Predicting Perovskite Performance with Multiple Machine-Learning Algorithms
Perovskites have attracted increasing attention because of their excellent physical and chemical properties in various fields, exhibiting a universal formula of ABO<sub>3</sub> with matching compatible sizes of A-site and B-site cations. In this work, four different prediction models of...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-07-01
|
| Series: | Crystals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4352/11/7/818 |
| _version_ | 1797527405391249408 |
|---|---|
| author | Ruoyu Li Qin Deng Dong Tian Daoye Zhu Bin Lin |
| author_facet | Ruoyu Li Qin Deng Dong Tian Daoye Zhu Bin Lin |
| author_sort | Ruoyu Li |
| collection | DOAJ |
| description | Perovskites have attracted increasing attention because of their excellent physical and chemical properties in various fields, exhibiting a universal formula of ABO<sub>3</sub> with matching compatible sizes of A-site and B-site cations. In this work, four different prediction models of machine learning algorithms, including support vector regression based on radial basis kernel function (SVM-RBF), ridge regression (RR), random forest (RF), and back propagation neural network (BPNN), are established to predict the formation energy, thermodynamic stability, crystal volume, and oxygen vacancy formation energy of perovskite materials. Combined with the fitting diagrams of the predicted values and DFT calculated values, the results show that SVM-RBF has a smaller bias in predicting the crystal volume. RR has a smaller bias in predicting the thermodynamic stability. RF has a smaller bias in predicting the formation energy, crystal volume, and thermodynamic stability. BPNN has a smaller bias in predicting the formation energy, thermodynamic stability, crystal volume, and oxygen vacancy formation energy. Obviously, different machine learning algorithms exhibit different sensitivity to data sample distribution, indicating that we should select different algorithms to predict different performance parameters of perovskite materials. |
| first_indexed | 2024-03-10T09:42:23Z |
| format | Article |
| id | doaj.art-b85a93a6b14240ce9cb498bb6a7093d5 |
| institution | Directory Open Access Journal |
| issn | 2073-4352 |
| language | English |
| last_indexed | 2024-03-10T09:42:23Z |
| publishDate | 2021-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Crystals |
| spelling | doaj.art-b85a93a6b14240ce9cb498bb6a7093d52023-11-22T03:33:34ZengMDPI AGCrystals2073-43522021-07-0111781810.3390/cryst11070818Predicting Perovskite Performance with Multiple Machine-Learning AlgorithmsRuoyu Li0Qin Deng1Dong Tian2Daoye Zhu3Bin Lin4School of Mechanical and Electrical Engineering, Yangtze Delta Region Institute (HuZhou), University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Mechanical and Electrical Engineering, Yangtze Delta Region Institute (HuZhou), University of Electronic Science and Technology of China, Chengdu 611731, ChinaAnhui Key Laboratory of Low Temperature Co-Fired Material, Huainan Normal University, Huainan 232001, ChinaCenter for Data Science, Peking University, Beijing 100871, ChinaSchool of Mechanical and Electrical Engineering, Yangtze Delta Region Institute (HuZhou), University of Electronic Science and Technology of China, Chengdu 611731, ChinaPerovskites have attracted increasing attention because of their excellent physical and chemical properties in various fields, exhibiting a universal formula of ABO<sub>3</sub> with matching compatible sizes of A-site and B-site cations. In this work, four different prediction models of machine learning algorithms, including support vector regression based on radial basis kernel function (SVM-RBF), ridge regression (RR), random forest (RF), and back propagation neural network (BPNN), are established to predict the formation energy, thermodynamic stability, crystal volume, and oxygen vacancy formation energy of perovskite materials. Combined with the fitting diagrams of the predicted values and DFT calculated values, the results show that SVM-RBF has a smaller bias in predicting the crystal volume. RR has a smaller bias in predicting the thermodynamic stability. RF has a smaller bias in predicting the formation energy, crystal volume, and thermodynamic stability. BPNN has a smaller bias in predicting the formation energy, thermodynamic stability, crystal volume, and oxygen vacancy formation energy. Obviously, different machine learning algorithms exhibit different sensitivity to data sample distribution, indicating that we should select different algorithms to predict different performance parameters of perovskite materials.https://www.mdpi.com/2073-4352/11/7/818perovskitemachine learningperformance predictionalgorithm selection |
| spellingShingle | Ruoyu Li Qin Deng Dong Tian Daoye Zhu Bin Lin Predicting Perovskite Performance with Multiple Machine-Learning Algorithms Crystals perovskite machine learning performance prediction algorithm selection |
| title | Predicting Perovskite Performance with Multiple Machine-Learning Algorithms |
| title_full | Predicting Perovskite Performance with Multiple Machine-Learning Algorithms |
| title_fullStr | Predicting Perovskite Performance with Multiple Machine-Learning Algorithms |
| title_full_unstemmed | Predicting Perovskite Performance with Multiple Machine-Learning Algorithms |
| title_short | Predicting Perovskite Performance with Multiple Machine-Learning Algorithms |
| title_sort | predicting perovskite performance with multiple machine learning algorithms |
| topic | perovskite machine learning performance prediction algorithm selection |
| url | https://www.mdpi.com/2073-4352/11/7/818 |
| work_keys_str_mv | AT ruoyuli predictingperovskiteperformancewithmultiplemachinelearningalgorithms AT qindeng predictingperovskiteperformancewithmultiplemachinelearningalgorithms AT dongtian predictingperovskiteperformancewithmultiplemachinelearningalgorithms AT daoyezhu predictingperovskiteperformancewithmultiplemachinelearningalgorithms AT binlin predictingperovskiteperformancewithmultiplemachinelearningalgorithms |