Data-augmented response surface methodology-machine learning hybrid model for predicting polyvinyl butyral synthesis
Reaction Chemistry & Engineering · 2026 · 11 (8) · 1698-1712
DOI: 10.1039/d6re00081a ↗Kurz gefasst
Fachartikel in der Zeitschrift Reaction Chemistry & Engineering, 2026. Verfasst von Yingying Liu und 2 weiteren Autor:innen. Die Arbeit nennt 47 Literaturangaben.
Abstract (Originalsprache)
LHS augmented RSM–SVR with hyperparameter tuning yields stable test predictions and strong validation set extrapolation; SHAP reveals n -butanal and HNO 3 synergy, and this framework links design, data augmentation, tuning, and interpretability for small sample multiphase synthesis.
Zitieren
APA
Liu, Y., Li, C. Y. V., & Gao, L. (2026). Data-augmented response surface methodology-machine learning hybrid model for predicting polyvinyl butyral synthesis. Reaction Chemistry & Engineering, 11(8), 1698-1712. https://doi.org/10.1039/d6re00081a
Vancouver
Liu Y, Li CYV, Gao L. Data-augmented response surface methodology-machine learning hybrid model for predicting polyvinyl butyral synthesis. Reaction Chemistry & Engineering. 2026;11(8):1698-1712. doi:10.1039/d6re00081a
BibTeX
@article{Liu2026,
author = {Liu, Yingying and Li, Chi Ying Vanessa and Gao, Liang},
title = {Data-augmented response surface methodology-machine learning hybrid model for predicting polyvinyl butyral synthesis},
journal = {Reaction Chemistry & Engineering},
year = {2026},
volume = {11},
number = {8},
pages = {1698--1712},
doi = {10.1039/d6re00081a}
}
EUVIMED