Machine Learning for First Principles Calculations of Material Properties for Ferromagnetic Materials

TL;DR

This paper develops machine learning surrogate models, specifically HydraGNN and linear mixing, to efficiently predict material properties in ferromagnetic materials, reducing reliance on costly DFT calculations during Monte Carlo simulations.

Contribution

The paper introduces and compares two ML surrogate models for DFT calculations in Monte Carlo simulations, highlighting HydraGNN's superior performance for magnetic alloys.

Findings

HydraGNN outperforms linear mixing in predictive accuracy.

Periodic retraining improves model reliability.

ML surrogates enable efficient property prediction in complex materials.

Abstract

The investigation of finite temperature properties using Monte-Carlo (MC) methods requires a large number of evaluations of the system's Hamiltonian to sample the phase space needed to obtain physical observables as function of temperature. DFT calculations can provide accurate evaluations of the energies, but they are too computationally expensive for routine simulations. To circumvent this problem, machine-learning (ML) based surrogate models have been developed and implemented on high-performance computing (HPC) architectures. In this paper, we describe two ML methods (linear mixing model and HydraGNN) as surrogates for first principles density functional theory (DFT) calculations with classical MC simulations. These two surrogate models are used to learn the dependence of target physical properties from complex compositions and interactions of their constituents. We present the predictive performance of these two surrogate models with respect to their complexity while avoiding the danger of overfitting the model. An important aspect of our approach is the periodic retraining with newly generated first principles data based on the progressive exploration of the system's phase space by the MC simulation. The numerical results show that HydraGNN model attains superior predictive performance compared to the linear mixing model for magnetic alloy materials.