Machine Learning Potential for Serpentines

Abstract Serpentines are layered hydrous magnesium silicates (MgO⋅SiO2⋅H2O) formed through serpentinization, a geochemical process that significantly alters the physical property of the mantle. They are hard to investigate experimentally and computationally due to the complexity of natural serpentin...

Full description

Saved in:
Bibliographic Details
Main Authors: Hongjin Wang, Chenxing Luo, Renata M. Wentzcovitch
Format: Article
Language:English
Published: Wiley 2024-12-01
Series:Journal of Geophysical Research: Machine Learning and Computation
Online Access:https://doi.org/10.1029/2024JH000434
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849388063074025472
author Hongjin Wang
Chenxing Luo
Renata M. Wentzcovitch
author_facet Hongjin Wang
Chenxing Luo
Renata M. Wentzcovitch
author_sort Hongjin Wang
collection DOAJ
description Abstract Serpentines are layered hydrous magnesium silicates (MgO⋅SiO2⋅H2O) formed through serpentinization, a geochemical process that significantly alters the physical property of the mantle. They are hard to investigate experimentally and computationally due to the complexity of natural serpentine samples and the large number of atoms in the unit cell. We developed a machine learning (ML) potential for serpentine minerals based on density functional theory calculation with the r2SCAN meta‐GGA functional for molecular dynamics simulation. We illustrate the success of this ML potential model in reproducing the high‐temperature equation of states of several hydrous phases under the Earth's subduction zone conditions, including brucite, lizardite, and antigorite. In addition, we investigate the polysomes of antigorite with periodicity m = 13–24, which is believed to be all the naturally existent antigorite species. We found that antigorite with m larger than 21 appears more stable than lizardite at low temperatures. This ML potential can be further applied to investigate more complex antigorite superstructures with multiple coexisting periodic waves.
format Article
id doaj-art-377175fe936c41cca8ea2bea921951b8
institution Kabale University
issn 2993-5210
language English
publishDate 2024-12-01
publisher Wiley
record_format Article
series Journal of Geophysical Research: Machine Learning and Computation
spelling doaj-art-377175fe936c41cca8ea2bea921951b82025-08-20T03:42:25ZengWileyJournal of Geophysical Research: Machine Learning and Computation2993-52102024-12-0114n/an/a10.1029/2024JH000434Machine Learning Potential for SerpentinesHongjin Wang0Chenxing Luo1Renata M. Wentzcovitch2Department of Applied Physics and Applied Mathematics Columbia University New York NY USADepartment of Applied Physics and Applied Mathematics Columbia University New York NY USADepartment of Applied Physics and Applied Mathematics Columbia University New York NY USAAbstract Serpentines are layered hydrous magnesium silicates (MgO⋅SiO2⋅H2O) formed through serpentinization, a geochemical process that significantly alters the physical property of the mantle. They are hard to investigate experimentally and computationally due to the complexity of natural serpentine samples and the large number of atoms in the unit cell. We developed a machine learning (ML) potential for serpentine minerals based on density functional theory calculation with the r2SCAN meta‐GGA functional for molecular dynamics simulation. We illustrate the success of this ML potential model in reproducing the high‐temperature equation of states of several hydrous phases under the Earth's subduction zone conditions, including brucite, lizardite, and antigorite. In addition, we investigate the polysomes of antigorite with periodicity m = 13–24, which is believed to be all the naturally existent antigorite species. We found that antigorite with m larger than 21 appears more stable than lizardite at low temperatures. This ML potential can be further applied to investigate more complex antigorite superstructures with multiple coexisting periodic waves.https://doi.org/10.1029/2024JH000434
spellingShingle Hongjin Wang
Chenxing Luo
Renata M. Wentzcovitch
Machine Learning Potential for Serpentines
Journal of Geophysical Research: Machine Learning and Computation
title Machine Learning Potential for Serpentines
title_full Machine Learning Potential for Serpentines
title_fullStr Machine Learning Potential for Serpentines
title_full_unstemmed Machine Learning Potential for Serpentines
title_short Machine Learning Potential for Serpentines
title_sort machine learning potential for serpentines
url https://doi.org/10.1029/2024JH000434
work_keys_str_mv AT hongjinwang machinelearningpotentialforserpentines
AT chenxingluo machinelearningpotentialforserpentines
AT renatamwentzcovitch machinelearningpotentialforserpentines