Nunzia Lauriello, Deekshith Naidu Ponnana, Zhan Ma, Karel Šindelka, Antonio Buffo, Gianluca Boccardo, Daniele Marchisio, Wenxiao Pan
{"title":"Interpretable machine-learning enhanced parametrization methodology for Pluronics-water mixtures in DPD simulations.","authors":"Nunzia Lauriello, Deekshith Naidu Ponnana, Zhan Ma, Karel Šindelka, Antonio Buffo, Gianluca Boccardo, Daniele Marchisio, Wenxiao Pan","doi":"10.1039/d5sm00291e","DOIUrl":null,"url":null,"abstract":"<p><p>Dissipative particle dynamics (DPD) is an incredibly powerful tool for simulating the behavior of structured fluids. However, identifying the appropriate model parameters to accurately replicate physical properties remains a challenge. This study showcases the benefits of integrating machine learning techniques into the top-down parameterization of Pluronic systems. The proposed workflow outlines a data-driven approach to accurately determine model parameters tailored to various Pluronic systems. Gaussian process regression (GPR)-based surrogate models effectively replicate the results of DPD simulations, delivering faster responses that streamline parameter optimization and enable the calibration of Pluronic systems against experimental data. Although DPD simulations provide valuable insight, their high computational cost, due to extensive simulations and post-processing, presents a challenge. The GPR-based surrogate model addresses this by modeling the relationships between input parameters and output properties. SHAP (SHapley additive exPlanations) analysis enhances model interpretability, providing deeper insights into the relationships and causal mechanisms between the input parameters and the predicted properties. The combination of GPR and SHAP analysis provides an interpretable machine learning approach, enabling a more efficient optimization process and reducing the need for exhaustive simulations. This work lays a foundation for generalizing the parameterization process across Pluronic systems and conditions, such as varying temperatures, by incorporating additional DPD model input parameters.</p>","PeriodicalId":103,"journal":{"name":"Soft Matter","volume":" ","pages":""},"PeriodicalIF":2.9000,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Soft Matter","FirstCategoryId":"92","ListUrlMain":"https://doi.org/10.1039/d5sm00291e","RegionNum":3,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"CHEMISTRY, PHYSICAL","Score":null,"Total":0}
引用次数: 0
Abstract
Dissipative particle dynamics (DPD) is an incredibly powerful tool for simulating the behavior of structured fluids. However, identifying the appropriate model parameters to accurately replicate physical properties remains a challenge. This study showcases the benefits of integrating machine learning techniques into the top-down parameterization of Pluronic systems. The proposed workflow outlines a data-driven approach to accurately determine model parameters tailored to various Pluronic systems. Gaussian process regression (GPR)-based surrogate models effectively replicate the results of DPD simulations, delivering faster responses that streamline parameter optimization and enable the calibration of Pluronic systems against experimental data. Although DPD simulations provide valuable insight, their high computational cost, due to extensive simulations and post-processing, presents a challenge. The GPR-based surrogate model addresses this by modeling the relationships between input parameters and output properties. SHAP (SHapley additive exPlanations) analysis enhances model interpretability, providing deeper insights into the relationships and causal mechanisms between the input parameters and the predicted properties. The combination of GPR and SHAP analysis provides an interpretable machine learning approach, enabling a more efficient optimization process and reducing the need for exhaustive simulations. This work lays a foundation for generalizing the parameterization process across Pluronic systems and conditions, such as varying temperatures, by incorporating additional DPD model input parameters.
期刊介绍:
Soft Matter is an international journal published by the Royal Society of Chemistry using Engineering-Materials Science: A Synthesis as its research focus. It publishes original research articles, review articles, and synthesis articles related to this field, reporting the latest discoveries in the relevant theoretical, practical, and applied disciplines in a timely manner, and aims to promote the rapid exchange of scientific information in this subject area. The journal is an open access journal. The journal is an open access journal and has not been placed on the alert list in the last three years.