Defect Diffusion Graph Neural Networks for Materials Discovery in High-Temperature Energy Applications

Way, Lauren; Spataru, Catalin Dan; Jones, Reese Edward; Trinkle, Dallas R.; Rowberg, Andrew J. E.; Varley, Joel B.; Wexler, Robert B.; Smyth, Christopher Michael; Douglas, Tyra Chenice; Bishop, Sean Robert; Fuller, Elliot James; McDaniel, Anthony Harrison; Lany, Stephan; Witman, Matthew David

doi:10.1021/acs.chemmater.5c00021

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

DOI:https://doi.org/10.1021/acs.chemmater.5c00021· OSTI ID:2588486

Way, Lauren ^[1]; Spataru, Catalin Dan ^[1]; ^[1]; Trinkle, Dallas R. ^[2]; ^[3]; ^[3]; ^[4]; ^[5]; ^[5]; ^[5]; ^[1]; McDaniel, Anthony Harrison ^[1]; ^[6]; ^[1]

Sandia National Laboratories (SNL-CA), Livermore, CA (United States)
Univ. of Illinois at Urbana-Champaign, IL (United States)
Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
Washington Univ., St. Louis, MO (United States)
Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
National Renewable Energy Laboratory (NREL), Golden, CO (United States)

Here, the migration of crystallographic defects dictates material properties and performance for a plethora of technological applications. Density functional theory (DFT)-based nudged elastic band (NEB) calculations are a powerful computational technique for predicting defect migration activation energy barriers, yet they become prohibitively expensive for high-throughput screening of defect diffusivities. Without introducing hand-crafted (i.e., chemistry- or structure-specific) descriptors, we propose a generalized deep learning approach to train surrogate models for NEB energies of vacancy migration by hybridizing graph neural networks with transformer encoders and simply using pristine host structures as input. With sufficient training data, computationally efficient and simultaneous inference of vacancy defect thermodynamics and migration activation energies can be obtained to compute temperature-dependent vacancy diffusivities and to down-select candidates for more thorough DFT analysis or experiments. Thus, as we specifically demonstrate for potential water-splitting materials, candidates with desired defect thermodynamics, kinetics, and host stability properties can be more rapidly targeted from open-source databases of experimentally validated or hypothetical materials.

View Accepted Manuscript (DOE)

Research Organization:: Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States); 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), Office of Sustainable Transportation. Hydrogen Fuel Cell Technologies Office (HFTO)

Grant/Contract Number:: AC36-08GO28308; EE0010733; NA0003525

OSTI ID:: 2588486

Alternate ID(s):: OSTI ID: 2589401
OSTI ID: 2588890

Report Number(s):: LLNL--JRNL-868661; SAND--2025-11829J

Journal Information:: Chemistry of Materials, Journal Name: Chemistry of Materials Journal Issue: 17 Vol. 37; ISSN 1520-5002; ISSN 0897-4756

Publisher:: American Chemical Society (ACS)Copyright Statement

Country of Publication:: United States

Language:: English

References (62)

An updated review and perspective on efficient hydrogen generation via solar thermal water splitting Tran, Justin T.; Warren, Kent J.; Wilson, Steven A. WIREs Energy and Environment, Vol. 13, Issue 4 https://doi.org/10.1002/wene.528	journal	July 2024
Diffusion in Oxides Martin, Manfred Diffusion in Condensed Matter https://doi.org/10.1007/3-540-30970-5_5	book	January 2005
Diffusion in Ceramics Pelleg, Joshua Solid Mechanics and Its Applications https://doi.org/10.1007/978-3-319-18437-1	book	January 2016
Diffusion in Solids: Fundamentals, Methods, Materials, Diffusion-Controlled Processes Mehrer, Helmut Springer Series in Solid-State Sciences https://doi.org/10.1007/978-3-540-71488-0	book	January 2007
Self-diffusion and impurity diffusion in oxides Freer, R. Journal of Materials Science, Vol. 15, Issue 4 https://doi.org/10.1007/BF00552089	journal	April 1980
Defects and transport properties of metal oxides Kofstad, Per Oxidation of Metals, Vol. 44, Issue 1-2 https://doi.org/10.1007/BF01046721	journal	August 1995
Diffusion of oxide ion vacancies in perovskite-type oxides Ishigaki, Takamasa; Yamauchi, Shigeru; Kishio, Kohji Journal of Solid State Chemistry, Vol. 73, Issue 1 https://doi.org/10.1016/0022-4596(88)90067-9	journal	March 1988
Vacancy formation energies and migration barriers in multi-principal element alloys Roy, Ankit; Singh, Prashant; Balasubramanian, Ganesh Acta Materialia, Vol. 226 https://doi.org/10.1016/j.actamat.2021.117611	journal	March 2022
Python Materials Genomics (pymatgen): A robust, open-source python library for materials analysis Ong, Shyue Ping; Richards, William Davidson; Jain, Anubhav Computational Materials Science, Vol. 68 https://doi.org/10.1016/j.commatsci.2012.10.028	journal	February 2013
Oxygen vacancy diffusion in bulk SrTiO3 from density functional theory calculations Zhang, Lipeng; Liu, Bin; Zhuang, Houlong Computational Materials Science, Vol. 118 https://doi.org/10.1016/j.commatsci.2016.02.041	journal	June 2016
A cluster expansion model for predicting activation barrier of atomic processes Rehman, Tafizur; Jaipal, M.; Chatterjee, Abhijit Journal of Computational Physics, Vol. 243 https://doi.org/10.1016/j.jcp.2013.03.005	journal	June 2013
Redox Defect Thermochemistry of FeAl ₂ O ₄ Hercynite in Water Splitting from First-Principles Methods Millican, Samantha L.; Clary, Jacob M.; Musgrave, Charles B. Chemistry of Materials, Vol. 34, Issue 2 https://doi.org/10.1021/acs.chemmater.1c01049	journal	January 2022
Impact of Sr-Containing Secondary Phases on Oxide Conductivity in Solid-Oxide Electrolyzer Cells Rowberg, Andrew J. E.; Slomski, Heather S.; Kim, Namhoon Chemistry of Materials, Vol. 36, Issue 13 https://doi.org/10.1021/acs.chemmater.4c00511	journal	June 2024
High-Throughput Computational Screening of Perovskites for Thermochemical Water Splitting Applications Emery, Antoine A.; Saal, James E.; Kirklin, Scott Chemistry of Materials, Vol. 28, Issue 16 https://doi.org/10.1021/acs.chemmater.6b01182	journal	July 2016
Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals Chen, Chi; Ye, Weike; Zuo, Yunxing Chemistry of Materials, Vol. 31, Issue 9 https://doi.org/10.1021/acs.chemmater.9b01294	journal	April 2019
Factors Governing Oxygen Vacancy Formation in Oxide Perovskites Wexler, Robert B.; Gautam, Gopalakrishnan Sai; Stechel, Ellen B. Journal of the American Chemical Society, Vol. 143, Issue 33 https://doi.org/10.1021/jacs.1c05570	journal	August 2021
Chemical Potential Analysis as an Alternative to the van’t Hoff Method: Hypothetical Limits of Solar Thermochemical Hydrogen Lany, Stephan Journal of the American Chemical Society, Vol. 146, Issue 20 https://doi.org/10.1021/jacs.4c02688	journal	May 2024
Giant onsite electronic entropy enhances the performance of ceria for water splitting Naghavi, S. Shahab; Emery, Antoine A.; Hansen, Heine A. Nature Communications, Vol. 8, Issue 1 https://doi.org/10.1038/s41467-017-00381-2	journal	August 2017
SpookyNet: Learning force fields with electronic degrees of freedom and nonlocal effects Unke, Oliver T.; Chmiela, Stefan; Gastegger, Michael Nature Communications, Vol. 12, Issue 1 https://doi.org/10.1038/s41467-021-27504-0	journal	December 2021
Atomistic Line Graph Neural Network for improved materials property predictions Choudhary, Kamal; DeCost, Brian npj Computational Materials, Vol. 7, Issue 1 https://doi.org/10.1038/s41524-021-00650-1	journal	November 2021
Calibration after bootstrap for accurate uncertainty quantification in regression models Palmer, Glenn; Du, Siqi; Politowicz, Alexander npj Computational Materials, Vol. 8, Issue 1 https://doi.org/10.1038/s41524-022-00794-8	journal	May 2022
Data-augmentation for graph neural network learning of the relaxed energies of unrelaxed structures Gibson, Jason; Hire, Ajinkya; Hennig, Richard G. npj Computational Materials, Vol. 8, Issue 1 https://doi.org/10.1038/s41524-022-00891-8	journal	September 2022
High-throughput calculations of charged point defect properties with semi-local density functional theory—performance benchmarks for materials screening applications Broberg, Danny; Bystrom, Kyle; Srivastava, Shivani npj Computational Materials, Vol. 9, Issue 1 https://doi.org/10.1038/s41524-023-01015-6	journal	May 2023
Topological graph-based analysis of solid-state ion migration Shen, Jimmy-Xuan; Li, Haoming Howard; Rutt, Ann npj Computational Materials, Vol. 9, Issue 1 https://doi.org/10.1038/s41524-023-01051-2	journal	June 2023
Machine-learning structural reconstructions for accelerated point defect calculations Mosquera-Lois, Irea; Kavanagh, Seán R.; Ganose, Alex M. npj Computational Materials, Vol. 10, Issue 1 https://doi.org/10.1038/s41524-024-01303-9	journal	June 2024
Computational discovery of fast interstitial oxygen conductors Meng, Jun; Sheikh, Md Sariful; Jacobs, Ryan Nature Materials, Vol. 23, Issue 9 https://doi.org/10.1038/s41563-024-01919-8	journal	June 2024
First principles study of oxygen vacancy activation energy barrier in zirconia-based resistive memory Hur, Ji-Hyun Scientific Reports, Vol. 10, Issue 1 https://doi.org/10.1038/s41598-020-62270-x	journal	March 2020
CHGNet as a pretrained universal neural network potential for charge-informed atomistic modelling Deng, Bowen; Zhong, Peichen; Jun, KyuJung Nature Machine Intelligence, Vol. 5, Issue 9 https://doi.org/10.1038/s42256-023-00716-3	journal	September 2023
Defect graph neural networks for materials discovery in high-temperature clean-energy applications Witman, Matthew D.; Goyal, Anuj; Ogitsu, Tadashi Nature Computational Science, Vol. 3, Issue 8 https://doi.org/10.1038/s43588-023-00495-2	journal	August 2023
The use of poly-cation oxides to lower the temperature of two-step thermochemical water splitting Zhai, Shang; Rojas, Jimmy; Ahlborg, Nadia Energy & Environmental Science, Vol. 11, Issue 8 https://doi.org/10.1039/C8EE00050F	journal	January 2018
BaCe 0.25 Mn 0.75 O 3−δ —a promising perovskite-type oxide for solar thermochemical hydrogen production R. Barcellos, Debora; Sanders, Michael D.; Tong, Jianhua Energy & Environmental Science, Vol. 11, Issue 11 https://doi.org/10.1039/C8EE01989D	journal	January 2018
Unified graph neural network force-field for the periodic table: solid state applications Choudhary, Kamal; DeCost, Brian; Major, Lily Digital Discovery, Vol. 2, Issue 2 https://doi.org/10.1039/D2DD00096B	journal	January 2023
Universal ion-transport descriptors and classes of inorganic solid-state electrolytes López, Cibrán; Emperador, Agustí; Saucedo, Edgardo Materials Horizons, Vol. 10, Issue 5 https://doi.org/10.1039/D2MH01516A	journal	January 2023
Multiple and nonlocal cation redox in Ca–Ce–Ti–Mn oxide perovskites for solar thermochemical applications Wexler, Robert B.; Sai Gautam, Gopalakrishnan; Bell, Robert T. Energy & Environmental Science, Vol. 16, Issue 6 https://doi.org/10.1039/D3EE00234A	journal	January 2023
MatFold: systematic insights into materials discovery models' performance through standardized cross-validation protocols Witman, Matthew D.; Schindler, Peter Digital Discovery, Vol. 4, Issue 3 https://doi.org/10.1039/D4DD00250D	journal	January 2025
Prediction of solid oxide fuel cell cathode activity with first-principles descriptors Lee, Yueh-Lin; Kleis, Jesper; Rossmeisl, Jan Energy & Environmental Science, Vol. 4, Issue 10 https://doi.org/10.1039/c1ee02032c	journal	January 2011
Sr- and Mn-doped LaAlO3−δ for solar thermochemical H2 and CO production McDaniel, Anthony H.; Miller, Elizabeth C.; Arifin, Darwin Energy & Environmental Science, Vol. 6, Issue 8 https://doi.org/10.1039/c3ee41372a	journal	January 2013
A climbing image nudged elastic band method for finding saddle points and minimum energy paths Henkelman, Graeme; Uberuaga, Blas P.; Jónsson, Hannes The Journal of Chemical Physics, Vol. 113, Issue 22, p. 9901-9904 https://doi.org/10.1063/1.1329672	journal	December 2000
Migration of oxygen vacancy in HfO2 and across the HfO2∕SiO2 interface: A first-principles investigation Capron, Nathalie; Broqvist, Peter; Pasquarello, Alfredo Applied Physics Letters, Vol. 91, Issue 19 https://doi.org/10.1063/1.2807282	journal	November 2007
A generalized solid-state nudged elastic band method Sheppard, Daniel; Xiao, Penghao; Chemelewski, William The Journal of Chemical Physics, Vol. 136, Issue 7 https://doi.org/10.1063/1.3684549	journal	February 2012
Commentary: The Materials Project: A materials genome approach to accelerating materials innovation Jain, Anubhav; Ong, Shyue Ping; Hautier, Geoffroy APL Materials, Vol. 1, Issue 1 https://doi.org/10.1063/1.4812323	journal	July 2013
Charge-dependent oxygen vacancy diffusion in Al ₂ O ₃ -based resistive-random-access-memories Yang, Moon Young; Kamiya, Katsumasa; Magyari-Köpe, Blanka Applied Physics Letters, Vol. 103, Issue 9 https://doi.org/10.1063/1.4819772	journal	August 2013
Communication: The electronic entropy of charged defect formation and its impact on thermochemical redox cycles Lany, Stephan The Journal of Chemical Physics, Vol. 148, Issue 7 https://doi.org/10.1063/1.5022176	journal	February 2018
Can a deep-learning model make fast predictions of vacancy formation in diverse materials? Choudhary, Kamal; Sumpter, Bobby G. AIP Advances, Vol. 13, Issue 9 https://doi.org/10.1063/5.0135382	journal	September 2023
Accelerating defect predictions in semiconductors using graph neural networks Rahman, Md Habibur; Gollapalli, Prince; Manganaris, Panayotis APL Machine Learning, Vol. 2, Issue 1 https://doi.org/10.1063/5.0176333	journal	March 2024
Simulating charged defects at database scale Shen, Jimmy-Xuan; Voss, Lars F.; Varley, Joel B. Journal of Applied Physics, Vol. 135, Issue 14 https://doi.org/10.1063/5.0203124	journal	April 2024
Theoretical modeling of defect diffusion in wide bandgap semiconductors Knausgård Hommedal, Ylva; Etzelmüller Bathen, Marianne; Mari Reinertsen, Vilde Journal of Applied Physics, Vol. 135, Issue 17 https://doi.org/10.1063/5.0205866	journal	May 2024
Diffusivity and derivatives for interstitial solutes: activation energy, volume, and elastodiffusion tensors Trinkle, Dallas R. Philosophical Magazine, Vol. 96, Issue 26 https://doi.org/10.1080/14786435.2016.1212175	journal	July 2016
Semiconducting transition metal oxides Lany, Stephan Journal of Physics: Condensed Matter, Vol. 27, Issue 28 https://doi.org/10.1088/0953-8984/27/28/283203	journal	June 2015
Predicting Thermochemical Equilibria with Interacting Defects: Sr1−xCexMnO3−δ Alloys for Water Splitting Goyal, Anuj; Sanders, Michael D.; O’Hayre, Ryan P. PRX Energy, Vol. 3, Issue 1 https://doi.org/10.1103/PRXEnergy.3.013008	journal	February 2024
First-principles theory of ionic diffusion with nondilute carriers Van der Ven, A.; Ceder, G.; Asta, M. Physical Review B, Vol. 64, Issue 18 https://doi.org/10.1103/PhysRevB.64.184307	journal	October 2001
Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties Xie, Tian; Grossman, Jeffrey C. Physical Review Letters, Vol. 120, Issue 14 https://doi.org/10.1103/PhysRevLett.120.145301	journal	April 2018
First Principles Analysis of the Stability and Diffusion of Oxygen Vacancies in Metal Oxides Carrasco, J.; Lopez, N.; Illas, F. Physical Review Letters, Vol. 93, Issue 22 https://doi.org/10.1103/PhysRevLett.93.225502	journal	November 2004
Developing an improved crystal graph convolutional neural network framework for accelerated materials discovery Park, Cheol Woo; Wolverton, Chris Physical Review Materials, Vol. 4, Issue 6 https://doi.org/10.1103/PhysRevMaterials.4.063801	journal	June 2020
Predicting activation energies for vacancy-mediated diffusion in alloys using a transition-state cluster expansion Li, Chenyang; Nilson, Thomas; Cao, Liang Physical Review Materials, Vol. 5, Issue 1 https://doi.org/10.1103/PhysRevMaterials.5.013803	journal	January 2021
Insights into oxygen vacancies from high-throughput first-principles calculations Kumagai, Yu; Tsunoda, Naoki; Takahashi, Akira Physical Review Materials, Vol. 5, Issue 12 https://doi.org/10.1103/PhysRevMaterials.5.123803	journal	December 2021
Explainable machine learning for hydrogen diffusion in metals and random binary alloys Lu, Grace M.; Witman, Matthew; Agarwal, Sapan Physical Review Materials, Vol. 7, Issue 10 https://doi.org/10.1103/PhysRevMaterials.7.105402	journal	October 2023
High-Flux Solar-Driven Thermochemical Dissociation of CO2 and H2O Using Nonstoichiometric Ceria Chueh, W. C.; Falter, C.; Abbott, M. Science, Vol. 330, Issue 6012 https://doi.org/10.1126/science.1197834	journal	December 2010
Transition Metal Oxides Rao, C. N. R. Annual Review of Physical Chemistry, Vol. 40, Issue 1 https://doi.org/10.1146/annurev.pc.40.100189.001451	journal	October 1989
doped: Python toolkit for robust and repeatable charged defect supercell calculations Kavanagh, Seán R.; Squires, Alexander G.; Nicolson, Adair Journal of Open Source Software, Vol. 9, Issue 96 https://doi.org/10.21105/joss.06433	journal	April 2024
Diffusion in Oxides Van Orman, J. A.; Crispin, K. L. Reviews in Mineralogy and Geochemistry, Vol. 72, Issue 1 https://doi.org/10.2138/rmg.2010.72.17	journal	January 2010
A foundation model for atomistic materials chemistry Batatia, Ilyes; Benner, Philipp; Chiang, Yuan arXiv https://doi.org/10.48550/arXiv.2401.00096	preprint	January 2024

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

First-principles investigation of the resistive switching energetics in monolayer MoS₂: insights into metal diffusion and adsorption

Journal Article · Mon Aug 18 20:00:00 EDT 2025 · npj 2D Materials and Applications · OSTI ID:2584486

Defect Diffusion Graph Neural Networks for Materials Discovery in High-Temperature Energy Applications

Citation Formats

References (62)

Similar Records

Related Subjects