Coarse-Grained Configurational Polymer Fingerprints for Property Prediction using Machine Learning
This work addresses polymer property prediction for materials science, but it appears incremental as it builds on existing fingerprinting methods with a new coarse-grained approach.
The authors tackled the problem of predicting polymer properties by developing a coarse-grained configurational fingerprint using a Bead-Spring-Model, which combines geometric and data-driven descriptors to learn mappings to properties like configuration probability at equilibrium.
In this work, we present a method to generate a configurational level fingerprint for polymers using the Bead-Spring-Model. Unlike some of the previous fingerprinting approaches that employ monomer-level information where atomistic descriptors are computed using quantum chemistry calculations, this approach incorporates configurational information from a coarse-grained model of a long polymer chain. The proposed approach may be advantageous for the study of behavior resulting from large molecular weights. To create this fingerprint, we make use of two kinds of descriptors. First, we calculate certain geometric descriptors like Re2, Rg2 etc. and label them as Calculated Descriptors. Second, we generate a set of data-driven descriptors using an unsupervised autoencoder model and call them Learnt Descriptors. Using a combination of both of them, we are able to learn mappings from the structure to various properties of the polymer chain by training ML models. We test our fingerprint to predict the probability of occurrence of a configuration at equilibrium, which is approximated by a simple linear relationship between the instantaneous internal energy and equilibrium average internal energy.