Machine learning of polyurethane prepolymer viscosity: a comparison of chemical and physicochemical approaches
A dual machine learning framework predicts polyurethane prepolymer viscosity using either chemical composition or physicochemical descriptors, balancing accuracy for known chemistries with generalizability to new formulations.
Authors
- Calvin Gang
- Karl W. Haider
- Joseph Pugar (ORCID: https://orcid.org/0000-0003-3295-5664)
- Newell R. Washburn (ORCID: https://orcid.org/0000-0001-7843-8860)
- I. Millán (ORCID: https://orcid.org/0009-0006-6305-6142)
Institutions
- Covestro (United States) (US)
- Carnegie Mellon University (US)
Publication Details
- Journal
- Digital Discovery
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1039/d5dd00287g
- Primary Topic
- Machine Learning in Materials Science
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Covestro