Application of Deep Learning to Polymer Solutions

Characterizations of the molecular interactions in polymer solutions is a fundamental problem of polymer physics. We developed a framework that utilizes a scaling relationship between solution correlation length ξ=lg^ν/B and number of monomers g per correlation volume for chains with monomer projection length l and a deep learning approach for evaluation of the B-parameters. The values of B_g and B_th corresponding to exponents ν = 0.588 and 0.5 uniquely describe a solvent quality for the polymer backbone. Applying a convolutional neural network (CNN), we obtained the set {B_g, B_th,} from solution specific viscosity, η_sp, as a function of concentration, c. The CNN was trained by generating a large number of sparse images representing the normalized specific viscosity η_sp/N_w(cl³)^1/(3ν-1) in solutions of chains with the weight-average degree of polymerization, N_w. This approach is capable of predicting the B-parameters with a mean absolute percentage error less than 6%. The calculated B-parameters were used to obtain the packing number, P_e and to predict the onset of entanglements in solutions of synthetic polymers and polysaccharides in water, organic solvents, and ionic liquids.