Thermodynamic assessment of machine learning models for solid-state synthesis prediction
Materials Horizons · 2026 · 13 (16) · 8188-8202
DOI: 10.1039/d6mh00209a ↗Kurz gefasst
Fachartikel in der Zeitschrift Materials Horizons, 2026. Verfasst von Jane Schlesinger und 3 weiteren Autor:innen. Beteiligte Einrichtung: Chemical Engineering and Materials Science, University of Minnesota, Minneapolis, MN 55455, USA. cbartel@umn.edu. Die Arbeit nennt 55 Literaturangaben. Gefördert von: Division of Information and Intelligent Systems.
Abstract (Originalsprache)
This work evaluates the performance of machine learning models for synthesizability prediction against computable thermodynamic heuristics associated with material stability and reaction selectivity.
Autor:innen und Institutionen
- Chemical Engineering and Materials Science, University of Minnesota, Minneapolis, MN 55455, USA. cbartel@umn.edu.
Förderung
- Division of Information and Intelligent Systems
Zitieren
APA
Schlesinger, J., Hjaltason, S., Szymanski, N. J., & Bartel, C. J. (2026). Thermodynamic assessment of machine learning models for solid-state synthesis prediction. Materials Horizons, 13(16), 8188-8202. https://doi.org/10.1039/d6mh00209a
Vancouver
Schlesinger J, Hjaltason S, Szymanski NJ, Bartel CJ. Thermodynamic assessment of machine learning models for solid-state synthesis prediction. Materials Horizons. 2026;13(16):8188-8202. doi:10.1039/d6mh00209a
BibTeX
@article{Schlesinger2026,
author = {Schlesinger, Jane and Hjaltason, Simon and Szymanski, Nathan J and Bartel, Christopher J},
title = {Thermodynamic assessment of machine learning models for solid-state synthesis prediction},
journal = {Materials Horizons},
year = {2026},
volume = {13},
number = {16},
pages = {8188--8202},
doi = {10.1039/d6mh00209a}
}
EUVIMED