EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 3.0

Machine learning-based predictions of melting temperature and enthalpy of fusion for protic organic salt phase change materials

Saliha Saher, Tu C. Le, Tamar L. Greaves, Jennifer M. Pringle, Douglas R. MacFarlane, Karolina Matuszek

Materials Advances · 2025 · 6 (17) · 6140-6151

DOI: 10.1039/d5ma00498e ↗

Kurz gefasst

Fachartikel in der Zeitschrift Materials Advances, 2025. Verfasst von Saliha Saher und 5 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 72 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 3.0). Gefördert von: Australian Research Council.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Linear and non-linear machine learning models predicted T m and Δ H f of 182 protic salts, achieving R 2 as high as 0.82. Experimental cross-validation demonstrated the acceptable predictive ability of linear models for both T m and Δ H f .

Förderung

  • Australian Research Council

Zitieren

APA

Saher, S., Le, T. C., Greaves, T. L., Pringle, J. M., MacFarlane, D. R., & Matuszek, K. (2025). Machine learning-based predictions of melting temperature and enthalpy of fusion for protic organic salt phase change materials. Materials Advances, 6(17), 6140-6151. https://doi.org/10.1039/d5ma00498e

Vancouver

Saher S, Le TC, Greaves TL, Pringle JM, MacFarlane DR, Matuszek K. Machine learning-based predictions of melting temperature and enthalpy of fusion for protic organic salt phase change materials. Materials Advances. 2025;6(17):6140-6151. doi:10.1039/d5ma00498e

BibTeX
@article{Saher2025,
  author = {Saher, Saliha and Le, Tu C. and Greaves, Tamar L. and Pringle, Jennifer M. and MacFarlane, Douglas R. and Matuszek, Karolina},
  title = {Machine learning-based predictions of melting temperature and enthalpy of fusion for protic organic salt phase change materials},
  journal = {Materials Advances},
  year = {2025},
  volume = {6},
  number = {17},
  pages = {6140--6151},
  doi = {10.1039/d5ma00498e}
}
Kostenlos starten →