A Comparison of Machine Learning Approaches in Predicting Viscosity for Partially Hydrolyzed Polyacrylamide Derivatives

Kelly Cristine Da Silveira; Matheus Henrique Silva  Siqueira; João Matheus Ramos  Gama; Jonathan Nogueira  Gois; Cláudio Fabiano Motta  Toledo; Antônio J.  Silva Neto

doi:10.14295/vetor.v33i1.15157

Authors

Kelly Cristine Da Silveira State University of Rio de Janeiro, Polytechnic Institute, Nova Friburgo, RJ, Brazil http://orcid.org/0000-0002-6055-6778
Matheus Henrique Silva Siqueira State University of Rio de Janeiro, Polytechnic Institute, Nova Friburgo, RJ, Brazil https://orcid.org/0000-0003-2178-9779
João Matheus Ramos Gama State University of Rio de Janeiro, Polytechnic Institute, Nova Friburgo, RJ, Brazil
Jonathan Nogueira Gois Federal Center for Technological Education Celso Suckow da Fonseca, Nova Friburgo, RJ, Brazil https://orcid.org/0000-0002-2859-7668
Cláudio Fabiano Motta Toledo University of São Paulo, Institute of Mathematics and Computer Sciences, São Carlos, SP, Brazil https://orcid.org/0000-0003-4776-8052
Antônio J. Silva Neto State University of Rio de Janeiro, Polytechnic Institute, Nova Friburgo, RJ, Brazil https://orcid.org/0000-0002-9616-6093

DOI:

https://doi.org/10.14295/vetor.v33i1.15157

Keywords:

Partially Hydrolyzed Polyacrylamide, Machine Learning, Viscosity

Abstract

Partially hydrolyzed polyacrylamides (HPAM) are widely used to modulate the viscosity of formulations. The appropriate application of a viscosity model can facilitate the idealization of new macromolecules and contribute to a better understanding of the structure-property relationship. In the present study, machine learning approaches, Multiple Linear Regression (MLR) and Random Forest (RF), were compared to model the viscosifying effect of HPAM derivatives, based on their chemical composition and concentration in an aqueous solution. The evaluated data come from a previous experimental study, which explores a post-synthetic polymer modification methodology. The relative importance of the variables was investigated, determining the features with the greatest influence on viscosity, including variations in chemical composition, with emphasis on the more hydrophobic groups (C7 and C12). The accuracy of the models was evaluated using statistical criteria, the coefficient of determination (R²) and the Root Mean Square Error (RMSE). The Random Forest approach outperformed Multiple Linear Regression, with values of 0.97 and 0.30 for R² and RMSE, respectively, compared to 0.83 and 0.67 for Multiple Linear Regression. Applying the Random Forest model, it was possible to generate a set of hypothetical macromolecules, with potential viscosifying effects. These macromolecules were idealized focusing on mixed compositions of C7 and C12 with a maximum structural variation of 10 mol%. Additionally, this structural mapping provided insights for designing promising polymers by inserting cyclic structures, such as CYCLOPROP, which could overcome the solubility limitation observed in the literature.

Downloads

Download data is not yet available.

References

E. F. Lucas, L. S. Spinelli, C. N. Khalil, “Polymers Applications in Petroleum Production”. In Encyclopedia of Polymer Science and Technology, 5th ed., 2015, pp. 01-49. Available at: https://doi.org/10.1002/0471440264.pst641.

Y. Feng, L. Billon, B. Grassl, A. Khoukh, and J. François, “Hydrophobically associating polyacrylamides and their partially hydrolyzed derivatives prepared by post-modification. 1. Synthesis and characterization,” Polymer, vol. 43, pp. 2055-2064, 2002. Available at: https://doi.org/10.1016/S0032-3861(01)00774-1.

W. Kuang, and C. W. Gao, “Synthesis and Characterization of Novel Twin-Tailed Hydrophobically Associated Copolymers and Their Applications to Cr(III) Removal from Aqueous Solutions,” Journal of Applied Polymer Science, vol. 131, 41028, 2014. Available at: https://doi.org/10.1002/app.41028.

K. C. Da Silveira, Q. Sheng, W. Tian, E.F. Lucas, and C. D. Wood, “Libraries of modified polyacrylamides using post-synthetic modification,” Journal of Applied Polymer Science, vol. 132, no. 47, 2015. Available at: https://doi.org/10.1002/app.42797.

J. N. Kumar, Q. Li, K.Y. Tang, T. Buonassisi, A. L. Gonzalez-Oyarce, and J. Ye, “Machine learning enables polymer cloud-point engineering via inverse design,” Npj Computational Materials, vol 5, pp. 1-6, 2019. Available at: https://doi.org/10.1038/s41524-019-0209-9.

L. Chen, G. Pilania, R. Batra, T. D. Huan, C. Kim, C. Kuenneth, and R. Ramprasad, “Polymer informatics: Current status and critical next steps,” Materials Science and Engineering: R: Reports, vol. 144, 100595, 2021. Available at: https://doi.org/10.1016/j.mser.2020.100595.

S. Wu, Y. Kondo, M. A. Kakimoto, M. A. Kakimoto, B. Yang, H. Yamada, I. Kuwajima, G. Lambard, K. Hongo, Y. Xu, J. Shiomi, C. Schick, J. Morikawa, and R. Yoshid, “Machine-learning-assisted discovery of polymers with high thermal conductivity using a molecular design algorithm,” Npj Computational Materials, vol 5, pp. 1-6, 2019. Available at: https://doi.org/10.1038/s41524-019-0203-2.

Z. R. Najafabadi, e J. B. Soares, “Flocculation and dewatering of oil sands tailings with a novel functionalized polyolefin flocculant,” Separation and Purification Technology, vol. 274, 119018, 2021. Available at: https://doi.org/10.1016/j.seppur.2021.119018.

L. Breiman, “Random Forests,” Machine Learning, vol. 45, pp. 5–32, 2001. Available at: https://doi.org/10.1023/A:1010933404324.

G. Y. Oukawa, P. Krecl, and A. C. Targino, “Fine-scale modeling of the urban heat island: a comparison of multiple linear regression and random forest approaches.,” Sci. Total Environment, vol. 815, 152836, 2022. Available at: https://doi.org/10.1016/j.scitotenv.2021.152836.

I. Ouedraogo, P. Defourny, e M. Vanclooster, “Application of random forest regression and comparison of its performance to multiple linear regression in modeling groundwater nitrate concentration at the African continent scale,” Hydrogeology Journal, vol. 27, pp. 1081–1098, 2019. Available at: https://doi.org/10.1007/s10040-018-1900-5.

Y. Ueki, N. Seko, e Y. Maekawa, “Machine learning approach for prediction of the grafting yield in radiationinduced graft polymerization,” Applied Materials Today, vol. 25, 101158, 2021. Available at: https://doi.org/10.1016/j.apmt.2021.101158.

M. Kishino, K. Matsumoto, Y. Kobayashi, R. Taguchi, N. Akamatsu, and A. Shishido, “Fatigue Life Prediction of Bending Polymer Films using Random Forest,” International Journal of Fatigue, 107230, 2022. Available at: https://doi.org/10.1016/j.ijfatigue.2022.107230

K. C. Da Silveira, Q. Sheng, W. Tian, C. Fong, N. Maeda, E. F. Lucas, and C. D. Wood, “High throughput synthesis and characterization of PNIPAM-based kinetic hydrate inhibitors,” Energy & Fuels, vol. 188, pp. 522–529, 2017. Available at: https://doi.org/10.1016/j.fuel.2016.10.075.

J. Park, K. C. Da Silveira, Q. Sheng, C. D. Wood, and Y. Seo, “Performance of PNIPAM-based Kinetic Hydrate Inhibitors for Nucleation and Growth of Natural Gas Hydrates,” Energy & Fuels, vol. 31, no. 3, pp. 2697–2704, 2017. Available at: https://doi.org/10.1021/acs.energyfuels.6b03369.

I. R. Ferreira Filho, K. C. Da Silveira, and A. J. Silva Neto, “Tecnologia de Hidrato de Gás: Modelagem Computacional para a Etapa de Crescimento do Hidrato,” VETOR - Revista De Ciências Exatas E Engenharias, vol. 31, no. 1, pp. 23–42, 2021. Available at: https://doi.org/10.14295/vetor.v31i1.13164.

C. M. Hansen, (2007), “Hansen Solubility Parameters: A User's Handbook”, 2nd ed. Boca Raton, United States: CRC Press, 2007. Available at: https://doi.org/10.1201/9781420006834.