Advancing Polymer Property Prediction through Machine Learning: A Focus on Melting Temperature and Molecular Parameter-based ANN Modeling
Keywords:
artificial neural network, fuzzy logic, polymer fingerprinting, simplified molecular input line entry systemAbstract
Polymeric materials play a pivotal role across numerous applications, driving innovation in various sectors. However, evaluating the properties of polymers traditionally involves costly and time-consuming experimental procedures. In this document, we explore the application of computational approaches, particularly machine learning (ML), in predicting crucial polymer properties, with a focus on the melting temperature (Tm). We introduce an Artificial Neural Network (ANN) model trained on molecular parameters to accurately predict Tm, demonstrating its effectiveness and affordability in comparison to conventional techniques. Additionally, we delve into the significance of polymer fingerprinting techniques, particularly Extended-Connectivity Fingerprints (ECFP), in encoding complex polymer structures for ML applications. Furthermore, we discuss feature engineering techniques such as Feature Selection and Feature Extraction, essential for refining input data and optimizing model performance. Finally, we detail the development of our ML model, including integration layers, optimization strategies, and hyperparameter tuning, emphasizing its potential for advancing polymer science and engineering. This comprehensive approach opens up new possibilities for material research and design while also advancing our understanding of polymer behavior.
Downloads
References
Audus, D. J., & de Pablo, J. J. (2017). ‘Polymer informatics: Opportunities and challenges’, ACS macro letters, Vol.6(10), pp.1078-1082.
Brindha, S., & Bhuvaneswari, S. (2021). ‘Repossession and recognition system: transliteration of antique Tamil Brahmi typescript’,Current Science, pp.654-665..
Chandrasekaran, A., Kamal, D., Batra, R., Kim, C., Chen, L., & Ramprasad, R. (2019). ‘Solving the electronic structure problem with machine learning’, npj Computational Materials, Vol.5(1), pp.22.
Chen, G., Shen, Z., Iyer, A., Ghumman, U. F., Tang, S., Bi, J., ... & Li, Y. (2020). ‘Machine-learning-assisted de novo design of organic molecules and polymers: opportunities and challenges’, Polymers, Vol.12(1), pp.163.
Dickson-Karn, N. M. (2017). ‘The use of ATR-FTIR in conjunction with thermal analysis methods for efficient identification of polymer samples: a qualitative multi-instrument instrumental analysis laboratory experiment’, Journal of Chemical Education, Vol.94(11), pp.1780-1783.
Doan Tran, H., Kim, C., Chen, L., Chandrasekaran, A., Batra, R., Venkatram, S., ... & Ramprasad, R. (2020). ‘Machine-learning predictions of polymer properties with Polymer Genome’, Journal of Applied Physics, Vol.128(17).
Haaf, F., Sanner, A., & Straub, F. J. P. J. (1985). ‘Polymers of N-vinylpyrrolidone: synthesis, characterization and use’,Polymer Journal, Vol.17(1), pp.143-152.
He, X., Yu, M., Han, J. P., Jiang, J., Jia, Q., Wang, Q., ... & Zhou, Y. N. (2023). ‘Leveraging Data-Driven strategy for Accelerating the Discovery of Polyesters with Targeted Glass Transition Temperatures’, Authorea Preprints.
Jain, A., Hautier, G., Ong, S. P., & Persson, K. (2016). ‘New opportunities for materials informatics: resources and data mining techniques for uncovering hidden relationships’, Journal of Materials Research, Vol.31(8), pp.977-994.
Jin, W., Barzilay, R., & Jaakkola, T. (2020, November). ‘Hierarchical generation of molecular graphs using structural motifs’, In International conference on machine learning (pp. 4839-4848). PMLR.
Lightstone, J. P., Chen, L., Kim, C., Batra, R., & Ramprasad, R. (2020). ‘Refractive index prediction models for polymers using machine learning’, Journal of Applied Physics, Vol.127(21).
Miccio, L. A., & Schwartz, G. A. (2020). ‘From chemical structure to quantitative polymer properties prediction through convolutional neural networks’, Polymer, Vo1.93, 122341.
Park, J. Y., & Paul, D. R. (1997). ‘Correlation and prediction of gas permeability in glassy polymer membrane materials via a modified free volume based group contribution method’, Journal of Membrane Science, Vol. 125(1), pp.23-39.
Robeson, L. M., Smith, C. D., & Langsam, M. (1997). ‘A group contribution approach to predict permeability and permselectivity of aromatic polymers’, Journal of membrane science, Vol.132(1), pp.33-54.
Tao, L., Varshney, V., & Li, Y. (2021). ‘Benchmarking machine learning models for polymer informatics: an example of glass transition temperature’, Journal of Chemical Information and Modeling, Vol.61(11), 5395-5413.
Targhi, E. K., Niri, M. E., & Zitha, P. L. (2023). ‘Design of Artificial Neural Network for predicting the reduction in permeability of porous media as a result of polymer gel injection’, Geoenergy Science and Engineering, Vol.227, pp.211925.
Wessling, M., Mulder, M. H. V., Bos, A., Van Der Linden, M., Bos, M., & Van Der Linden, W. E. (1994). ‘Modelling the permeability of polymers: a neural network approach’, Journal of membrane science, Vol.86(1-2), pp.193-198.
Yu, X. (2010). ‘Support vector machine-based QSPR for the prediction of glass transition temperatures of polymers’, Fibers and Polymers, Vol.11, pp.757-766.
Zhu, G., Kim, C., Chandrasekarn, A., Everett, J. D., Ramprasad, R., & Lively, R. P. (2020). ‘Polymer genome–based prediction of gas permeabilities in polymers’, Journal of Polymer Engineering, Vol.40(6), pp.451-457.
Zhu, Q., Sharma, V., Oganov, A. R., & Ramprasad, R. (2014). ‘Predicting polymeric crystal structures by evolutionary algorithms’, The Journal of chemical physics, Vol.141(15).
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
