Machine Learning Isotropic g Values of Radical Polymers

Journal of Chemical Theory and Computation, vol. 20, pp. 2592–2604

Abstract

High Resolution Image Download MS PowerPoint Slide Methods for electronic structure computations, such as density functional theory (DFT), are routinely used for the calculation of spectroscopic parameters to establish and validate structure–parameter correlations. DFT calculations, however, are computationally expensive for large systems such as polymers. This work explores the machine learning (ML) of isotropic g values, g iso, obtained from electron paramagnetic resonance (EPR) experiments of an organic radical polymer. An ML model based on regression trees is trained on DFT-calculated g values of poly(2,2,6,6-tetramethylpiperidinyloxy-4-yl methacrylate) (PTMA) polymer structures extracted from different time frames of a molecular dynamics trajectory. The DFT-derived g values, g iso calc, for different radical densities of PTMA, are compared against experimentally derived g values obtained from in operando EPR measurements of a PTMA-based organic radical battery. The ML-predicted g iso values, g iso pred, were compared with g iso calc to evaluate the performance of the model. Mean deviations of g iso pred from g iso calc were found to be on the order of 0.0001. Furthermore, a performance evaluation on test structures from a separate MD trajectory indicated that the model is sensitive to the radical density and efficiently learns to predict g iso values even for radical densities that were not part of the training data set. Since our trained model can reproduce the changes in g iso along the MD trajectory and is sensitive to the extent of equilibration of the polymer structure, it is a promising alternative to computationally more expensive DFT methods, particularly for large systems that cannot be easily represented by a smaller model system.

Authors 5

1. Davis Thomas Daniel corresponding Aachen Institute of Technical and Macromolecular Chemistry

   Forschungszentrum Jülich · RWTH Aachen University

   Affiliation as printed

   Institute of Energy and Climate Research (IEK-9), Forschungszentrum Jülich GmbH, 52425 Jülich, Germany

   Institute of Technical and Macromolecular Chemistry, RWTH Aachen University, 52056 Aachen, Germany

2. Souvik Mitra

   University of Münster

   Affiliation as printed

   Institute of Physical Chemistry, University of Münster, 48149 Münster, Germany

3. Rüdiger‐A. Eichel Aachen Institute of Physical Chemistry

   Forschungszentrum Jülich · RWTH Aachen University

   Affiliation as printed

   Institute of Energy and Climate Research (IEK-9), Forschungszentrum Jülich GmbH, 52425 Jülich, Germany

   Institute of Physical Chemistry, RWTH Aachen University, Aachen 52056, Germany

4. Diddo Diddens

   Forschungszentrum Jülich · Helmholtz-Institute Münster

   Affiliation as printed

   Helmholtz Institute Münster (IEK-12), Forschungszentrum Jülich GmbH, 48149 Münster, Germany

5. Josef Granwehr Aachen Institute of Technical and Macromolecular Chemistry

   Forschungszentrum Jülich · RWTH Aachen University

   Affiliation as printed

   Institute of Energy and Climate Research (IEK-9), Forschungszentrum Jülich GmbH, 52425 Jülich, Germany

   Institute of Technical and Macromolecular Chemistry, RWTH Aachen University, 52056 Aachen, Germany