Quantitative analysis of EXAFS data sets using deep reinforcement learning

Abstract Extended X-ray absorption fine structure (EXAFS) serves as a unique tool for accurately characterizing the local structural properties surrounding specific atoms. However, the quantitative analysis of EXAFS data demands significant effort. Artificial intelligence (AI) techniques, including...

Full description

Saved in:
Bibliographic Details
Main Authors: Eun-Suk Jeong, In-Hui Hwang, Sang-Wook Han
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-94376-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849731807235276800
author Eun-Suk Jeong
In-Hui Hwang
Sang-Wook Han
author_facet Eun-Suk Jeong
In-Hui Hwang
Sang-Wook Han
author_sort Eun-Suk Jeong
collection DOAJ
description Abstract Extended X-ray absorption fine structure (EXAFS) serves as a unique tool for accurately characterizing the local structural properties surrounding specific atoms. However, the quantitative analysis of EXAFS data demands significant effort. Artificial intelligence (AI) techniques, including deep reinforcement learning (RL) methods, present a promising avenue for the rapid and precise analysis of EXAFS data sets. Unlike other AI approaches, a deep RL method utilizing reward values does not necessitate a large volume of pre-prepared data sets for training the neural networks of the AI system. We explored the application of a deep RL method for the quantitative analysis of EXAFS data sets, utilizing the reciprocal of the R-factor of a fit as the reward metric. The deep RL method effectively determined the local structural properties of PtOx and Zn-O complexes by fitting a series of EXAFS data sets to theoretical EXAFS calculations without imposing specific constraints. Looking ahead, AI has the potential to independently analyze any EXAFS data, although there are still challenges to overcome.
format Article
id doaj-art-9ce4170bf46740abbb5a22ed832e61d3
institution DOAJ
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-9ce4170bf46740abbb5a22ed832e61d32025-08-20T03:08:25ZengNature PortfolioScientific Reports2045-23222025-05-0115111010.1038/s41598-025-94376-5Quantitative analysis of EXAFS data sets using deep reinforcement learningEun-Suk Jeong0In-Hui Hwang1Sang-Wook Han2Department of Physics Education, Institute of Fusion Science, and Institute of Science Education, Jeonbuk National UniversityPohang Accelerator Laboratory, POSTECHDepartment of Physics Education, Institute of Fusion Science, and Institute of Science Education, Jeonbuk National UniversityAbstract Extended X-ray absorption fine structure (EXAFS) serves as a unique tool for accurately characterizing the local structural properties surrounding specific atoms. However, the quantitative analysis of EXAFS data demands significant effort. Artificial intelligence (AI) techniques, including deep reinforcement learning (RL) methods, present a promising avenue for the rapid and precise analysis of EXAFS data sets. Unlike other AI approaches, a deep RL method utilizing reward values does not necessitate a large volume of pre-prepared data sets for training the neural networks of the AI system. We explored the application of a deep RL method for the quantitative analysis of EXAFS data sets, utilizing the reciprocal of the R-factor of a fit as the reward metric. The deep RL method effectively determined the local structural properties of PtOx and Zn-O complexes by fitting a series of EXAFS data sets to theoretical EXAFS calculations without imposing specific constraints. Looking ahead, AI has the potential to independently analyze any EXAFS data, although there are still challenges to overcome.https://doi.org/10.1038/s41598-025-94376-5Artificial intelligenceReinforcement learningExtended X-ray absorption fine structureMachine learningLocal structural property
spellingShingle Eun-Suk Jeong
In-Hui Hwang
Sang-Wook Han
Quantitative analysis of EXAFS data sets using deep reinforcement learning
Scientific Reports
Artificial intelligence
Reinforcement learning
Extended X-ray absorption fine structure
Machine learning
Local structural property
title Quantitative analysis of EXAFS data sets using deep reinforcement learning
title_full Quantitative analysis of EXAFS data sets using deep reinforcement learning
title_fullStr Quantitative analysis of EXAFS data sets using deep reinforcement learning
title_full_unstemmed Quantitative analysis of EXAFS data sets using deep reinforcement learning
title_short Quantitative analysis of EXAFS data sets using deep reinforcement learning
title_sort quantitative analysis of exafs data sets using deep reinforcement learning
topic Artificial intelligence
Reinforcement learning
Extended X-ray absorption fine structure
Machine learning
Local structural property
url https://doi.org/10.1038/s41598-025-94376-5
work_keys_str_mv AT eunsukjeong quantitativeanalysisofexafsdatasetsusingdeepreinforcementlearning
AT inhuihwang quantitativeanalysisofexafsdatasetsusingdeepreinforcementlearning
AT sangwookhan quantitativeanalysisofexafsdatasetsusingdeepreinforcementlearning