Physics-Informed Gaussian Process Classification for Constraint-Aware Alloy Design

2025-02-17

AI Summary

To address multi-constraint satisfaction in alloy design—particularly phase stability and continuous property threshold constraints—this work proposes a physics-informed Gaussian process classifier (PI-GPC). It embeds thermodynamic priors, such as CALPHAD-predicted phase diagrams, into the GPC mean function, enabling, for the first time, unified modeling of both continuous and discrete constraints. A physics-guided active learning strategy is further introduced to efficiently refine phase boundaries and screen compliant alloys. Evaluated on three representative tasks, PI-GPC achieves substantial improvements: 32% reduction in phase stability verification error, 50% fewer iterations for phase diagram correction, and a 3.8× acceleration in identifying qualified alloys—all validated experimentally via XRD. The core contribution is the first interpretable, generalizable, and sample-efficient physics-driven classification framework for alloy design.

Technology Category

• Machine Learning: Active Learning
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems

Abstract

Alloy design can be framed as a constraint-satisfaction problem. Building on previous methodologies, we propose equipping Gaussian Process Classifiers (GPCs) with physics-informed prior mean functions to model the boundaries of feasible design spaces. Through three case studies, we highlight the utility of informative priors for handling constraints on continuous and categorical properties. (1) Phase Stability: By incorporating CALPHAD predictions as priors for solid-solution phase stability, we enhance model validation using a publicly available XRD dataset. (2) Phase Stability Prediction Refinement: We demonstrate an in silico active learning approach to efficiently correct phase diagrams. (3) Continuous Property Thresholds: By embedding priors into continuous property models, we accelerate the discovery of alloys meeting specific property thresholds via active learning. In each case, integrating physics-based insights into the classification framework substantially improved model performance, demonstrating an efficient strategy for constraint-aware alloy design.

Problem

• Physics-informed GPCs for alloy design
• Handling alloy property constraints efficiently
• Enhancing phase stability prediction accuracy

Innovation

• Physics-informed Gaussian Process Classifiers
• CALPHAD predictions for phase stability
• Active learning for alloy discovery