Accelerating spin Hall conductivity predictions via machine learning
Abstract Accurately predicting the spin Hall conductivity (SHC) is crucial for designing novel spintronic devices that leverage the spin Hall effect. First‐principles calculations of SHCs are computationally intensive and unsuitable for quick high‐throughput screening. Here, we have developed a resi...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley-VCH
2024-12-01
|
| Series: | Materials Genome Engineering Advances |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/mgea.67 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841543273539174400 |
|---|---|
| author | Jinbin Zhao Junwen Lai Jiantao Wang Yi‐Chi Zhang Junlin Li Xing‐Qiu Chen Peitao Liu |
| author_facet | Jinbin Zhao Junwen Lai Jiantao Wang Yi‐Chi Zhang Junlin Li Xing‐Qiu Chen Peitao Liu |
| author_sort | Jinbin Zhao |
| collection | DOAJ |
| description | Abstract Accurately predicting the spin Hall conductivity (SHC) is crucial for designing novel spintronic devices that leverage the spin Hall effect. First‐principles calculations of SHCs are computationally intensive and unsuitable for quick high‐throughput screening. Here, we have developed a residual crystal graph convolutional neural network (Res‐CGCNN) deep learning model to classify and predict SHCs solely based on the structural and compositional information. This is enabled by having access to 9249 instances of SHCs data and incorporating extra residual networks into the standard CGCNN framework. We found that Res‐CGCNN surpasses CGCNN, achieving a mean absolute error of 115.4 (ℏ/e) (S/cm) for regression and an area under the receiver operating characteristic curve of 0.86 for classification. Additionally, we utilized Res‐CGCNN to conduct high‐throughput screenings of materials in the Materials Project database that were absent in the training set. This led to the prediction of several previously unreported materials displaying large SHCs exceeding 1000 (ℏ/e) (S/cm), which were validated through first‐principles calculations. This study represents the inaugural endeavor to construct a machine learning model capable of effectively capturing the intricate nonlinear relationship between SHCs and crystal structure and composition, serving as a useful tool for the efficient screening and design of materials exhibiting high SHCs. |
| format | Article |
| id | doaj-art-806948faffd24c4086f7d989e4c1f6b6 |
| institution | Kabale University |
| issn | 2940-9489 2940-9497 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Wiley-VCH |
| record_format | Article |
| series | Materials Genome Engineering Advances |
| spelling | doaj-art-806948faffd24c4086f7d989e4c1f6b62025-01-13T15:15:31ZengWiley-VCHMaterials Genome Engineering Advances2940-94892940-94972024-12-0124n/an/a10.1002/mgea.67Accelerating spin Hall conductivity predictions via machine learningJinbin Zhao0Junwen Lai1Jiantao Wang2Yi‐Chi Zhang3Junlin Li4Xing‐Qiu Chen5Peitao Liu6School of Materials Science and Engineering Taiyuan University of Science and Technology Taiyuan ChinaShenyang National Laboratory for Materials Science Institute of Metal Research Chinese Academy of Sciences Shenyang ChinaShenyang National Laboratory for Materials Science Institute of Metal Research Chinese Academy of Sciences Shenyang ChinaShenyang National Laboratory for Materials Science Institute of Metal Research Chinese Academy of Sciences Shenyang ChinaSchool of Materials Science and Engineering Taiyuan University of Science and Technology Taiyuan ChinaShenyang National Laboratory for Materials Science Institute of Metal Research Chinese Academy of Sciences Shenyang ChinaShenyang National Laboratory for Materials Science Institute of Metal Research Chinese Academy of Sciences Shenyang ChinaAbstract Accurately predicting the spin Hall conductivity (SHC) is crucial for designing novel spintronic devices that leverage the spin Hall effect. First‐principles calculations of SHCs are computationally intensive and unsuitable for quick high‐throughput screening. Here, we have developed a residual crystal graph convolutional neural network (Res‐CGCNN) deep learning model to classify and predict SHCs solely based on the structural and compositional information. This is enabled by having access to 9249 instances of SHCs data and incorporating extra residual networks into the standard CGCNN framework. We found that Res‐CGCNN surpasses CGCNN, achieving a mean absolute error of 115.4 (ℏ/e) (S/cm) for regression and an area under the receiver operating characteristic curve of 0.86 for classification. Additionally, we utilized Res‐CGCNN to conduct high‐throughput screenings of materials in the Materials Project database that were absent in the training set. This led to the prediction of several previously unreported materials displaying large SHCs exceeding 1000 (ℏ/e) (S/cm), which were validated through first‐principles calculations. This study represents the inaugural endeavor to construct a machine learning model capable of effectively capturing the intricate nonlinear relationship between SHCs and crystal structure and composition, serving as a useful tool for the efficient screening and design of materials exhibiting high SHCs.https://doi.org/10.1002/mgea.67CGCNNfirst‐principles calculationsmachine learningspin Hall conductivity |
| spellingShingle | Jinbin Zhao Junwen Lai Jiantao Wang Yi‐Chi Zhang Junlin Li Xing‐Qiu Chen Peitao Liu Accelerating spin Hall conductivity predictions via machine learning Materials Genome Engineering Advances CGCNN first‐principles calculations machine learning spin Hall conductivity |
| title | Accelerating spin Hall conductivity predictions via machine learning |
| title_full | Accelerating spin Hall conductivity predictions via machine learning |
| title_fullStr | Accelerating spin Hall conductivity predictions via machine learning |
| title_full_unstemmed | Accelerating spin Hall conductivity predictions via machine learning |
| title_short | Accelerating spin Hall conductivity predictions via machine learning |
| title_sort | accelerating spin hall conductivity predictions via machine learning |
| topic | CGCNN first‐principles calculations machine learning spin Hall conductivity |
| url | https://doi.org/10.1002/mgea.67 |
| work_keys_str_mv | AT jinbinzhao acceleratingspinhallconductivitypredictionsviamachinelearning AT junwenlai acceleratingspinhallconductivitypredictionsviamachinelearning AT jiantaowang acceleratingspinhallconductivitypredictionsviamachinelearning AT yichizhang acceleratingspinhallconductivitypredictionsviamachinelearning AT junlinli acceleratingspinhallconductivitypredictionsviamachinelearning AT xingqiuchen acceleratingspinhallconductivitypredictionsviamachinelearning AT peitaoliu acceleratingspinhallconductivitypredictionsviamachinelearning |