We present mechanoChemML, a machine learning software library for computational materials physics. mechanoChemML is designed to function as an interface between platforms that are widely used for machine learning on one hand, and others for solution of partial differential equations-based models of physics. Of special interest here, and the focus of mechanoChemML, are applications to computational materials physics. These typically feature the coupled solution of material transport, reaction, phase transformation, mechanics, heat transport and electrochemistry. Central to the organization of mechanoChemML are machine learning workflows that arise in the context of data-driven computational materials physics. The mechanoChemML code structure is described, the machine learning workflows are laid out and their application to the solution of several problems in materials physics is outlined.
@article{arxiv.2112.04960,
title = {mechanoChemML: A software library for machine learning in computational materials physics},
author = {X. Zhang and G. H. Teichert and Z. Wang and M. Duschenes and S. Srivastava and E. Livingston and J. Holber and M. Faghih Shojaei and A. Sundararajan and K. Garikipati},
journal= {arXiv preprint arXiv:2112.04960},
year = {2022}
}