Machine learning-based predictions of melting temperature and enthalpy of fusion for protic organic salt phase change materials
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 .
Authors
- Jennifer M. Pringle (ORCID: https://orcid.org/0000-0002-2729-2838)
- Tu C. Le (ORCID: https://orcid.org/0000-0003-3552-8211)
- Karolina Matuszek (ORCID: https://orcid.org/0000-0001-8979-5927)
- Douglas R. MacFarlane (ORCID: https://orcid.org/0000-0001-5963-9659)
- Tamar L. Greaves (ORCID: https://orcid.org/0000-0002-0298-0183)
- Saliha Saher (ORCID: https://orcid.org/0000-0002-4112-8938)
Institutions
- Deakin University (AU)
- Monash University (AU)
- RMIT University (AU)
Publication Details
- Journal
- Materials Advances
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1039/d5ma00498e
- Citations
- 2
- Primary Topic
- Phase-change materials and chalcogenides
- Type
- article
- Field-Weighted Citation Impact
- 1.04