Machine learning-based hydrogen recycling model for predicting rovibrational distributions of released molecular hydrogen on tungsten materials via molecular dynamics simulations

Understanding the hydrogen recycling process is crucial for comprehending the behavior of detached plasma in nuclear fusion devices. To achieve this, a molecular dynamics (MD) model is being developed to predict the distribution of translational energies and rovibrational states of hydrogen atoms an...

Full description

Saved in:
Bibliographic Details
Main Authors: Seiki Saito, Masato Iida, Hiroaki Nakamura, Keiji Sawada, Kazuo Hoshino, Masahiro Kobayashi, Masahiro Hasuo, Yuki Homma, Shohei Yamoto
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:Nuclear Materials and Energy
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2352179125000845
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849312972969607168
author Seiki Saito
Masato Iida
Hiroaki Nakamura
Keiji Sawada
Kazuo Hoshino
Masahiro Kobayashi
Masahiro Hasuo
Yuki Homma
Shohei Yamoto
author_facet Seiki Saito
Masato Iida
Hiroaki Nakamura
Keiji Sawada
Kazuo Hoshino
Masahiro Kobayashi
Masahiro Hasuo
Yuki Homma
Shohei Yamoto
author_sort Seiki Saito
collection DOAJ
description Understanding the hydrogen recycling process is crucial for comprehending the behavior of detached plasma in nuclear fusion devices. To achieve this, a molecular dynamics (MD) model is being developed to predict the distribution of translational energies and rovibrational states of hydrogen atoms and molecules released from the plasma-facing materials. Neutral transport simulations, utilizing distributions obtained from the MD model as boundary conditions, are also a powerful tool for analyzing the impact of recycled hydrogens on edge plasma. However, the MD model requires significant computational resources to obtain distributions under varying material and irradiation conditions such as material temperature and incident energy. Therefore, developing effective models that seamlessly integrate neutral transport simulation with hydrogen recycling models is crucial. Machine learning techniques are employed to develop predictive models capable of forecasting distributions of energies and rovibrational states of released hydrogen atoms and molecules. Furthermore, a model considering the incident energy distribution (shifted-Maxwellian) is developed by integrating the monochromatic distribution with the shifted-Maxwellian distribution.
format Article
id doaj-art-bfdd07a33d1248319eaa6335ddf3f192
institution Kabale University
issn 2352-1791
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series Nuclear Materials and Energy
spelling doaj-art-bfdd07a33d1248319eaa6335ddf3f1922025-08-20T03:52:55ZengElsevierNuclear Materials and Energy2352-17912025-06-014310194210.1016/j.nme.2025.101942Machine learning-based hydrogen recycling model for predicting rovibrational distributions of released molecular hydrogen on tungsten materials via molecular dynamics simulationsSeiki Saito0Masato Iida1Hiroaki Nakamura2Keiji Sawada3Kazuo Hoshino4Masahiro Kobayashi5Masahiro Hasuo6Yuki Homma7Shohei Yamoto8Graduate School of Science and Engineering, Yamagata University, Yonezawa, Yamagata 992-8510, Japan; Corresponding author.Graduate School of Science and Engineering, Yamagata University, Yonezawa, Yamagata 992-8510, JapanDepartment Research, National Institute for Fusion Science, Toki Gifu 509-5292, Japan; Graduate School of Engineering, Nagoya University, Nagoya, Aichi 464-8601, JapanGraduate School of Science and Technology, Shinshu University, Nagano 380-8553, JapanDepartment of Applied Physics and Physico-Informatics, Keio University, Yokohama, Kanagawa 223-8521, JapanDepartment Research, National Institute for Fusion Science, Toki Gifu 509-5292, JapanGraduate School of Engineering, Kyoto University, Kyoto, JapanNational Institutes for Quantum Science and Technology, Rokkasho, Aomori 039-3212, JapanNational Institutes for Quantum Science and Technology, Naka, Ibaraki 311-0193, JapanUnderstanding the hydrogen recycling process is crucial for comprehending the behavior of detached plasma in nuclear fusion devices. To achieve this, a molecular dynamics (MD) model is being developed to predict the distribution of translational energies and rovibrational states of hydrogen atoms and molecules released from the plasma-facing materials. Neutral transport simulations, utilizing distributions obtained from the MD model as boundary conditions, are also a powerful tool for analyzing the impact of recycled hydrogens on edge plasma. However, the MD model requires significant computational resources to obtain distributions under varying material and irradiation conditions such as material temperature and incident energy. Therefore, developing effective models that seamlessly integrate neutral transport simulation with hydrogen recycling models is crucial. Machine learning techniques are employed to develop predictive models capable of forecasting distributions of energies and rovibrational states of released hydrogen atoms and molecules. Furthermore, a model considering the incident energy distribution (shifted-Maxwellian) is developed by integrating the monochromatic distribution with the shifted-Maxwellian distribution.http://www.sciencedirect.com/science/article/pii/S2352179125000845Rovibrational statesMolecular hydrogenRecyclingMachine LearningMolecular Dynamics
spellingShingle Seiki Saito
Masato Iida
Hiroaki Nakamura
Keiji Sawada
Kazuo Hoshino
Masahiro Kobayashi
Masahiro Hasuo
Yuki Homma
Shohei Yamoto
Machine learning-based hydrogen recycling model for predicting rovibrational distributions of released molecular hydrogen on tungsten materials via molecular dynamics simulations
Nuclear Materials and Energy
Rovibrational states
Molecular hydrogen
Recycling
Machine Learning
Molecular Dynamics
title Machine learning-based hydrogen recycling model for predicting rovibrational distributions of released molecular hydrogen on tungsten materials via molecular dynamics simulations
title_full Machine learning-based hydrogen recycling model for predicting rovibrational distributions of released molecular hydrogen on tungsten materials via molecular dynamics simulations
title_fullStr Machine learning-based hydrogen recycling model for predicting rovibrational distributions of released molecular hydrogen on tungsten materials via molecular dynamics simulations
title_full_unstemmed Machine learning-based hydrogen recycling model for predicting rovibrational distributions of released molecular hydrogen on tungsten materials via molecular dynamics simulations
title_short Machine learning-based hydrogen recycling model for predicting rovibrational distributions of released molecular hydrogen on tungsten materials via molecular dynamics simulations
title_sort machine learning based hydrogen recycling model for predicting rovibrational distributions of released molecular hydrogen on tungsten materials via molecular dynamics simulations
topic Rovibrational states
Molecular hydrogen
Recycling
Machine Learning
Molecular Dynamics
url http://www.sciencedirect.com/science/article/pii/S2352179125000845
work_keys_str_mv AT seikisaito machinelearningbasedhydrogenrecyclingmodelforpredictingrovibrationaldistributionsofreleasedmolecularhydrogenontungstenmaterialsviamoleculardynamicssimulations
AT masatoiida machinelearningbasedhydrogenrecyclingmodelforpredictingrovibrationaldistributionsofreleasedmolecularhydrogenontungstenmaterialsviamoleculardynamicssimulations
AT hiroakinakamura machinelearningbasedhydrogenrecyclingmodelforpredictingrovibrationaldistributionsofreleasedmolecularhydrogenontungstenmaterialsviamoleculardynamicssimulations
AT keijisawada machinelearningbasedhydrogenrecyclingmodelforpredictingrovibrationaldistributionsofreleasedmolecularhydrogenontungstenmaterialsviamoleculardynamicssimulations
AT kazuohoshino machinelearningbasedhydrogenrecyclingmodelforpredictingrovibrationaldistributionsofreleasedmolecularhydrogenontungstenmaterialsviamoleculardynamicssimulations
AT masahirokobayashi machinelearningbasedhydrogenrecyclingmodelforpredictingrovibrationaldistributionsofreleasedmolecularhydrogenontungstenmaterialsviamoleculardynamicssimulations
AT masahirohasuo machinelearningbasedhydrogenrecyclingmodelforpredictingrovibrationaldistributionsofreleasedmolecularhydrogenontungstenmaterialsviamoleculardynamicssimulations
AT yukihomma machinelearningbasedhydrogenrecyclingmodelforpredictingrovibrationaldistributionsofreleasedmolecularhydrogenontungstenmaterialsviamoleculardynamicssimulations
AT shoheiyamoto machinelearningbasedhydrogenrecyclingmodelforpredictingrovibrationaldistributionsofreleasedmolecularhydrogenontungstenmaterialsviamoleculardynamicssimulations