Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Phase Diagrams of Alloys and Their Hydrides via On-Lattice Graph Neural Networks and Limited Training Data

Journal Article · · Journal of Physical Chemistry Letters
 [1];  [1];  [2];  [1];  [1];  [1];  [1]
  1. Sandia National Lab. (SNL-CA), Livermore, CA (United States)
  2. Univ. of Nottingham (United Kingdom)
+ Show Author Affiliations
Efficient prediction of sampling-intensive thermodynamic properties is needed to evaluate material performance and permit high-throughput materials modeling for a diverse array of technology applications. To alleviate the prohibitive computational expense of high-throughput configurational sampling with density functional theory (DFT), surrogate modeling strategies like cluster expansion are many orders of magnitude more efficient but can be difficult to construct in systems with high compositional complexity. We therefore employ minimal-complexity graph neural network models that accurately predict and can even extrapolate to out-of-train distribution formation energies of DFT-relaxed structures from an ideal (unrelaxed) crystallographic representation. This enables the large-scale sampling necessary for various thermodynamic property predictions that may otherwise be intractable and can be achieved with small training data sets. Two exemplars, optimizing the thermodynamic stability of low-density high-entropy alloys and modulating the plateau pressure of hydrogen in metal alloys, demonstrate the power of this approach, which can be extended to a variety of materials discovery and modeling problems.
Research Organization:
Sandia National Laboratories (SNL-CA), Livermore, CA (United States)
Sponsoring Organization:
USDOE Laboratory Directed Research and Development (LDRD) Program; USDOE National Nuclear Security Administration (NNSA); USDOE Office of Energy Efficiency and Renewable Energy (EERE)
Grant/Contract Number:
NA0003525
OSTI ID:
2463035
Report Number(s):
SAND--2024-01797J
Journal Information:
Journal of Physical Chemistry Letters, Journal Name: Journal of Physical Chemistry Letters Journal Issue: 5 Vol. 15; ISSN 1948-7185
Publisher:
American Chemical SocietyCopyright Statement
Country of Publication:
United States
Language:
English

References (43)

Nanostructured High-Entropy Alloys with Multiple Principal Elements: Novel Alloy Design Concepts and Outcomes journal May 2004
Direct Prediction of Phonon Density of States With Euclidean Neural Networks journal March 2021
Thermodynamics of Hydrogen Solution and Hydride Formation in Binary Pd Alloys journal February 2007
Phase Stability of Low-Density, Multiprincipal Component Alloys Containing Aluminum, Magnesium, and Lithium journal July 2014
Generalized cluster description of multicomponent systems journal November 1984
High entropy alloys: A focused review of mechanical properties and deformation mechanisms journal April 2020
Design of multicomponent alloys with C14 laves phase structure for hydrogen storage assisted by computational thermodynamic journal November 2022
Python Materials Genomics (pymatgen): A robust, open-source python library for materials analysis journal February 2013
Graph neural networks predict energetic and mechanical properties for models of solid solution metal alloy phases journal May 2023
Thermodynamics of concentrated solid solution alloys journal October 2017
A cluster expansion model for predicting activation barrier of atomic processes journal June 2013
High-Entropy Alloys as a Discovery Platform for Electrocatalysis journal March 2019
Robust data-driven approach for predicting the configurational energy of high entropy alloys journal January 2020
Data-Driven Discovery and Synthesis of High Entropy Alloy Hydrides with Targeted Thermodynamic Stability journal April 2021
Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals journal April 2019
The Use of Cluster Expansions To Predict the Structures and Properties of Surfaces and Nanostructured Materials journal September 2018
SpookyNet: Learning force fields with electronic degrees of freedom and nonlocal effects journal December 2021
A map of single-phase high-entropy alloys journal May 2023
First-principles prediction of high-entropy-alloy stability journal November 2017
Machine-learning the configurational energy of multicomponent crystalline solids journal November 2018
Atomistic Line Graph Neural Network for improved materials property predictions journal November 2021
Cation-disordered rocksalt-type high-entropy cathodes for Li-ion batteries journal October 2020
Processing and Properties of High-Entropy Ultra-High Temperature Carbides journal June 2018
CHGNet as a pretrained universal neural network potential for charge-informed atomistic modelling journal September 2023
Defect graph neural networks for materials discovery in high-temperature clean-energy applications journal August 2023
Superior hydrogen storage in high entropy alloys journal November 2016
Computational design of novel MAX phase alloys as potential hydrogen storage media combining first principles and cluster expansion methods journal January 2023
Unified graph neural network force-field for the periodic table: solid state applications journal January 2023
Cluster expansion of electronic excitations: Application to fcc Ni–Al alloys journal June 2005
Commentary: The Materials Project: A materials genome approach to accelerating materials innovation journal July 2013
A Novel Low-Density, High-Hardness, High-entropy Alloy with Close-packed Single-phase Nanocrystalline Structures journal December 2014
Magnesium- and intermetallic alloys-based hydrides for energy storage: modelling, synthesis and properties journal June 2022
Effective cluster interactions from cluster-variation formalism. I journal September 1991
Cluster expansions of alloy energetics in ternary intermetallics journal April 1994
Bayesian approach to cluster expansions journal July 2009
Accuracy of density functional theory in predicting formation energies of ternary oxides from binary oxides and its implication on phase stability journal April 2012
Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties journal April 2018
Low-Pressure Electrochemical Synthesis of Complex High-Pressure Superconducting Superhydrides journal May 2022
Developing an improved crystal graph convolutional neural network framework for accelerated materials discovery journal June 2020
Predicting activation energies for vacancy-mediated diffusion in alloys using a transition-state cluster expansion journal January 2021
Tuning the critical Li intercalation concentrations for MoX2 ( X=S , Se, or Te) bilayer phase transitions journal August 2021
Thermodynamic limit for synthesis of metastable inorganic materials journal April 2018
An equivariant graph neural network for the elasticity tensors of all seven crystal systems text January 2023

Similar Records

Defect Diffusion Graph Neural Networks for Materials Discovery in High-Temperature Energy Applications
Journal Article · Tue Aug 26 00:00:00 EDT 2025 · Chemistry of Materials · OSTI ID:2589401
Defect Diffusion Graph Neural Networks for Materials Discovery in High-Temperature Energy Applications
Journal Article · Mon Aug 25 20:00:00 EDT 2025 · Chemistry of Materials · OSTI ID:2588486

Related Subjects

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY
alloys
computer simulations
density functional theory
energy
materials