Approaching Polymer Dynamics Combining Artificial Neural Networks and Elastically Collective Nonlinear Langevin Equation

This article belongs to the Special Issue Polymer Dynamics: Bulk and Nanoconfined Polymers.
The analysis of structural relaxation dynamics of polymers gives an insight into their mechanical properties, whose characterization is used to qualify a given material for its practical scope. The dynamics are usually expressed in terms of the temperature dependence of the relaxation time, which is only available through time-consuming experimental processes following polymer synthesis. However, it would be advantageous to estimate their dynamics before synthesizing them when designing new materials. In this work, we propose a combined approach of artificial neural networks and the elastically collective nonlinear Langevin equation (ECNLE) to estimate the temperature dependence of the main structural relaxation time of polymers based only on the knowledge of the chemical structure of the corresponding monomer.
We gratefully acknowledge the financial support from the Spanish Government “Ministerio de Ciencia e Innovación” (PID2019-104650GB-C21) and the Basque Government (IT1566-22). This research was also funded by the Vietnam National Foundation for Science and Technology Development (NAFOSTED) under grant number 103.01-2019.318. We also acknowledge the support of NVIDIA Corporation with the donation of the GPU used for this research.