EUVIMEDObjevte EUVIMED
Open access · CC BY 3.0

Two-stage transfer learning for deep learning-based prediction of lattice thermal conductivity

Liudmyla Klochko, Mathieu d'Aquin

Physical Chemistry Chemical Physics · 2026 · 28 (13) · 8146-8154

DOI: 10.1039/d5cp04401d ↗

At a glance

Journal article in Physical Chemistry Chemical Physics, 2026. Written by Liudmyla Klochko and 1 co-authors. Institution: Université de Lorraine, LORIA, Nancy F-54000, France. liudmyla.klochko@loria.fr. 42 references. The full text is freely available (open access, CC BY 3.0).

AbstraktBibliografické údajeCiteRelated studies

Abstract (original language)

Machine learning promises to accelerate material discovery by enabling high-throughput prediction of desirable macro-properties from atomic-level descriptors or structures.

Authors and institutions

  • Université de Lorraine, LORIA, Nancy F-54000, France. liudmyla.klochko@loria.fr.

Cite

APA

Klochko, L., & d'Aquin, M. (2026). Two-stage transfer learning for deep learning-based prediction of lattice thermal conductivity. Physical Chemistry Chemical Physics, 28(13), 8146-8154. https://doi.org/10.1039/d5cp04401d

Vancouver

Klochko L, d'Aquin M. Two-stage transfer learning for deep learning-based prediction of lattice thermal conductivity. Physical Chemistry Chemical Physics. 2026;28(13):8146-8154. doi:10.1039/d5cp04401d

BibTeX
@article{Klochko2026,
  author = {Klochko, Liudmyla and d'Aquin, Mathieu},
  title = {Two-stage transfer learning for deep learning-based prediction of lattice thermal conductivity},
  journal = {Physical Chemistry Chemical Physics},
  year = {2026},
  volume = {28},
  number = {13},
  pages = {8146--8154},
  doi = {10.1039/d5cp04401d}
}
Start for free →