Prediction of superior thermoelectric performance in unexplored doped-BiCuSeO via machine learning
BiCuSeO compound is a promising thermoelectric material, which has attracted many experimental studies through trial-and-error approaches to improve its thermoelectric performance by element doping, such that a fast and efficient prediction of thermoelectric property for unexplored and rarely explor...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-05-01
|
| Series: | Materials & Design |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0264127523002836 |
| _version_ | 1797850487557455872 |
|---|---|
| author | Zhijian He Jinlin Peng Chihou Lei Shuhong Xie Daifeng Zou Yunya Liu |
| author_facet | Zhijian He Jinlin Peng Chihou Lei Shuhong Xie Daifeng Zou Yunya Liu |
| author_sort | Zhijian He |
| collection | DOAJ |
| description | BiCuSeO compound is a promising thermoelectric material, which has attracted many experimental studies through trial-and-error approaches to improve its thermoelectric performance by element doping, such that a fast and efficient prediction of thermoelectric property for unexplored and rarely explored doped-BiCuSeO is highly desired. In this work, a machine learning (ML) model for predicting the ZT value of M element doped-BiCuSeO (Bi1-xMxCuSeO) has been established via the correlation analysis for descriptors and the comparison among different ML approaches. The results show that Gradient Boosting Regressor is the most appropriate approach for our ML model, which is well validated by comparing the predicted and experimental ZT values for the cases in the dataset. The ML model is also used to predict the ZT values of Bi1-xMxCuSeO with unexplored and rarely explored doping element M, and the optimal doping elements as well as their doping contents are screened out. The results indicate that the ZT of Bi0.86Po0.14CuSeO (Po-doped) and Bi0.88Cs0.12CuSeO (Cs-doped) are higher than that of pure BiCuSeO, and are improved by 104 % and 98 % at the 923 K, respectively. The enhancement is well explained by the first-principles calculations. The findings offer a guideline for exploring superior thermoelectric performance in BiCuSeO. |
| first_indexed | 2024-04-09T19:01:43Z |
| format | Article |
| id | doaj.art-26ca66d9a2da4f87bc3649932e2dd700 |
| institution | Directory Open Access Journal |
| issn | 0264-1275 |
| language | English |
| last_indexed | 2024-04-09T19:01:43Z |
| publishDate | 2023-05-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Materials & Design |
| spelling | doaj.art-26ca66d9a2da4f87bc3649932e2dd7002023-04-08T05:10:31ZengElsevierMaterials & Design0264-12752023-05-01229111868Prediction of superior thermoelectric performance in unexplored doped-BiCuSeO via machine learningZhijian He0Jinlin Peng1Chihou Lei2Shuhong Xie3Daifeng Zou4Yunya Liu5Key Laboratory of Low Dimensional Materials and Application Technology of Ministry of Education, School of Materials Science and Engineering, Xiangtan University, Xiangtan 411105, ChinaAll-Solid-State Energy Storage Materials and Devices Key Laboratory of Hunan Province, College of Information and Electronic Engineering, Hunan City University, Yiyang 413002, ChinaDepartment of Aerospace and Mechanical Engineering, Saint Louis University, Saint Louis 63103-1110, MO, USAKey Laboratory of Low Dimensional Materials and Application Technology of Ministry of Education, School of Materials Science and Engineering, Xiangtan University, Xiangtan 411105, China; Corresponding authors.School of Physics and Electronic Science, Hunan University of Science and Technology, Xiangtan 411201, China; Corresponding authors.Key Laboratory of Low Dimensional Materials and Application Technology of Ministry of Education, School of Materials Science and Engineering, Xiangtan University, Xiangtan 411105, China; Corresponding authors.BiCuSeO compound is a promising thermoelectric material, which has attracted many experimental studies through trial-and-error approaches to improve its thermoelectric performance by element doping, such that a fast and efficient prediction of thermoelectric property for unexplored and rarely explored doped-BiCuSeO is highly desired. In this work, a machine learning (ML) model for predicting the ZT value of M element doped-BiCuSeO (Bi1-xMxCuSeO) has been established via the correlation analysis for descriptors and the comparison among different ML approaches. The results show that Gradient Boosting Regressor is the most appropriate approach for our ML model, which is well validated by comparing the predicted and experimental ZT values for the cases in the dataset. The ML model is also used to predict the ZT values of Bi1-xMxCuSeO with unexplored and rarely explored doping element M, and the optimal doping elements as well as their doping contents are screened out. The results indicate that the ZT of Bi0.86Po0.14CuSeO (Po-doped) and Bi0.88Cs0.12CuSeO (Cs-doped) are higher than that of pure BiCuSeO, and are improved by 104 % and 98 % at the 923 K, respectively. The enhancement is well explained by the first-principles calculations. The findings offer a guideline for exploring superior thermoelectric performance in BiCuSeO.http://www.sciencedirect.com/science/article/pii/S0264127523002836BiCuSeOThermoelectricMachine learningDopingPrediction |
| spellingShingle | Zhijian He Jinlin Peng Chihou Lei Shuhong Xie Daifeng Zou Yunya Liu Prediction of superior thermoelectric performance in unexplored doped-BiCuSeO via machine learning Materials & Design BiCuSeO Thermoelectric Machine learning Doping Prediction |
| title | Prediction of superior thermoelectric performance in unexplored doped-BiCuSeO via machine learning |
| title_full | Prediction of superior thermoelectric performance in unexplored doped-BiCuSeO via machine learning |
| title_fullStr | Prediction of superior thermoelectric performance in unexplored doped-BiCuSeO via machine learning |
| title_full_unstemmed | Prediction of superior thermoelectric performance in unexplored doped-BiCuSeO via machine learning |
| title_short | Prediction of superior thermoelectric performance in unexplored doped-BiCuSeO via machine learning |
| title_sort | prediction of superior thermoelectric performance in unexplored doped bicuseo via machine learning |
| topic | BiCuSeO Thermoelectric Machine learning Doping Prediction |
| url | http://www.sciencedirect.com/science/article/pii/S0264127523002836 |
| work_keys_str_mv | AT zhijianhe predictionofsuperiorthermoelectricperformanceinunexploreddopedbicuseoviamachinelearning AT jinlinpeng predictionofsuperiorthermoelectricperformanceinunexploreddopedbicuseoviamachinelearning AT chihoulei predictionofsuperiorthermoelectricperformanceinunexploreddopedbicuseoviamachinelearning AT shuhongxie predictionofsuperiorthermoelectricperformanceinunexploreddopedbicuseoviamachinelearning AT daifengzou predictionofsuperiorthermoelectricperformanceinunexploreddopedbicuseoviamachinelearning AT yunyaliu predictionofsuperiorthermoelectricperformanceinunexploreddopedbicuseoviamachinelearning |