Discovery of new high-pressure phases – integrating high-throughput DFT simulations, graph neural networks, and active learning

Abstract Pressure-induced phase transformations in materials are of interest in a range of fields, including geophysics, planetary sciences, and shock physics. In addition, the high-pressure phases can exhibit desirable properties, eliciting interest in materials science. Despite its importance, the...

Full description

Saved in:
Bibliographic Details
Main Authors: Ching-Chien Chen, Robert J. Appleton, Saswat Mishra, Kat Nykiel, Alejandro Strachan
Format: Article
Language:English
Published: Nature Portfolio 2025-06-01
Series:npj Computational Materials
Online Access:https://doi.org/10.1038/s41524-025-01682-7
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849686031924723712
author Ching-Chien Chen
Robert J. Appleton
Saswat Mishra
Kat Nykiel
Alejandro Strachan
author_facet Ching-Chien Chen
Robert J. Appleton
Saswat Mishra
Kat Nykiel
Alejandro Strachan
author_sort Ching-Chien Chen
collection DOAJ
description Abstract Pressure-induced phase transformations in materials are of interest in a range of fields, including geophysics, planetary sciences, and shock physics. In addition, the high-pressure phases can exhibit desirable properties, eliciting interest in materials science. Despite its importance, the process of finding new high-pressure phases, either experimentally or computationally, is time-consuming and often driven by intuition. In this study, we use graph neural networks trained on density functional theory (DFT) equation of state data of 2258 materials and 7255 phases to identify potential phase transitions. The model is used to explore possible phase transitions in 7677 pairs of phases and promising cases are confirmed or denied via DFT calculations. Importantly, the new data is added to the training set, the model is refined, and a new cycle of discovery is started. Within 13 iterations, we discovered 28 new high-pressure stable phases (never synthesized through high-pressure routes nor reported in high-pressure computational works) and rediscovered 18 pressure-induced phase transitions. The results provide new insight and classification of pressure-induced phase transitions in terms of the ambient properties of the phases involved.
format Article
id doaj-art-a85fceaf3e7a483d8321e5a45b388e5c
institution DOAJ
issn 2057-3960
language English
publishDate 2025-06-01
publisher Nature Portfolio
record_format Article
series npj Computational Materials
spelling doaj-art-a85fceaf3e7a483d8321e5a45b388e5c2025-08-20T03:22:53ZengNature Portfolionpj Computational Materials2057-39602025-06-011111910.1038/s41524-025-01682-7Discovery of new high-pressure phases – integrating high-throughput DFT simulations, graph neural networks, and active learningChing-Chien Chen0Robert J. Appleton1Saswat Mishra2Kat Nykiel3Alejandro Strachan4School of Materials Engineering, Purdue UniversitySchool of Materials Engineering, Purdue UniversitySchool of Materials Engineering, Purdue UniversitySchool of Materials Engineering, Purdue UniversitySchool of Materials Engineering, Purdue UniversityAbstract Pressure-induced phase transformations in materials are of interest in a range of fields, including geophysics, planetary sciences, and shock physics. In addition, the high-pressure phases can exhibit desirable properties, eliciting interest in materials science. Despite its importance, the process of finding new high-pressure phases, either experimentally or computationally, is time-consuming and often driven by intuition. In this study, we use graph neural networks trained on density functional theory (DFT) equation of state data of 2258 materials and 7255 phases to identify potential phase transitions. The model is used to explore possible phase transitions in 7677 pairs of phases and promising cases are confirmed or denied via DFT calculations. Importantly, the new data is added to the training set, the model is refined, and a new cycle of discovery is started. Within 13 iterations, we discovered 28 new high-pressure stable phases (never synthesized through high-pressure routes nor reported in high-pressure computational works) and rediscovered 18 pressure-induced phase transitions. The results provide new insight and classification of pressure-induced phase transitions in terms of the ambient properties of the phases involved.https://doi.org/10.1038/s41524-025-01682-7
spellingShingle Ching-Chien Chen
Robert J. Appleton
Saswat Mishra
Kat Nykiel
Alejandro Strachan
Discovery of new high-pressure phases – integrating high-throughput DFT simulations, graph neural networks, and active learning
npj Computational Materials
title Discovery of new high-pressure phases – integrating high-throughput DFT simulations, graph neural networks, and active learning
title_full Discovery of new high-pressure phases – integrating high-throughput DFT simulations, graph neural networks, and active learning
title_fullStr Discovery of new high-pressure phases – integrating high-throughput DFT simulations, graph neural networks, and active learning
title_full_unstemmed Discovery of new high-pressure phases – integrating high-throughput DFT simulations, graph neural networks, and active learning
title_short Discovery of new high-pressure phases – integrating high-throughput DFT simulations, graph neural networks, and active learning
title_sort discovery of new high pressure phases integrating high throughput dft simulations graph neural networks and active learning
url https://doi.org/10.1038/s41524-025-01682-7
work_keys_str_mv AT chingchienchen discoveryofnewhighpressurephasesintegratinghighthroughputdftsimulationsgraphneuralnetworksandactivelearning
AT robertjappleton discoveryofnewhighpressurephasesintegratinghighthroughputdftsimulationsgraphneuralnetworksandactivelearning
AT saswatmishra discoveryofnewhighpressurephasesintegratinghighthroughputdftsimulationsgraphneuralnetworksandactivelearning
AT katnykiel discoveryofnewhighpressurephasesintegratinghighthroughputdftsimulationsgraphneuralnetworksandactivelearning
AT alejandrostrachan discoveryofnewhighpressurephasesintegratinghighthroughputdftsimulationsgraphneuralnetworksandactivelearning