Machine Learning Compatible CALPHAD-type Optimization from Phase Equilibria by Auto-differentiation

Abstract

To accurately determine phase boundaries and phase transitions, thermodynamic models that describe free energies of phases often have to be optimized based on experimentally observed phase equilibria. While different approaches exist for thermodynamic optimizations, these approaches are often implemented in ways that are not compatible with machine learning workflows that requires differentiable calculation of loss function. In this work, we derive a phase equilibrium loss function based on thermodynamic potentials that can be efficiently evaluated and enable gradient based optimization by auto-differentiation in the PyTorch package. By minimizing this loss function, general thermodynamic model parameters can be optimized with respect to experimental phase equilibria data. Using thermodynamic models in the CALculation of PHAse Diagram (CALPHAD) framework, We illustrate successful and efficient optimization in different systems including ternary ones with more than 100 parameters. As the loss function is defined independently of the details of the thermodynamic models, it can be used to optimize machine learning thermodynamic models in general. In particular, we demonstrate a top-down optimization of atomistic potential from target phase equilibria.