Ionic surfactants critical micelle concentration modelling in water/organic solvent mixtures using random forest and support vector machine algorithms

Abstract: The physicochemical property of surfactants that is widely used to study their behavior is the critical micellar concentration (CMC). The value of this property is specific to each surfactant as it depends on a number of external factors and the chemical composition of the surfactant. This research focused on using two new machine learning approaches, Random Forest (RF) and Support Vector Machine (SVM), to predict the logarithmic CMC value of 10 ionic surfactants. The same database from the previous study (a total of 258 experimental cases) was used with the same input variables – those defining the mixture of the organic solvent-water: T, molecular weight, molar fraction and log P; and the chemical composition of the surfactant: number of atoms of each element of the surfactant – to develop the predictive models. The best RF and SVM models were then compared with the best ANN model developed in the previous study. According to the results, the normalized models were those that presented the lowest RMSE values in the validation phase. Finally, the two approaches proposed in this research are suitable tools, together with the ANN, for the prediction of CMC and as possible alternative methods to replace expensive experimental laboratory measurements.

Object Details

• Location: Deutsche Nationalbibliothek Frankfurt am Main
• Extent: Online-Ressource
• Language: Englisch

References and Relationships

• Bibliographic citation: Ionic surfactants critical micelle concentration modelling in water/organic solvent mixtures using random forest and support vector machine algorithms ; volume:62 ; number:1 ; year:2025 ; pages:8-18 ; extent:11 ; Tenside, surfactants, detergents ; 62, Heft 1 (2025), 8-18 (gesamt 11)

Contributors, Places and Time

• Creator: Soria-López, Anton ; García-Martí, María ; Mejuto, Juan C.

Further information

• DOI: 10.1515/tsd-2024-2636
• URN: urn:nbn:de:101:1-2501080507018.996600373696
• Rights: Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
• Last update: 15.08.2025, 7:28 AM CEST