Estimation of Hansen solubility parameters with regularized regression for biomass conversion products: An application of adaptable group contribution. (2nd February 2022)

• Record Type: Journal Article
• Authors: Terrell, Evan
• Is Part Of: Chemical engineering science. Volume 248:Part B(2022)
• Publication Date: 2022-02-02
• Subjects: Biomass conversion -- Hansen solubility parameters -- Group contribution -- Regression modeling; Chemical engineering -- Periodicals; Génie chimique -- Périodiques; Chemical engineering; Periodicals; Electronic journals; 660
• DOI: 10.1016/j.ces.2021.117184
• Languages: English
• ISSNs: 0009-2509

Abstract

Highlights: Hansen solubility parameters are estimated using regularized regression. Regularized regression is applied with adaptable, flexible group contribution. Solubility parameters are estimated for novel biomass-derived compounds. Low computational cost parameter modeling requires no proprietary software. This approach shows promise for extension to modeling other properties. Abstract: Biomass conversion technologies yield unique products for which laboratory characterization of structure and properties is an ongoing challenge. In this study, Hansen solubility parameters are estimated using regularized regression as a platform for adaptable group contribution. A training set of small molecules and a set of biomass conversion molecules are parameterized using simple contributing groups. Regularized regression is then applied as a tool to reduce model complexity. This allows for flexible development of contributing groups, which are then down-selected to those which are most important, while avoiding overfitting. The model is built upon experimental data and uses only python and its science/data analysis libraries. The model also shows good agreement with other published work designed for "pencil and paper" estimation of solubility parameters. The combination of regularized regression with adaptable group contribution has potential for applications in prediction of other molecular properties for which group contribution methods are commonly employed.