Interpretable Prediction and Analysis of PVA Hydrogel Mechanical Behavior Using Machine Learning
Polyvinyl alcohol (PVA) hydrogels have emerged as versatile materials due to their exceptional biocompatibility and tunable mechanical properties, showing great promise for flexible sensors, smart wound dressings, and tissue engineering applications. However, rational design remains challenging due...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Gels |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2310-2861/11/7/550 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849733151262244864 |
|---|---|
| author | Liying Xu Siqi Liu Anqi Lin Zichuan Su Daxin Liang |
| author_facet | Liying Xu Siqi Liu Anqi Lin Zichuan Su Daxin Liang |
| author_sort | Liying Xu |
| collection | DOAJ |
| description | Polyvinyl alcohol (PVA) hydrogels have emerged as versatile materials due to their exceptional biocompatibility and tunable mechanical properties, showing great promise for flexible sensors, smart wound dressings, and tissue engineering applications. However, rational design remains challenging due to complex structure–property relationships involving multiple formulation parameters. This study presents an interpretable machine learning framework for predicting PVA hydrogel tensile strain properties with emphasis on mechanistic understanding, based on a comprehensive dataset of 350 data points collected from a systematic literature review. XGBoost demonstrated superior performance after Optuna-based optimization, achieving R<sup>2</sup> values of 0.964 for training and 0.801 for testing. SHAP analysis provided unprecedented mechanistic insights, revealing that PVA molecular weight dominates mechanical performance (SHAP importance: 84.94) through chain entanglement and crystallization mechanisms, followed by degree of hydrolysis (72.46) and cross-linking parameters. The interpretability analysis identified optimal parameter ranges and critical feature interactions, elucidating complex non-linear relationships and reinforcement mechanisms. By addressing the “black box” limitation of machine learning, this approach enables rational design strategies and mechanistic understanding for next-generation multifunctional hydrogels. |
| format | Article |
| id | doaj-art-ef475a15161341018fc23fda1314bce7 |
| institution | DOAJ |
| issn | 2310-2861 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Gels |
| spelling | doaj-art-ef475a15161341018fc23fda1314bce72025-08-20T03:08:06ZengMDPI AGGels2310-28612025-07-0111755010.3390/gels11070550Interpretable Prediction and Analysis of PVA Hydrogel Mechanical Behavior Using Machine LearningLiying Xu0Siqi Liu1Anqi Lin2Zichuan Su3Daxin Liang4School of Food Engineering, Harbin University, Harbin 150086, ChinaKey Laboratory of Bio-Based Material Science and Technology (Ministry of Education), Northeast Forestry University, Harbin 150040, ChinaKey Laboratory of Bio-Based Material Science and Technology (Ministry of Education), Northeast Forestry University, Harbin 150040, ChinaCollege of Chemistry and Chemical Engineering, China University of Petroleum (East China), Qingdao 266580, ChinaKey Laboratory of Bio-Based Material Science and Technology (Ministry of Education), Northeast Forestry University, Harbin 150040, ChinaPolyvinyl alcohol (PVA) hydrogels have emerged as versatile materials due to their exceptional biocompatibility and tunable mechanical properties, showing great promise for flexible sensors, smart wound dressings, and tissue engineering applications. However, rational design remains challenging due to complex structure–property relationships involving multiple formulation parameters. This study presents an interpretable machine learning framework for predicting PVA hydrogel tensile strain properties with emphasis on mechanistic understanding, based on a comprehensive dataset of 350 data points collected from a systematic literature review. XGBoost demonstrated superior performance after Optuna-based optimization, achieving R<sup>2</sup> values of 0.964 for training and 0.801 for testing. SHAP analysis provided unprecedented mechanistic insights, revealing that PVA molecular weight dominates mechanical performance (SHAP importance: 84.94) through chain entanglement and crystallization mechanisms, followed by degree of hydrolysis (72.46) and cross-linking parameters. The interpretability analysis identified optimal parameter ranges and critical feature interactions, elucidating complex non-linear relationships and reinforcement mechanisms. By addressing the “black box” limitation of machine learning, this approach enables rational design strategies and mechanistic understanding for next-generation multifunctional hydrogels.https://www.mdpi.com/2310-2861/11/7/550PVA hydrogelinterpretable machine learningSHAP analysisfeature importancehyperparameter optimization |
| spellingShingle | Liying Xu Siqi Liu Anqi Lin Zichuan Su Daxin Liang Interpretable Prediction and Analysis of PVA Hydrogel Mechanical Behavior Using Machine Learning Gels PVA hydrogel interpretable machine learning SHAP analysis feature importance hyperparameter optimization |
| title | Interpretable Prediction and Analysis of PVA Hydrogel Mechanical Behavior Using Machine Learning |
| title_full | Interpretable Prediction and Analysis of PVA Hydrogel Mechanical Behavior Using Machine Learning |
| title_fullStr | Interpretable Prediction and Analysis of PVA Hydrogel Mechanical Behavior Using Machine Learning |
| title_full_unstemmed | Interpretable Prediction and Analysis of PVA Hydrogel Mechanical Behavior Using Machine Learning |
| title_short | Interpretable Prediction and Analysis of PVA Hydrogel Mechanical Behavior Using Machine Learning |
| title_sort | interpretable prediction and analysis of pva hydrogel mechanical behavior using machine learning |
| topic | PVA hydrogel interpretable machine learning SHAP analysis feature importance hyperparameter optimization |
| url | https://www.mdpi.com/2310-2861/11/7/550 |
| work_keys_str_mv | AT liyingxu interpretablepredictionandanalysisofpvahydrogelmechanicalbehaviorusingmachinelearning AT siqiliu interpretablepredictionandanalysisofpvahydrogelmechanicalbehaviorusingmachinelearning AT anqilin interpretablepredictionandanalysisofpvahydrogelmechanicalbehaviorusingmachinelearning AT zichuansu interpretablepredictionandanalysisofpvahydrogelmechanicalbehaviorusingmachinelearning AT daxinliang interpretablepredictionandanalysisofpvahydrogelmechanicalbehaviorusingmachinelearning |