Predicting the glass transition temperature of polymer based on generative adversarial networks and automated machine learning
Abstract Solution styrene‐butadiene rubber (SSBR) finds wide applications in high performance tire design and various other fields. This study aims to create a quantitative structure–property relationship (QSPR) model linking SSBR's glass transition temperature (Tg) to its structural properties...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley-VCH
2024-12-01
|
| Series: | Materials Genome Engineering Advances |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/mgea.78 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841543273292759040 |
|---|---|
| author | Zhanjie Liu Yixuan Huo Qionghai Chen Siqi Zhan Qian Li Qingsong Zhao Lihong Cui Jun Liu |
| author_facet | Zhanjie Liu Yixuan Huo Qionghai Chen Siqi Zhan Qian Li Qingsong Zhao Lihong Cui Jun Liu |
| author_sort | Zhanjie Liu |
| collection | DOAJ |
| description | Abstract Solution styrene‐butadiene rubber (SSBR) finds wide applications in high performance tire design and various other fields. This study aims to create a quantitative structure–property relationship (QSPR) model linking SSBR's glass transition temperature (Tg) to its structural properties. A dataset of 68 sets of data from published literature was compiled to develop a predictive machine learning model for SSBR's structural design and synthesis using small sample sizes. To tackle small sample sizes, a framework combining generative adversarial networks (GAN) and the Tree‐based Pipeline Optimization Tool (TPOT) is proposed. GAN is first used to generate additional samples that mirror the original dataset's distribution, expanding the dataset. The TPOT is then applied to automatically find the best model and parameter combinations, creating an optimal predictive model for the mixed dataset. Experimental results show that using GAN to enlarge the dataset and TPOT regression models significantly enhances model performance, increasing the R2 value from 0.745 to 0.985 and decreasing the RMSE from 7.676 to 1.569. The proposed GAN–TPOT framework demonstrates the potential of combining generative models with automated machine learning to improve materials science research. This combination accelerates research and development processes, enhances prediction and design accuracy, and introduces new perspectives and possibilities for the field. |
| format | Article |
| id | doaj-art-806880635127498492547ad79f41f704 |
| institution | Kabale University |
| issn | 2940-9489 2940-9497 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Wiley-VCH |
| record_format | Article |
| series | Materials Genome Engineering Advances |
| spelling | doaj-art-806880635127498492547ad79f41f7042025-01-13T15:15:31ZengWiley-VCHMaterials Genome Engineering Advances2940-94892940-94972024-12-0124n/an/a10.1002/mgea.78Predicting the glass transition temperature of polymer based on generative adversarial networks and automated machine learningZhanjie Liu0Yixuan Huo1Qionghai Chen2Siqi Zhan3Qian Li4Qingsong Zhao5Lihong Cui6Jun Liu7College of Mathematics and Physics Beijing University of Chemical Technology Beijing ChinaCollege of Mathematics and Physics Beijing University of Chemical Technology Beijing ChinaState Key Laboratory of Organic‐Inorganic Composites College of Materials Science and Engineering Beijing University of Chemical Technology Beijing ChinaState Key Laboratory of Organic‐Inorganic Composites College of Materials Science and Engineering Beijing University of Chemical Technology Beijing ChinaState Key Laboratory of Organic‐Inorganic Composites College of Materials Science and Engineering Beijing University of Chemical Technology Beijing ChinaNational Engineering Research Center for Synthesis of Novel Rubber and Plastic Materials Yanshan Branch of Beijing Research Institute of Chemical Industry China Petroleum & Chemical Company (Sinopec Corp.) Beijing ChinaCollege of Mathematics and Physics Beijing University of Chemical Technology Beijing ChinaState Key Laboratory of Organic‐Inorganic Composites College of Materials Science and Engineering Beijing University of Chemical Technology Beijing ChinaAbstract Solution styrene‐butadiene rubber (SSBR) finds wide applications in high performance tire design and various other fields. This study aims to create a quantitative structure–property relationship (QSPR) model linking SSBR's glass transition temperature (Tg) to its structural properties. A dataset of 68 sets of data from published literature was compiled to develop a predictive machine learning model for SSBR's structural design and synthesis using small sample sizes. To tackle small sample sizes, a framework combining generative adversarial networks (GAN) and the Tree‐based Pipeline Optimization Tool (TPOT) is proposed. GAN is first used to generate additional samples that mirror the original dataset's distribution, expanding the dataset. The TPOT is then applied to automatically find the best model and parameter combinations, creating an optimal predictive model for the mixed dataset. Experimental results show that using GAN to enlarge the dataset and TPOT regression models significantly enhances model performance, increasing the R2 value from 0.745 to 0.985 and decreasing the RMSE from 7.676 to 1.569. The proposed GAN–TPOT framework demonstrates the potential of combining generative models with automated machine learning to improve materials science research. This combination accelerates research and development processes, enhances prediction and design accuracy, and introduces new perspectives and possibilities for the field.https://doi.org/10.1002/mgea.78generative adversarial networksglass transition temperaturesolution styrene‐butadiene rubbertree‐based pipeline optimization toolvirtual sample generation |
| spellingShingle | Zhanjie Liu Yixuan Huo Qionghai Chen Siqi Zhan Qian Li Qingsong Zhao Lihong Cui Jun Liu Predicting the glass transition temperature of polymer based on generative adversarial networks and automated machine learning Materials Genome Engineering Advances generative adversarial networks glass transition temperature solution styrene‐butadiene rubber tree‐based pipeline optimization tool virtual sample generation |
| title | Predicting the glass transition temperature of polymer based on generative adversarial networks and automated machine learning |
| title_full | Predicting the glass transition temperature of polymer based on generative adversarial networks and automated machine learning |
| title_fullStr | Predicting the glass transition temperature of polymer based on generative adversarial networks and automated machine learning |
| title_full_unstemmed | Predicting the glass transition temperature of polymer based on generative adversarial networks and automated machine learning |
| title_short | Predicting the glass transition temperature of polymer based on generative adversarial networks and automated machine learning |
| title_sort | predicting the glass transition temperature of polymer based on generative adversarial networks and automated machine learning |
| topic | generative adversarial networks glass transition temperature solution styrene‐butadiene rubber tree‐based pipeline optimization tool virtual sample generation |
| url | https://doi.org/10.1002/mgea.78 |
| work_keys_str_mv | AT zhanjieliu predictingtheglasstransitiontemperatureofpolymerbasedongenerativeadversarialnetworksandautomatedmachinelearning AT yixuanhuo predictingtheglasstransitiontemperatureofpolymerbasedongenerativeadversarialnetworksandautomatedmachinelearning AT qionghaichen predictingtheglasstransitiontemperatureofpolymerbasedongenerativeadversarialnetworksandautomatedmachinelearning AT siqizhan predictingtheglasstransitiontemperatureofpolymerbasedongenerativeadversarialnetworksandautomatedmachinelearning AT qianli predictingtheglasstransitiontemperatureofpolymerbasedongenerativeadversarialnetworksandautomatedmachinelearning AT qingsongzhao predictingtheglasstransitiontemperatureofpolymerbasedongenerativeadversarialnetworksandautomatedmachinelearning AT lihongcui predictingtheglasstransitiontemperatureofpolymerbasedongenerativeadversarialnetworksandautomatedmachinelearning AT junliu predictingtheglasstransitiontemperatureofpolymerbasedongenerativeadversarialnetworksandautomatedmachinelearning |