting, catalysis, sensor, superconductor, ferroelectric, piezoelectric, magnetic, and luminescence. Hence, an accurate, cost-effective, and easy-to-use methodology to discover new compositions is much needed. Here, we developed a function-confined machine learning methodology to discover new FDPOs with high prediction accuracy from limited experimental data. By focusing on a specific application, namely solar thermochemical hydrogen production, we collected 632 training data and defined 21 desirable features. Our gradient boosting classifier model achieved a high prediction accuracy of 95.4% and a high F1 score of 0.921. Furthermore, when verified on additional 36 experimental data from existing literature, the model showed a prediction accuracy of 94.4%. With the help of this machine learning approach, we identified and synthesized 11 new FDPO compositions, 7 of which are relevant for solar thermochemical hydrogen production. We believe this confined machine learning methodology can be used to discover, from limited data, FDPOs with other specific application purposes.