Using GPT-4 in parameter selection of polymer informatics: improving predictive accuracy amidst data scarcity and ‘Ugly Duckling’ dilemma
Open Access
- 12 September 2023
- journal article
- research article
- Published by Royal Society of Chemistry (RSC) in Digital Discovery
- Vol. 2 (5) , 1548-1557
Abstract
Data scarcity in materials informatics hinders structure–property relationships. Using GPT-4 can address challenges, improving predictions like polymer refractive indices.Keywords
Funding Information
- Japan Society for the Promotion of Science (21H02017, 21H04695, 22H04623, 22KJ2927)
- Japan Science and Technology Corporation (JPMJFR213V)
This publication has 49 references indexed in Scilit:
- Designing High-Refractive Index Polymers Using Materials InformaticsPolymers, 2018
- Machine learning in materials informatics: recent applications and prospectsnpj Computational Materials, 2017
- JRgui: A Python Program of Joback and Reid MethodACS Omega, 2017
- QSPR studies on refractive indices of structurally heterogeneous polymersChemometrics and Intelligent Laboratory Systems, 2015
- Group Contribution Model for the Prediction of Refractive Indices of Organic CompoundsJournal of Chemical & Engineering Data, 2014
- Commentary: The Materials Project: A materials genome approach to accelerating materials innovationAPL Materials, 2013
- Optimization of parameters for semiempirical methods VI: more modifications to the NDDO approximations and re-optimization of parametersJournal of Molecular Modeling, 2012
- The NCBI BioSystems databaseNucleic Acids Research, 2009
- Pattern Representation in Feature Extraction and Classifier Design: Matrix Versus VectorIEEE Transactions on Neural Networks, 2008
- A Group-Contribution Method for Predicting Pure Component Properties of Biochemical and Safety InterestIndustrial & Engineering Chemistry Research, 2004