XGBoost model for electrocaloric temperature change prediction in ceramics
Abstract An eXtreme Gradient Boosting (XGBoost) machine learning model is built to predict the electrocaloric (EC) temperature change of a ceramic based on its composition (encoded by Magpie elemental properties), dielectric constant, Curie temperature, and characterization conditions. A dataset of...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-07-01
|
| Series: | npj Computational Materials |
| Online Access: | https://doi.org/10.1038/s41524-022-00826-3 |
| _version_ | 1811328349565353984 |
|---|---|
| author | Jie Gong Sharon Chu Rohan K. Mehta Alan J. H. McGaughey |
| author_facet | Jie Gong Sharon Chu Rohan K. Mehta Alan J. H. McGaughey |
| author_sort | Jie Gong |
| collection | DOAJ |
| description | Abstract An eXtreme Gradient Boosting (XGBoost) machine learning model is built to predict the electrocaloric (EC) temperature change of a ceramic based on its composition (encoded by Magpie elemental properties), dielectric constant, Curie temperature, and characterization conditions. A dataset of 97 EC ceramics is assembled from the experimental literature. By sampling data from clusters in the feature space, the model can achieve a coefficient of determination of 0.77 and a root mean square error of 0.38 K for the test data. Feature analysis shows that the model captures known physics for effective EC materials. The Magpie features help the model to distinguish between materials, with the elemental electronegativities and ionic charges identified as key features. The model is applied to 66 ferroelectrics whose EC performance has not been characterized. Lead-free candidates with a predicted EC temperature change above 2 K at room temperature and 100 kV/cm are identified. |
| first_indexed | 2024-04-13T15:23:27Z |
| format | Article |
| id | doaj.art-86ca1e53d261451cb7bcfc69b6b6abf1 |
| institution | Directory Open Access Journal |
| issn | 2057-3960 |
| language | English |
| last_indexed | 2024-04-13T15:23:27Z |
| publishDate | 2022-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Computational Materials |
| spelling | doaj.art-86ca1e53d261451cb7bcfc69b6b6abf12022-12-22T02:41:34ZengNature Portfolionpj Computational Materials2057-39602022-07-018111010.1038/s41524-022-00826-3XGBoost model for electrocaloric temperature change prediction in ceramicsJie Gong0Sharon Chu1Rohan K. Mehta2Alan J. H. McGaughey3Department of Mechanical Engineering, Carnegie Mellon UniversityDepartment of Mechanical Engineering, Carnegie Mellon UniversityDepartment of Mechanical Engineering, Carnegie Mellon UniversityDepartment of Mechanical Engineering, Carnegie Mellon UniversityAbstract An eXtreme Gradient Boosting (XGBoost) machine learning model is built to predict the electrocaloric (EC) temperature change of a ceramic based on its composition (encoded by Magpie elemental properties), dielectric constant, Curie temperature, and characterization conditions. A dataset of 97 EC ceramics is assembled from the experimental literature. By sampling data from clusters in the feature space, the model can achieve a coefficient of determination of 0.77 and a root mean square error of 0.38 K for the test data. Feature analysis shows that the model captures known physics for effective EC materials. The Magpie features help the model to distinguish between materials, with the elemental electronegativities and ionic charges identified as key features. The model is applied to 66 ferroelectrics whose EC performance has not been characterized. Lead-free candidates with a predicted EC temperature change above 2 K at room temperature and 100 kV/cm are identified.https://doi.org/10.1038/s41524-022-00826-3 |
| spellingShingle | Jie Gong Sharon Chu Rohan K. Mehta Alan J. H. McGaughey XGBoost model for electrocaloric temperature change prediction in ceramics npj Computational Materials |
| title | XGBoost model for electrocaloric temperature change prediction in ceramics |
| title_full | XGBoost model for electrocaloric temperature change prediction in ceramics |
| title_fullStr | XGBoost model for electrocaloric temperature change prediction in ceramics |
| title_full_unstemmed | XGBoost model for electrocaloric temperature change prediction in ceramics |
| title_short | XGBoost model for electrocaloric temperature change prediction in ceramics |
| title_sort | xgboost model for electrocaloric temperature change prediction in ceramics |
| url | https://doi.org/10.1038/s41524-022-00826-3 |
| work_keys_str_mv | AT jiegong xgboostmodelforelectrocalorictemperaturechangepredictioninceramics AT sharonchu xgboostmodelforelectrocalorictemperaturechangepredictioninceramics AT rohankmehta xgboostmodelforelectrocalorictemperaturechangepredictioninceramics AT alanjhmcgaughey xgboostmodelforelectrocalorictemperaturechangepredictioninceramics |