| Autor: |
Cerqueira, Tiago F. T., Botti, Silvana, Marques, Miguel A. L. |
| Rok vydání: |
2024 |
| Předmět: |
|
| Druh dokumentu: |
Working Paper |
| Popis: |
We present a novel approach to generate a fingerprint for crystalline materials that balances efficiency for machine processing and human interpretability, allowing its application in both machine learning inference and understanding of structure-property relationships. Our proposed fingerprint has two components: one representing the crystal structure and the other characterizing the chemical composition. To represent the latter we construct a non-orthogonal space where each axis represents a chemical element and where the angle between the axes quantifies a measure of the similarity between them. The chemical composition is then defined by the point on the unit sphere in this non-orthogonal space. By utilizing dimension reduction techniques we can construct a two-dimensional global map of the space of the thermodynamically stable crystalline compounds. Despite their simplicity, such maps succeed in providing a physical separation of material classes according to basic physical properties. Moreover, this compositional fingerprint can be used as a versatile input for machine learning algorithms, supplanting conventional one-hot representations of the chemical composition. |
| Databáze: |
arXiv |
| Externí odkaz: |
|
