Machine learningmodels for the prediction of diffusivities in supercritical CO2 systems

abstract

The molecular diffusion coefficient is fundamental to estimate dispersion coefficients, convective mass transfer coefficients, etc. Since experimental diffusion data is scarce, there is significant demand for accurate models capable of providing reliable diffusion coefficient estimations. In this work we applied machine learning algorithms to develop predictive models to estimate diffusivities of solutes in supercritical carbon dioxide. A database of experimental data containing 13 properties for 174 binary systems totaling 4917 data points was used in the training of the models. Five machine learning algorithms were evaluated and the results were compared with three commonly used classic models. The best results were found using the Gradient Boosted algorithm which showed an average absolute relative deviation (AARD) of 2.58 % (pure prediction). This model has five parameters: temperature, density, solute molar mass, solute critical pressure and solute acentric factor. For the same dataset, the classic Wilke-Chang equation showed AARD of 12.41 %. The developed model is provided as command line program. (C) 2021 Elsevier B.V. All rights reserved.

subject category

Chemistry, Physical; Physics, Atomic, Molecular & Chemical

authors

Aniceto, JPS; Zezere, B; Silva, CM

our authors

acknowledgements

This work was developed within the scope of the project CICECO-Aveiro Institute of Materials, UIDB/50011/2020 & UIDP/50011/2020, financed by national funds through the Foundation for Science and Technology/MCTES, as well as the Multibiorefinery project (POCI-01-0145-FEDER-016403). Bruno Zezere thanks FCT for PhD grant SFRH/BD/137751/2018.

Share this project:

Related Publications

We use cookies for marketing activities and to offer you a better experience. By clicking “Accept Cookies” you agree with our cookie policy. Read about how we use cookies by clicking "Privacy and Cookie Policy".