Machine Learning Regression-Enhanced Property Prediction of Brush Particle Solids.
- 1Department of Mechanical Engineering, Carnegie Mellon University, 5000 Forbes Ave, Pittsburgh, Pennsylvania 15213, United States.
- 2Department of Materials Science and Engineering, Carnegie Mellon University, 5000 Forbes Ave, Pittsburgh, Pennsylvania 15213, United States.
- 3Materials & Manufacturing Directorate, Air Force Research Laboratory, 2977 Hobson Way, Wright-Patterson AFB, Ohio 45433, United States.
Abstract
The development of advanced hybrid materials such as polymer-grafted nanoparticles (aka "brush" or "hairy" particles) hinges on the ability to accurately predict suitable compositions to realize desired functionalities. Such systems are characterized by expensive synthesis, sparse data, and large parameter spaces that often render physics-based modeling or experimental exploration of structure-property relationships expensive and impractical. Regression models provide a versatile data-driven alternative to establish empirical structure-property relations. However, the implications of sparse data availability and method of training on the predictive capability of regression models outside of the respective range of training data is poorly understood. This work presents a comparative analysis of widely used linear and nonlinear models versus machine learning regression models to evaluate their ability to predict the elastic modulus of brush particle solids formed by poly-(methyl methacrylate) (PMMA) and polystyrene (PS) tethered silica nanoparticles with systematic variation of the degree of polymerization, dispersity, and grafting density. The methods investigated include k-nearest neighbors, multilayer perceptron, and XGBoost regression. The performance of each model is assessed on a consistent set of training and testing data. Within the experimental certainty, the k-nearest neighbors regressor and XGBoost were found to provide the most reliable property prediction. Combining data sets of disparate polymer systems (PMMA/PS) was found to increase the accuracy of prediction and to enable models to forecast previously reported unexpected behavior outside of the range of the original training data. This supports the use of trained regression models as capable exploratory tools to reveal structure-property relations for systems that are controlled by multiple parameters with unknown interactions.
Related
- Molecular Property Prediction with Well-Calibrated Uncertainties via Graph Neural Networks and Conformal Quantile Regression
- Topology-Guided Multi-Level Graph Learning: A Unified Framework for Molecular Property Prediction
- Beyond conventional sequence-based encoding: a generalized Machine Learning pipeline for oligonucleotide property prediction
- Machine learning-aided design of metallic mechanical metamaterials: fabrication-aware modelling, property prediction, and inverse design
- P2MAT: A machine learning (ML) driven software for Property Prediction of MATerial
BibTeX
@article{ferguson2026machine,
title = {{Machine Learning Regression-Enhanced Property Prediction of Brush Particle Solids.}},
author = {Kevin Ferguson and Ayesha Abdullah and Yuqi Zhao and Yunhao Xu and Michael R Bockstaller and Levent Burak Kara and Lawrence Drummy and Eric Harper and Andrew Gillman},
journal = {ACS applied polymer materials},
year = {2026},
month = oct,
doi = {10.1021/acsapm.6c03454},
url = {https://europepmc.org/article/MED/42948644},
note = {CC BY},
}
RIS
TY - JOUR
TI - Machine Learning Regression-Enhanced Property Prediction of Brush Particle Solids.
AU - Kevin Ferguson
AU - Ayesha Abdullah
AU - Yuqi Zhao
AU - Yunhao Xu
AU - Michael R Bockstaller
AU - Levent Burak Kara
AU - Lawrence Drummy
AU - Eric Harper
AU - Andrew Gillman
PY - 2026
DA - 2026/10/13
JO - ACS applied polymer materials
DO - 10.1021/acsapm.6c03454
UR - https://europepmc.org/article/MED/42948644
AB - The development of advanced hybrid materials such as polymer-grafted nanoparticles (aka "brush" or "hairy" particles) hinges on the ability to accurately predict suitable compositions to realize desired functionalities. Such systems are characterized by expensive synthesis, sparse data, and large parameter spaces that often render physics-based modeling or experimental exploration of structure-property relationships expensive and impractical. Regression models provide a versatile data-driven alternative to establish empirical structure-property relations. However, the implications of sparse data availability and method of training on the predictive capability of regression models outside of the respective range of training data is poorly understood. This work presents a comparative analysis of widely used linear and nonlinear models versus machine learning regression models to evaluate their ability to predict the elastic modulus of brush particle solids formed by poly-(methyl methacrylate) (PMMA) and polystyrene (PS) tethered silica nanoparticles with systematic variation of the degree of polymerization, dispersity, and grafting density. The methods investigated include k-nearest neighbors, multilayer perceptron, and XGBoost regression. The performance of each model is assessed on a consistent set of training and testing data. Within the experimental certainty, the k-nearest neighbors regressor and XGBoost were found to provide the most reliable property prediction. Combining data sets of disparate polymer systems (PMMA/PS) was found to increase the accuracy of prediction and to enable models to forecast previously reported unexpected behavior outside of the range of the original training data. This supports the use of trained regression models as capable exploratory tools to reveal structure-property relations for systems that are controlled by multiple parameters with unknown interactions.
SN - 2637-6105
ER -