About this Abstract |
Meeting |
MS&T23: Materials Science & Technology
|
Symposium
|
Materials Processing and Fundamental Understanding Based on Machine Learning and Data Informatics
|
Presentation Title |
Optical and Photothermal Property Prediction of Gold Nanoparticle/polymer Hybrid Films Through Machine Learning and Finite Element Modeling |
Author(s) |
Yi Je Cho, Kathy Lu |
On-Site Speaker (Planned) |
Yi Je Cho |
Abstract Scope |
Different machine learning approaches have been adopted to predict novel material properties with the assistance of the corresponding large datasets. For new materials, however, collecting sufficient data points for model training is unavailable, which is the case for gold nanoparticle/polymer hybrid films. In this study, a material informatics framework was proposed for different gold nanoparticle/polymer hybrid films to predict microstructure/property relationships based on various geometrical configurations. A dataset of optical and photothermal properties was built initially using experimental results from the literature, which was combined with synthetic data points from numerical analysis using finite element modeling to satisfy the quality and quantity of the data size for establishing machine learning models. The effects of the number of highly ranked features obtained with correlation analysis on the model performance were evaluated. The proposed approach offers reliable predictions of optical and photothermal properties of different combinations of gold nanoparticles and polymer matrices. |