Machine learning-based prediction models for formation energies of interstitial atoms in HCP crystals
| Autor: | Dongwoo Lee, Won-Yong Shin, Sooran Kim, Keonwook Kang, Daegun You, Shraddha Ganorkar |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Materials science
Brute-force search 02 engineering and technology Machine learning computer.software_genre 01 natural sciences Kriging Interstitial defect 0103 physical sciences Linear regression General Materials Science Mathematics 010302 applied physics business.industry Mechanical Engineering Metals and Alloys Nonparametric statistics 021001 nanoscience & nanotechnology Condensed Matter Physics Support vector machine Mechanics of Materials Parametric model Artificial intelligence 0210 nano-technology business computer Predictive modelling |
| Zdroj: | Scripta Materialia. 183:1-5 |
| ISSN: | 1359-6462 |
| DOI: | 10.1016/j.scriptamat.2020.02.042 |
| Popis: | Prediction models of the formation energies of H, B, C, N, and O atoms in various interstitial sites of hcp-Ti, Zr, and Hf crystals are developed based on machine learning. Parametric models such as linear regression and brute force search (BFS) as well as nonparametric algorithms including the support vector regression (SVR) and the Gaussian process regression (GPR) are employed. Readily accessible chemical and geometrical descriptors allow straightforward implementation of the prediction models without any expensive computational modeling. The models based on BFS, SVR, and GPR show the excellent performance with R2 > 96%. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect