Machine-Learned Potentials for Polymer-Grafted Nanoparticles
Predicting how polymer-grafted nanoparticles interact is central to designing nanocomposite materials, but computing the potential of mean force (PMF) directly from molecular dynamics is expensive. I trained deep learning models on MD-simulated configurations to predict the effective PMF between two polymer-grafted nanoparticles, giving a fast, accurate surrogate for the underlying atomistic interactions.
This work is published as Deep Learning Potential of Mean Force Between Polymer Grafted Nanoparticles in Soft Matter (2022).
