mechanoChemML: A software library for machine learning in computational materials physics

TL;DR

MechanoChemML is a software library that integrates machine learning with computational materials physics, enabling data-driven modeling of complex coupled physical phenomena.

Contribution

It introduces a flexible software framework that bridges machine learning platforms with physics-based PDE solvers for materials science applications.

Findings

Demonstrates application to multiple materials physics problems.

Provides a structured workflow for data-driven modeling.

Facilitates integration of machine learning with PDE-based simulations.

Abstract

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.