| About this Abstract |
| Meeting |
MS&T24: Materials Science & Technology
|
| Symposium
|
Advances in Dielectric Materials and Electronic Devices
|
| Presentation Title |
Machine Learning Predictions of Structural and Ferroelectric Properties of Perovskites |
| Author(s) |
Luiz Fernando Cotica, Hugo Nasser Machado, Gustavo Sanguino Dias, Valdirlei Fernandes Freitas, Ivair Aparecido dos Santos, Ruyan Guo, Amar Bhalla |
| On-Site Speaker (Planned) |
Luiz Fernando Cotica |
| Abstract Scope |
The integration of machine learning with materials science has introduced a new era of predictive capabilities in understanding material properties. This study prospects into the application of machine learning methodologies to investigate ferroelectric materials, with a specific focus on those exhibiting a perovskite structure. A crystal structure database was built containing the properties of these materials. By using different machine learning algorithms, structural parameter predictions were refined. Further analysis and validation efforts were made to underscore the potential of machine learning in generating structure predictions closely to experimental observations, particularly within the domain of ferroelectric perovskites. Finally, estimations of electric polarization and dielectric properties for these materials, demonstrating results in close proximity to experimental benchmarks. |