Construction and Tuning of CALPHAD Models Using Machine-Learned Interatomic Potentials and Experimental Data: A Case Study of the Pt-W System

TL;DR

This paper presents PhaseForgePlus, an open-source workflow that combines machine-learned interatomic potentials with experimental data to efficiently generate and tune CALPHAD models, demonstrated on the Pt-W system.

Contribution

It introduces a novel, physically-informed CALPHAD modeling approach integrating machine learning potentials and experimental data, improving accuracy and efficiency.

Findings

Machine learning potentials can produce physically grounded Gibbs energy descriptions.

The workflow requires only slight adjustments for accurate phase diagrams.

Gradient-informed optimization effectively tunes model parameters.

Abstract

This work introduces PhaseForgePlus -- a computationally efficient, fully open-source workflow for physically-informed CALPHAD model generation and parameter fitting. Using the Pt-W system as an example, we show that the integration of Machine Learning Potentials into the Alloy Theoretic Automated Toolkit can produce physically grounded Gibbs energy descriptions requiring only slight adjustments to produce accurate phase diagrams. Employing the Jansson derivative method in the context of experimental observations, such adjustments can be efficiently and robustly determined through gradient-informed optimization procedures.