Machine Learning Potentials for Alloys: A Detailed Workflow to Predict Phase Diagrams and Benchmark Accuracy

Abstract

High-entropy alloys (HEAs) have attracted increasing attention due to their unique structural and functional properties. In the study of HEAs, thermodynamic properties and phase stability play a crucial role, making phase diagram calculations significantly important. However, phase diagram calculations with conventional CALPHAD assessments based on experimental or ab-initio data can be expensive. With the emergence of machine-learning interatomic potentials (MLIPs), we have developed a program named PhaseForge, which integrates MLIPs into the Alloy Theoretic Automated Toolkit (ATAT) framework using our MLIP calculation library, MaterialsFramework, to enable efficient exploration of alloy phase diagrams. Moreover, our workflow can also serve as a benchmarking tool for evaluating the quality of different MLIPs.

References in corpus (24)

• DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics
• The Alloy Theoretic Automated Toolkit: A User Guide
• Multicomponent multisublattice alloys, nonconfigurational entropy and other additions to the Alloy Theoretic Automated Toolkit
• A Universal Graph Deep Learning Interatomic Potential for the Periodic Table
• Atomistic Line Graph Neural Network for Improved Materials Property Predictions
• DeePMD-kit v2: A software package for Deep Potential models
• On-the-fly Closed-loop Autonomous Materials Discovery via Bayesian Active Learning
• A foundation model for atomistic materials chemistry
• Scalable Parallel Algorithm for Graph Neural Network Interatomic Potentials in Molecular Dynamics Simulations
• Unified Graph Neural Network Force-field for the Periodic Table
• MatterSim: A Deep Learning Atomistic Model Across Elements, Temperatures and Pressures
• DeePMD-kit v3: A Multiple-Backend Framework for Machine Learning Potentials
• Autonomous synthesis of metastable materials
• Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models
• Accelerating CALPHAD-based Phase Diagram Predictions in Complex Alloys Using Universal Machine Learning Potentials: Opportunities and Challenges
• Free energy calculation of mechanically unstable but dynamically stabilized bcc titanium
• Orb: A Fast, Scalable Neural Network Potential
• GPTFF: A high-accuracy out-of-the-box universal AI force field for arbitrary inorganic materials
• Learning Smooth and Expressive Interatomic Potentials for Physical Property Prediction
• Orb-v3: atomistic simulation at scale
• CHGNet: Pretrained universal neural network potential for charge-informed atomistic modeling
• PET-MAD, a lightweight universal interatomic potential for advanced materials modeling
• A Materials Foundation Model via Hybrid Invariant-Equivariant Architectures
• AlphaNet: Scaling Up Local-frame-based Atomistic Interatomic Potential