Multi-Label Phase Diagram Prediction in Complex Alloys via Physics-Informed Graph Attention Networks

TL;DR

This paper introduces a physics-informed graph attention network that accurately predicts multi-phase equilibria in complex alloys, enabling rapid and physically consistent phase mapping for alloy design.

Contribution

It develops a novel graph attention network model incorporating thermodynamic constraints for multi-label phase prediction in complex alloys.

Findings

Achieves over 96% exact-set accuracy on dense in-domain grids.

Generalizes to unseen ternary and quaternary alloy sections with high accuracy.

Improves robustness and physical consistency through thermodynamic constraint enforcement.

Abstract

Accurate phase equilibria are foundational to alloy design because they encode the underlying thermodynamics governing stability, transformations, and processing windows. However, while the CALculation of Phase Diagrams (CALPHAD) provides a rigorous thermodynamic framework, exploring multicomponent composition-temperature space remains computationally expensive and is typically limited to sparse section. To enable rapid phase mapping and alloy screening, we propose a physics-informed graph attention network (GAT) that learns element-aware representations and couples them with thermodynamic constraints for multi-label phase-set prediction in the Ag-Bi-Cu-Sn alloy system. Using about 25,000 equilibrium states generated with pycalphad, each composition-temperature point is represented as a four-node element graph with atomic fractions and elemental descriptors as node features. The model combines graph attention, global pooling, and a multilayer perceptron to predict nine relevant phases. To improve physical consistency, we incorporate thermodynamic constraints, applied as training penalties or as an inference-time projection. Across six binary and three ternary subsystems, the baseline model achieves a macro-F1 score of 0.951 and 93.98% exact-set match, while physics-informed decoding improves robustness and raises exact-set accuracy to about 96% on dense in-domain grids. The surrogate also generalizes to an unseen ternary section with 99.32% exact-set accuracy and to a quaternary section at 700 {\deg}C with 91.78% accuracy. These results demonstrate that attention-based graph learning coupled with thermodynamic constraint enforcement provides an effective and physically consistent surrogate for high-resolution phase mapping and extrapolative alloy screening.