guest ::
| Home > Publications database > Benchmarking CHGNet Universal Machine Learning Interatomic Potential against DFT and EXAFS: The Case of Layered WS$_2$ and MoS$_2$ > print |
| Home > Publications database > Benchmarking CHGNet Universal Machine Learning Interatomic Potential against DFT and EXAFS: The Case of Layered WS$_2$ and MoS$_2$ > print |
| 001 | 637337 | ||
| 005 | 20250907054648.0 | ||
| 024 | 7 | _ | |a 10.1021/acs.jctc.5c00955 |2 doi |
| 024 | 7 | _ | |a 1549-9618 |2 ISSN |
| 024 | 7 | _ | |a 1549-9626 |2 ISSN |
| 024 | 7 | _ | |a 10.3204/PUBDB-2025-03829 |2 datacite_doi |
| 024 | 7 | _ | |a altmetric:180266053 |2 altmetric |
| 024 | 7 | _ | |a pmid:40801247 |2 pmid |
| 037 | _ | _ | |a PUBDB-2025-03829 |
| 041 | _ | _ | |a English |
| 082 | _ | _ | |a 610 |
| 100 | 1 | _ | |a Zguns, Pjotrs |0 P:(DE-H253)PIP1114016 |b 0 |e Corresponding author |
| 245 | _ | _ | |a Benchmarking CHGNet Universal Machine Learning Interatomic Potential against DFT and EXAFS: The Case of Layered WS$_2$ and MoS$_2$ |
| 260 | _ | _ | |a Washington, DC |c 2025 |b [Verlag nicht ermittelbar] |
| 336 | 7 | _ | |a article |2 DRIVER |
| 336 | 7 | _ | |a Output Types/Journal article |2 DataCite |
| 336 | 7 | _ | |a Journal Article |b journal |m journal |0 PUB:(DE-HGF)16 |s 1756886279_1637428 |2 PUB:(DE-HGF) |
| 336 | 7 | _ | |a ARTICLE |2 BibTeX |
| 336 | 7 | _ | |a JOURNAL_ARTICLE |2 ORCID |
| 336 | 7 | _ | |a Journal Article |0 0 |2 EndNote |
| 520 | _ | _ | |a Universal machine learning interatomic potentials (uMLIPs) deliver near \emph{ab initio} accuracy in energy and force calculations at a low computational cost, making them invaluable for materials modeling. Although uMLIPs are pretrained on vast \emph{ab initio} data sets, rigorous validation remains essential for their ongoing adoption. In this study, we use the CHGNet uMLIP to model thermal disorder in isostructural layered 2H$_c$-WS$_2$ and 2H$_c$-MoS$_2$, benchmarking it against \emph{ab initio} data and extended X-ray absorption fine structure (EXAFS) spectra, which capture thermal variations in bond lengths and angles. Fine-tuning CHGNet with compound-specific \emph{ab initio} (density functional theory (DFT)) data mitigates the systematic softening (i.e., force underestimation) typical of uMLIPs and simultaneously improves the alignment between molecular dynamics-derived and experimental EXAFS spectra. While fine-tuning with a single DFT structure is viable, using $\sim$100 structures is recommended to accurately reproduce EXAFS spectra and achieve DFT-level accuracy. Benchmarking the CHGNet uMLIP against both DFT and experimental EXAFS data reinforces confidence in its performance and provides guidance for determining optimal fine-tuning data set sizes. |
| 536 | _ | _ | |a 6G3 - PETRA III (DESY) (POF4-6G3) |0 G:(DE-HGF)POF4-6G3 |c POF4-6G3 |f POF IV |x 0 |
| 536 | _ | _ | |a FS-Proposal: I-20170739 EC (I-20170739-EC) |0 G:(DE-H253)I-20170739-EC |c I-20170739-EC |x 1 |
| 536 | _ | _ | |a CALIPSOplus - Convenient Access to Light Sources Open to Innovation, Science and to the World (730872) |0 G:(EU-Grant)730872 |c 730872 |f H2020-INFRAIA-2016-1 |x 2 |
| 588 | _ | _ | |a Dataset connected to CrossRef, Journals: bib-pubdb1.desy.de |
| 693 | _ | _ | |a PETRA III |f PETRA Beamline P65 |1 EXP:(DE-H253)PETRAIII-20150101 |0 EXP:(DE-H253)P-P65-20150101 |6 EXP:(DE-H253)P-P65-20150101 |x 0 |
| 700 | 1 | _ | |a Pudza, Inga |0 P:(DE-H253)PIP1029767 |b 1 |
| 700 | 1 | _ | |a Kuzmin, Aleksejs |0 P:(DE-H253)PIP1009042 |b 2 |e Corresponding author |
| 773 | _ | _ | |a 10.1021/acs.jctc.5c00955 |g Vol. 21, no. 16, p. 8142 - 8150 |0 PERI:(DE-600)2166976-4 |n 16 |p 8142 - 8150 |t Journal of chemical theory and computation |v 21 |y 2025 |x 1549-9618 |
| 856 | 4 | _ | |y Restricted |u https://bib-pubdb1.desy.de/record/637337/files/%C5%BEguns-et-al-2025.pdf |
| 856 | 4 | _ | |y Restricted |u https://bib-pubdb1.desy.de/record/637337/files/Supporting%20Information.pdf |
| 856 | 4 | _ | |y Published on 2025-08-13. Available in OpenAccess from 2026-08-13. |u https://bib-pubdb1.desy.de/record/637337/files/achemso-v19.pdf |
| 856 | 4 | _ | |y Restricted |x pdfa |u https://bib-pubdb1.desy.de/record/637337/files/%C5%BEguns-et-al-2025.pdf?subformat=pdfa |
| 856 | 4 | _ | |y Restricted |x pdfa |u https://bib-pubdb1.desy.de/record/637337/files/Supporting%20Information.pdf?subformat=pdfa |
| 856 | 4 | _ | |y Published on 2025-08-13. Available in OpenAccess from 2026-08-13. |x pdfa |u https://bib-pubdb1.desy.de/record/637337/files/achemso-v19.pdf?subformat=pdfa |
| 909 | C | O | |o oai:bib-pubdb1.desy.de:637337 |p openaire |p open_access |p driver |p VDB |p ec_fundedresources |p dnbdelivery |
| 910 | 1 | _ | |a External Institute |0 I:(DE-HGF)0 |k Extern |b 0 |6 P:(DE-H253)PIP1114016 |
| 910 | 1 | _ | |a Institute of Solid State Physics, University of Latvia |0 I:(DE-HGF)0 |b 0 |6 P:(DE-H253)PIP1114016 |
| 910 | 1 | _ | |a External Institute |0 I:(DE-HGF)0 |k Extern |b 1 |6 P:(DE-H253)PIP1029767 |
| 910 | 1 | _ | |a Institute of Solid State Physics, University of Latvia |0 I:(DE-HGF)0 |b 1 |6 P:(DE-H253)PIP1029767 |
| 910 | 1 | _ | |a External Institute |0 I:(DE-HGF)0 |k Extern |b 2 |6 P:(DE-H253)PIP1009042 |
| 910 | 1 | _ | |a Institute of Solid State Physics, University of Latvia |0 I:(DE-HGF)0 |b 2 |6 P:(DE-H253)PIP1009042 |
| 913 | 1 | _ | |a DE-HGF |b Forschungsbereich Materie |l Großgeräte: Materie |1 G:(DE-HGF)POF4-6G0 |0 G:(DE-HGF)POF4-6G3 |3 G:(DE-HGF)POF4 |2 G:(DE-HGF)POF4-600 |4 G:(DE-HGF)POF |v PETRA III (DESY) |x 0 |
| 914 | 1 | _ | |y 2025 |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)0200 |2 StatID |b SCOPUS |d 2024-12-12 |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)0300 |2 StatID |b Medline |d 2024-12-12 |
| 915 | _ | _ | |a Embargoed OpenAccess |0 StatID:(DE-HGF)0530 |2 StatID |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)1150 |2 StatID |b Current Contents - Physical, Chemical and Earth Sciences |d 2024-12-12 |
| 915 | _ | _ | |a IF >= 5 |0 StatID:(DE-HGF)9905 |2 StatID |b J CHEM THEORY COMPUT : 2022 |d 2024-12-12 |
| 915 | _ | _ | |a WoS |0 StatID:(DE-HGF)0113 |2 StatID |b Science Citation Index Expanded |d 2024-12-12 |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)0150 |2 StatID |b Web of Science Core Collection |d 2024-12-12 |
| 915 | _ | _ | |a JCR |0 StatID:(DE-HGF)0100 |2 StatID |b J CHEM THEORY COMPUT : 2022 |d 2024-12-12 |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)0160 |2 StatID |b Essential Science Indicators |d 2024-12-12 |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)0199 |2 StatID |b Clarivate Analytics Master Journal List |d 2024-12-12 |
| 920 | 1 | _ | |0 I:(DE-H253)HAS-User-20120731 |k DOOR ; HAS-User |l DOOR-User |x 0 |
| 980 | _ | _ | |a journal |
| 980 | _ | _ | |a VDB |
| 980 | _ | _ | |a UNRESTRICTED |
| 980 | _ | _ | |a I:(DE-H253)HAS-User-20120731 |
| 980 | 1 | _ | |a FullTexts |
| Library | Collection | CLSMajor | CLSMinor | Language | Author |
|---|