CopDDB: a descriptor database for copolymers and its applications to machine learning
A descriptor database for copolymers was developed using reaction energies and activation barriers for 2500 radical–monomer pairs. Machine learning models based on these descriptors achieved high accuracy in predicting key physical properties.
Authors
- Miho Hatanaka (ORCID: https://orcid.org/0000-0001-9908-7860)
- Tomoyuki Miyao (ORCID: https://orcid.org/0000-0002-8769-2702)
- Takamitsu Matsubara (ORCID: https://orcid.org/0000-0003-3545-4814)
- Hiroharu Ajiro (ORCID: https://orcid.org/0000-0003-4091-6956)
- Taichi Inagaki (ORCID: https://orcid.org/0000-0002-8112-6419)
- Yu‐ya Ohnishi (ORCID: https://orcid.org/0000-0003-2559-5760)
- Tetsunori Sugawara
- Shigehito Asano
- Takayoshi Yoshimura
- Mikiya Fujii (ORCID: https://orcid.org/0000-0002-3728-3097)
- Hiromoto Kato
- Shunto Oikawa
Institutions
- Yokkaichi University (JP)
- Keio University (JP)
- Institute for Molecular Science (JP)
- Nara Institute of Science and Technology (JP)
Publication Details
- Journal
- Digital Discovery
- Published
- 2024-11-28
- DOI
- https://doi.org/10.1039/d4dd00266k
- Citations
- 7
- Primary Topic
- Machine Learning in Materials Science
- Type
- article
- Field-Weighted Citation Impact
- 0.82
Funders
- Japan Society for the Promotion of Science