Data-driven prediction of chemically relevant compositions in multi-component systems using tensor embeddings
Abstract The discovery of novel materials is crucial for developing new functional materials. This study introduces a predictive model designed to forecast complex multi-component oxide compositions, leveraging data derived from simpler pseudo-binary systems. By applying tensor decomposition and mac...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-024-85062-z |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841544804600643584 |
|---|---|
| author | Hiroyuki Hayashi Isao Tanaka |
| author_facet | Hiroyuki Hayashi Isao Tanaka |
| author_sort | Hiroyuki Hayashi |
| collection | DOAJ |
| description | Abstract The discovery of novel materials is crucial for developing new functional materials. This study introduces a predictive model designed to forecast complex multi-component oxide compositions, leveraging data derived from simpler pseudo-binary systems. By applying tensor decomposition and machine learning techniques, we transformed pseudo-binary oxide compositions from the Inorganic Crystal Structure Database (ICSD) into tensor representations, capturing key chemical trends such as oxidation states and periodic positions. Tucker decomposition was utilized to extract tensor embeddings, which were used to train a Random Forest classifier. The model successfully predicted the existence probabilities of pseudo-ternary and quaternary oxides, with 84% and 52% of ICSD-registered compositions, respectively, achieving high scores. Our approach highlights the potential of leveraging simpler oxide data to predict more complex compositions, suggesting broader applicability to other material systems such as sulfides and nitrides. |
| format | Article |
| id | doaj-art-279d0aff3c9a4c738f2dbe87bcbe22f5 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-279d0aff3c9a4c738f2dbe87bcbe22f52025-01-12T12:16:43ZengNature PortfolioScientific Reports2045-23222025-01-011511910.1038/s41598-024-85062-zData-driven prediction of chemically relevant compositions in multi-component systems using tensor embeddingsHiroyuki Hayashi0Isao Tanaka1Department of Materials Science and Engineering, Kyoto UniversityDepartment of Materials Science and Engineering, Kyoto UniversityAbstract The discovery of novel materials is crucial for developing new functional materials. This study introduces a predictive model designed to forecast complex multi-component oxide compositions, leveraging data derived from simpler pseudo-binary systems. By applying tensor decomposition and machine learning techniques, we transformed pseudo-binary oxide compositions from the Inorganic Crystal Structure Database (ICSD) into tensor representations, capturing key chemical trends such as oxidation states and periodic positions. Tucker decomposition was utilized to extract tensor embeddings, which were used to train a Random Forest classifier. The model successfully predicted the existence probabilities of pseudo-ternary and quaternary oxides, with 84% and 52% of ICSD-registered compositions, respectively, achieving high scores. Our approach highlights the potential of leveraging simpler oxide data to predict more complex compositions, suggesting broader applicability to other material systems such as sulfides and nitrides.https://doi.org/10.1038/s41598-024-85062-z |
| spellingShingle | Hiroyuki Hayashi Isao Tanaka Data-driven prediction of chemically relevant compositions in multi-component systems using tensor embeddings Scientific Reports |
| title | Data-driven prediction of chemically relevant compositions in multi-component systems using tensor embeddings |
| title_full | Data-driven prediction of chemically relevant compositions in multi-component systems using tensor embeddings |
| title_fullStr | Data-driven prediction of chemically relevant compositions in multi-component systems using tensor embeddings |
| title_full_unstemmed | Data-driven prediction of chemically relevant compositions in multi-component systems using tensor embeddings |
| title_short | Data-driven prediction of chemically relevant compositions in multi-component systems using tensor embeddings |
| title_sort | data driven prediction of chemically relevant compositions in multi component systems using tensor embeddings |
| url | https://doi.org/10.1038/s41598-024-85062-z |
| work_keys_str_mv | AT hiroyukihayashi datadrivenpredictionofchemicallyrelevantcompositionsinmulticomponentsystemsusingtensorembeddings AT isaotanaka datadrivenpredictionofchemicallyrelevantcompositionsinmulticomponentsystemsusingtensorembeddings |