High-temperature multi-element 2021 (HME21) dataset
HME21 is the atomic structure dataset aimed for the neural network potential development. It was created in the development of PFP, a universal neural network potential for material discovery [1]. It contains multiple elements in a single structure and was sampled through a high-temperature molecula...
Gespeichert in:
Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , , |
---|---|
Format: | Dataset |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | |
container_volume | |
creator | Takamoto, So Shinagawa, Chikashi Motoki, Daisuke Nakago, Kosuke Li, Wenwen Kurata, Iori Watanabe, Taku Yayama, Yoshihiro Iriguchi, Hiroki Asano, Yusuke Onodera, Tasuku Ishii, Takafumi Kudo, Takao Ono, Hideki Sawada, Ryohto Ishitani, Ryuichiro Ong, Marc Yamaguchi, Taiki Kataoka, Toshiki Hayashi, Akihide Charoenphakdee, Nontawat Ibuka, Takeshi |
description | HME21 is the atomic structure dataset aimed for the neural network potential development. It was created in the development of PFP, a universal neural network potential for material discovery [1]. It contains multiple elements in a single structure and was sampled through a high-temperature molecular dynamics simulation. There are a total of 37 elements in the HME21 dataset, i.e., H, Li, C, N, O, F, Na, Mg, Al, Si, P, S, Cl, K, Ca, Sc, Ti, V, Cr, Mn, Fe, Co, Ni, Cu, Zn, Mo, Ru, Rh, Pd, Ag, In, Sn, Ba, Ir, Pt, Au, and Pb. They are calculated by Spin-polarized DFT calculations using PBE exchange-correlation functional implemented in VASP [2] version 5.4.4. All structures are under periodic boundary conditions. For the details of DFT calculation conditions and structure sampling method, please see the reference [1]. Please cite the reference [1] if you use this dataset. Files HME21 consists of three files with extxyz format: train.xyz: 19956 structures valid.xyz: 2498 structures test.xyz 2495 structures The structures were randomly split into training, validation, and test sub-datasets at a ratio of 8:1:1. They are used as training, validation, and test dataset for the benchmark of neural network potentials [1]. The target values are energy and atomic forces. The energy is shifted such that the energy of a single atom located in a vacuum becomes zero. The length is in angstroms (10^−10 m), and the energy is in electronvolts (eV). For supplementary, vasp_shift_energies.json which corresponds to the reference energy of single atom for each element is also included. |
doi_str_mv | 10.6084/m9.figshare.19658538 |
format | Dataset |
fullrecord | <record><control><sourceid>datacite_PQ8</sourceid><recordid>TN_cdi_datacite_primary_10_6084_m9_figshare_19658538</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>10_6084_m9_figshare_19658538</sourcerecordid><originalsourceid>FETCH-LOGICAL-d918-b5a8543a7d83634e8cbaf8293be60be4d5fc883332e1ab47491d4a52d5e3f3c3</originalsourceid><addsrcrecordid>eNo1zzFPAyEYxnEWB1P9Bg436sAJvHCF0TTVM2njoDt5OV5aksM0HB389qbRTs_2f_Jj7EGKfhBWPxfXp3xYjlipl24w1oC9ZTDmw5E3Kieq2M6VunKeW-Y0U6Hv1imhZPc47rdKPnURGy7U7thNwnmh-_9dsc_X7ddm5LuPt_fNy45HJy0PBq3RgOtoYQBNdgqYrHIQaBCBdDRpshYAFEkMeq2djBqNioYgwQQrpv-ql9cpN_KnmgvWHy-Fv4h8cf4q8lcR_AKHSEXL</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>dataset</recordtype></control><display><type>dataset</type><title>High-temperature multi-element 2021 (HME21) dataset</title><source>DataCite</source><creator>Takamoto, So ; Shinagawa, Chikashi ; Motoki, Daisuke ; Nakago, Kosuke ; Li, Wenwen ; Kurata, Iori ; Watanabe, Taku ; Yayama, Yoshihiro ; Iriguchi, Hiroki ; Asano, Yusuke ; Onodera, Tasuku ; Ishii, Takafumi ; Kudo, Takao ; Ono, Hideki ; Sawada, Ryohto ; Ishitani, Ryuichiro ; Ong, Marc ; Yamaguchi, Taiki ; Kataoka, Toshiki ; Hayashi, Akihide ; Charoenphakdee, Nontawat ; Ibuka, Takeshi</creator><creatorcontrib>Takamoto, So ; Shinagawa, Chikashi ; Motoki, Daisuke ; Nakago, Kosuke ; Li, Wenwen ; Kurata, Iori ; Watanabe, Taku ; Yayama, Yoshihiro ; Iriguchi, Hiroki ; Asano, Yusuke ; Onodera, Tasuku ; Ishii, Takafumi ; Kudo, Takao ; Ono, Hideki ; Sawada, Ryohto ; Ishitani, Ryuichiro ; Ong, Marc ; Yamaguchi, Taiki ; Kataoka, Toshiki ; Hayashi, Akihide ; Charoenphakdee, Nontawat ; Ibuka, Takeshi</creatorcontrib><description>HME21 is the atomic structure dataset aimed for the neural network potential development. It was created in the development of PFP, a universal neural network potential for material discovery [1]. It contains multiple elements in a single structure and was sampled through a high-temperature molecular dynamics simulation. There are a total of 37 elements in the HME21 dataset, i.e., H, Li, C, N, O, F, Na, Mg, Al, Si, P, S, Cl, K, Ca, Sc, Ti, V, Cr, Mn, Fe, Co, Ni, Cu, Zn, Mo, Ru, Rh, Pd, Ag, In, Sn, Ba, Ir, Pt, Au, and Pb. They are calculated by Spin-polarized DFT calculations using PBE exchange-correlation functional implemented in VASP [2] version 5.4.4. All structures are under periodic boundary conditions. For the details of DFT calculation conditions and structure sampling method, please see the reference [1]. Please cite the reference [1] if you use this dataset. Files HME21 consists of three files with extxyz format: train.xyz: 19956 structures valid.xyz: 2498 structures test.xyz 2495 structures The structures were randomly split into training, validation, and test sub-datasets at a ratio of 8:1:1. They are used as training, validation, and test dataset for the benchmark of neural network potentials [1]. The target values are energy and atomic forces. The energy is shifted such that the energy of a single atom located in a vacuum becomes zero. The length is in angstroms (10^−10 m), and the energy is in electronvolts (eV). For supplementary, vasp_shift_energies.json which corresponds to the reference energy of single atom for each element is also included.</description><identifier>DOI: 10.6084/m9.figshare.19658538</identifier><language>eng</language><publisher>figshare</publisher><subject>Computational Chemistry</subject><creationdate>2022</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,1894</link.rule.ids><linktorsrc>$$Uhttps://commons.datacite.org/doi.org/10.6084/m9.figshare.19658538$$EView_record_in_DataCite.org$$FView_record_in_$$GDataCite.org$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Takamoto, So</creatorcontrib><creatorcontrib>Shinagawa, Chikashi</creatorcontrib><creatorcontrib>Motoki, Daisuke</creatorcontrib><creatorcontrib>Nakago, Kosuke</creatorcontrib><creatorcontrib>Li, Wenwen</creatorcontrib><creatorcontrib>Kurata, Iori</creatorcontrib><creatorcontrib>Watanabe, Taku</creatorcontrib><creatorcontrib>Yayama, Yoshihiro</creatorcontrib><creatorcontrib>Iriguchi, Hiroki</creatorcontrib><creatorcontrib>Asano, Yusuke</creatorcontrib><creatorcontrib>Onodera, Tasuku</creatorcontrib><creatorcontrib>Ishii, Takafumi</creatorcontrib><creatorcontrib>Kudo, Takao</creatorcontrib><creatorcontrib>Ono, Hideki</creatorcontrib><creatorcontrib>Sawada, Ryohto</creatorcontrib><creatorcontrib>Ishitani, Ryuichiro</creatorcontrib><creatorcontrib>Ong, Marc</creatorcontrib><creatorcontrib>Yamaguchi, Taiki</creatorcontrib><creatorcontrib>Kataoka, Toshiki</creatorcontrib><creatorcontrib>Hayashi, Akihide</creatorcontrib><creatorcontrib>Charoenphakdee, Nontawat</creatorcontrib><creatorcontrib>Ibuka, Takeshi</creatorcontrib><title>High-temperature multi-element 2021 (HME21) dataset</title><description>HME21 is the atomic structure dataset aimed for the neural network potential development. It was created in the development of PFP, a universal neural network potential for material discovery [1]. It contains multiple elements in a single structure and was sampled through a high-temperature molecular dynamics simulation. There are a total of 37 elements in the HME21 dataset, i.e., H, Li, C, N, O, F, Na, Mg, Al, Si, P, S, Cl, K, Ca, Sc, Ti, V, Cr, Mn, Fe, Co, Ni, Cu, Zn, Mo, Ru, Rh, Pd, Ag, In, Sn, Ba, Ir, Pt, Au, and Pb. They are calculated by Spin-polarized DFT calculations using PBE exchange-correlation functional implemented in VASP [2] version 5.4.4. All structures are under periodic boundary conditions. For the details of DFT calculation conditions and structure sampling method, please see the reference [1]. Please cite the reference [1] if you use this dataset. Files HME21 consists of three files with extxyz format: train.xyz: 19956 structures valid.xyz: 2498 structures test.xyz 2495 structures The structures were randomly split into training, validation, and test sub-datasets at a ratio of 8:1:1. They are used as training, validation, and test dataset for the benchmark of neural network potentials [1]. The target values are energy and atomic forces. The energy is shifted such that the energy of a single atom located in a vacuum becomes zero. The length is in angstroms (10^−10 m), and the energy is in electronvolts (eV). For supplementary, vasp_shift_energies.json which corresponds to the reference energy of single atom for each element is also included.</description><subject>Computational Chemistry</subject><fulltext>true</fulltext><rsrctype>dataset</rsrctype><creationdate>2022</creationdate><recordtype>dataset</recordtype><sourceid>PQ8</sourceid><recordid>eNo1zzFPAyEYxnEWB1P9Bg436sAJvHCF0TTVM2njoDt5OV5aksM0HB389qbRTs_2f_Jj7EGKfhBWPxfXp3xYjlipl24w1oC9ZTDmw5E3Kieq2M6VunKeW-Y0U6Hv1imhZPc47rdKPnURGy7U7thNwnmh-_9dsc_X7ddm5LuPt_fNy45HJy0PBq3RgOtoYQBNdgqYrHIQaBCBdDRpshYAFEkMeq2djBqNioYgwQQrpv-ql9cpN_KnmgvWHy-Fv4h8cf4q8lcR_AKHSEXL</recordid><startdate>20220428</startdate><enddate>20220428</enddate><creator>Takamoto, So</creator><creator>Shinagawa, Chikashi</creator><creator>Motoki, Daisuke</creator><creator>Nakago, Kosuke</creator><creator>Li, Wenwen</creator><creator>Kurata, Iori</creator><creator>Watanabe, Taku</creator><creator>Yayama, Yoshihiro</creator><creator>Iriguchi, Hiroki</creator><creator>Asano, Yusuke</creator><creator>Onodera, Tasuku</creator><creator>Ishii, Takafumi</creator><creator>Kudo, Takao</creator><creator>Ono, Hideki</creator><creator>Sawada, Ryohto</creator><creator>Ishitani, Ryuichiro</creator><creator>Ong, Marc</creator><creator>Yamaguchi, Taiki</creator><creator>Kataoka, Toshiki</creator><creator>Hayashi, Akihide</creator><creator>Charoenphakdee, Nontawat</creator><creator>Ibuka, Takeshi</creator><general>figshare</general><scope>DYCCY</scope><scope>PQ8</scope></search><sort><creationdate>20220428</creationdate><title>High-temperature multi-element 2021 (HME21) dataset</title><author>Takamoto, So ; Shinagawa, Chikashi ; Motoki, Daisuke ; Nakago, Kosuke ; Li, Wenwen ; Kurata, Iori ; Watanabe, Taku ; Yayama, Yoshihiro ; Iriguchi, Hiroki ; Asano, Yusuke ; Onodera, Tasuku ; Ishii, Takafumi ; Kudo, Takao ; Ono, Hideki ; Sawada, Ryohto ; Ishitani, Ryuichiro ; Ong, Marc ; Yamaguchi, Taiki ; Kataoka, Toshiki ; Hayashi, Akihide ; Charoenphakdee, Nontawat ; Ibuka, Takeshi</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-d918-b5a8543a7d83634e8cbaf8293be60be4d5fc883332e1ab47491d4a52d5e3f3c3</frbrgroupid><rsrctype>datasets</rsrctype><prefilter>datasets</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computational Chemistry</topic><toplevel>online_resources</toplevel><creatorcontrib>Takamoto, So</creatorcontrib><creatorcontrib>Shinagawa, Chikashi</creatorcontrib><creatorcontrib>Motoki, Daisuke</creatorcontrib><creatorcontrib>Nakago, Kosuke</creatorcontrib><creatorcontrib>Li, Wenwen</creatorcontrib><creatorcontrib>Kurata, Iori</creatorcontrib><creatorcontrib>Watanabe, Taku</creatorcontrib><creatorcontrib>Yayama, Yoshihiro</creatorcontrib><creatorcontrib>Iriguchi, Hiroki</creatorcontrib><creatorcontrib>Asano, Yusuke</creatorcontrib><creatorcontrib>Onodera, Tasuku</creatorcontrib><creatorcontrib>Ishii, Takafumi</creatorcontrib><creatorcontrib>Kudo, Takao</creatorcontrib><creatorcontrib>Ono, Hideki</creatorcontrib><creatorcontrib>Sawada, Ryohto</creatorcontrib><creatorcontrib>Ishitani, Ryuichiro</creatorcontrib><creatorcontrib>Ong, Marc</creatorcontrib><creatorcontrib>Yamaguchi, Taiki</creatorcontrib><creatorcontrib>Kataoka, Toshiki</creatorcontrib><creatorcontrib>Hayashi, Akihide</creatorcontrib><creatorcontrib>Charoenphakdee, Nontawat</creatorcontrib><creatorcontrib>Ibuka, Takeshi</creatorcontrib><collection>DataCite (Open Access)</collection><collection>DataCite</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Takamoto, So</au><au>Shinagawa, Chikashi</au><au>Motoki, Daisuke</au><au>Nakago, Kosuke</au><au>Li, Wenwen</au><au>Kurata, Iori</au><au>Watanabe, Taku</au><au>Yayama, Yoshihiro</au><au>Iriguchi, Hiroki</au><au>Asano, Yusuke</au><au>Onodera, Tasuku</au><au>Ishii, Takafumi</au><au>Kudo, Takao</au><au>Ono, Hideki</au><au>Sawada, Ryohto</au><au>Ishitani, Ryuichiro</au><au>Ong, Marc</au><au>Yamaguchi, Taiki</au><au>Kataoka, Toshiki</au><au>Hayashi, Akihide</au><au>Charoenphakdee, Nontawat</au><au>Ibuka, Takeshi</au><format>book</format><genre>unknown</genre><ristype>DATA</ristype><title>High-temperature multi-element 2021 (HME21) dataset</title><date>2022-04-28</date><risdate>2022</risdate><abstract>HME21 is the atomic structure dataset aimed for the neural network potential development. It was created in the development of PFP, a universal neural network potential for material discovery [1]. It contains multiple elements in a single structure and was sampled through a high-temperature molecular dynamics simulation. There are a total of 37 elements in the HME21 dataset, i.e., H, Li, C, N, O, F, Na, Mg, Al, Si, P, S, Cl, K, Ca, Sc, Ti, V, Cr, Mn, Fe, Co, Ni, Cu, Zn, Mo, Ru, Rh, Pd, Ag, In, Sn, Ba, Ir, Pt, Au, and Pb. They are calculated by Spin-polarized DFT calculations using PBE exchange-correlation functional implemented in VASP [2] version 5.4.4. All structures are under periodic boundary conditions. For the details of DFT calculation conditions and structure sampling method, please see the reference [1]. Please cite the reference [1] if you use this dataset. Files HME21 consists of three files with extxyz format: train.xyz: 19956 structures valid.xyz: 2498 structures test.xyz 2495 structures The structures were randomly split into training, validation, and test sub-datasets at a ratio of 8:1:1. They are used as training, validation, and test dataset for the benchmark of neural network potentials [1]. The target values are energy and atomic forces. The energy is shifted such that the energy of a single atom located in a vacuum becomes zero. The length is in angstroms (10^−10 m), and the energy is in electronvolts (eV). For supplementary, vasp_shift_energies.json which corresponds to the reference energy of single atom for each element is also included.</abstract><pub>figshare</pub><doi>10.6084/m9.figshare.19658538</doi><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | DOI: 10.6084/m9.figshare.19658538 |
ispartof | |
issn | |
language | eng |
recordid | cdi_datacite_primary_10_6084_m9_figshare_19658538 |
source | DataCite |
subjects | Computational Chemistry |
title | High-temperature multi-element 2021 (HME21) dataset |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T00%3A12%3A42IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-datacite_PQ8&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=unknown&rft.au=Takamoto,%20So&rft.date=2022-04-28&rft_id=info:doi/10.6084/m9.figshare.19658538&rft_dat=%3Cdatacite_PQ8%3E10_6084_m9_figshare_19658538%3C/datacite_PQ8%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |