Performance and Cost Assessment of Machine Learning Interatomic Potentials
Machine learning of the quantitative relationship between local environment descriptors and the potential energy surface of a system of atoms has emerged as a new frontier in the development of interatomic potentials (IAPs). Here, we present a comprehensive evaluation of machine learning IAPs (ML-IA...
Uloženo v:
| Vydáno v: | The journal of physical chemistry. A, Molecules, spectroscopy, kinetics, environment, & general theory Ročník 124; číslo 4; s. 731 |
|---|---|
| Hlavní autoři: | , , , , , , , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
United States
30.01.2020
|
| ISSN: | 1520-5215, 1520-5215 |
| On-line přístup: | Zjistit podrobnosti o přístupu |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Machine learning of the quantitative relationship between local environment descriptors and the potential energy surface of a system of atoms has emerged as a new frontier in the development of interatomic potentials (IAPs). Here, we present a comprehensive evaluation of machine learning IAPs (ML-IAPs) based on four local environment descriptors-atom-centered symmetry functions (ACSF), smooth overlap of atomic positions (SOAP), the spectral neighbor analysis potential (SNAP) bispectrum components, and moment tensors-using a diverse data set generated using high-throughput density functional theory (DFT) calculations. The data set comprising bcc (Li, Mo) and fcc (Cu, Ni) metals and diamond group IV semiconductors (Si, Ge) is chosen to span a range of crystal structures and bonding. All descriptors studied show excellent performance in predicting energies and forces far surpassing that of classical IAPs, as well as predicting properties such as elastic constants and phonon dispersion curves. We observe a general trade-off between accuracy and the degrees of freedom of each model and, consequently, computational cost. We will discuss these trade-offs in the context of model selection for molecular dynamics and other applications. |
|---|---|
| AbstractList | Machine learning of the quantitative relationship between local environment descriptors and the potential energy surface of a system of atoms has emerged as a new frontier in the development of interatomic potentials (IAPs). Here, we present a comprehensive evaluation of machine learning IAPs (ML-IAPs) based on four local environment descriptors-atom-centered symmetry functions (ACSF), smooth overlap of atomic positions (SOAP), the spectral neighbor analysis potential (SNAP) bispectrum components, and moment tensors-using a diverse data set generated using high-throughput density functional theory (DFT) calculations. The data set comprising bcc (Li, Mo) and fcc (Cu, Ni) metals and diamond group IV semiconductors (Si, Ge) is chosen to span a range of crystal structures and bonding. All descriptors studied show excellent performance in predicting energies and forces far surpassing that of classical IAPs, as well as predicting properties such as elastic constants and phonon dispersion curves. We observe a general trade-off between accuracy and the degrees of freedom of each model and, consequently, computational cost. We will discuss these trade-offs in the context of model selection for molecular dynamics and other applications. Machine learning of the quantitative relationship between local environment descriptors and the potential energy surface of a system of atoms has emerged as a new frontier in the development of interatomic potentials (IAPs). Here, we present a comprehensive evaluation of machine learning IAPs (ML-IAPs) based on four local environment descriptors-atom-centered symmetry functions (ACSF), smooth overlap of atomic positions (SOAP), the spectral neighbor analysis potential (SNAP) bispectrum components, and moment tensors-using a diverse data set generated using high-throughput density functional theory (DFT) calculations. The data set comprising bcc (Li, Mo) and fcc (Cu, Ni) metals and diamond group IV semiconductors (Si, Ge) is chosen to span a range of crystal structures and bonding. All descriptors studied show excellent performance in predicting energies and forces far surpassing that of classical IAPs, as well as predicting properties such as elastic constants and phonon dispersion curves. We observe a general trade-off between accuracy and the degrees of freedom of each model and, consequently, computational cost. We will discuss these trade-offs in the context of model selection for molecular dynamics and other applications.Machine learning of the quantitative relationship between local environment descriptors and the potential energy surface of a system of atoms has emerged as a new frontier in the development of interatomic potentials (IAPs). Here, we present a comprehensive evaluation of machine learning IAPs (ML-IAPs) based on four local environment descriptors-atom-centered symmetry functions (ACSF), smooth overlap of atomic positions (SOAP), the spectral neighbor analysis potential (SNAP) bispectrum components, and moment tensors-using a diverse data set generated using high-throughput density functional theory (DFT) calculations. The data set comprising bcc (Li, Mo) and fcc (Cu, Ni) metals and diamond group IV semiconductors (Si, Ge) is chosen to span a range of crystal structures and bonding. All descriptors studied show excellent performance in predicting energies and forces far surpassing that of classical IAPs, as well as predicting properties such as elastic constants and phonon dispersion curves. We observe a general trade-off between accuracy and the degrees of freedom of each model and, consequently, computational cost. We will discuss these trade-offs in the context of model selection for molecular dynamics and other applications. |
| Author | Shapeev, Alexander V Csányi, Gábor Thompson, Aidan P Ong, Shyue Ping Zuo, Yunxing Chen, Yiming Wood, Mitchell A Chen, Chi Li, Xiangguo Deng, Zhi Behler, Jörg |
| Author_xml | – sequence: 1 givenname: Yunxing orcidid: 0000-0002-2734-7720 surname: Zuo fullname: Zuo, Yunxing organization: Department of NanoEngineering , University of California San Diego , 9500 Gilman Drive , Mail Code 0448, La Jolla , California 92093-0448 , United States – sequence: 2 givenname: Chi orcidid: 0000-0001-8008-7043 surname: Chen fullname: Chen, Chi organization: Department of NanoEngineering , University of California San Diego , 9500 Gilman Drive , Mail Code 0448, La Jolla , California 92093-0448 , United States – sequence: 3 givenname: Xiangguo surname: Li fullname: Li, Xiangguo organization: Department of NanoEngineering , University of California San Diego , 9500 Gilman Drive , Mail Code 0448, La Jolla , California 92093-0448 , United States – sequence: 4 givenname: Zhi surname: Deng fullname: Deng, Zhi organization: Department of NanoEngineering , University of California San Diego , 9500 Gilman Drive , Mail Code 0448, La Jolla , California 92093-0448 , United States – sequence: 5 givenname: Yiming orcidid: 0000-0002-1501-5550 surname: Chen fullname: Chen, Yiming organization: Department of NanoEngineering , University of California San Diego , 9500 Gilman Drive , Mail Code 0448, La Jolla , California 92093-0448 , United States – sequence: 6 givenname: Jörg orcidid: 0000-0002-1220-1542 surname: Behler fullname: Behler, Jörg organization: Institut für Physikalische Chemie, Theoretische Chemie , Universität Göttingen , Tammannstraße 6 , 37077 Göttingen , Germany – sequence: 7 givenname: Gábor surname: Csányi fullname: Csányi, Gábor organization: Department of Engineering , University of Cambridge , Trumpington Street , Cambridge , CB2 1PZ , U.K – sequence: 8 givenname: Alexander V surname: Shapeev fullname: Shapeev, Alexander V organization: Skolkovo Institute of Science and Technology , Skolkovo Innovation Center, Building 3 , Moscow , 143026 , Russia – sequence: 9 givenname: Aidan P surname: Thompson fullname: Thompson, Aidan P organization: Center for Computing Research , Sandia National Laboratories , Albuquerque , New Mexico 87185 , United States – sequence: 10 givenname: Mitchell A surname: Wood fullname: Wood, Mitchell A organization: Center for Computing Research , Sandia National Laboratories , Albuquerque , New Mexico 87185 , United States – sequence: 11 givenname: Shyue Ping orcidid: 0000-0001-5726-2587 surname: Ong fullname: Ong, Shyue Ping organization: Department of NanoEngineering , University of California San Diego , 9500 Gilman Drive , Mail Code 0448, La Jolla , California 92093-0448 , United States |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/31916773$$D View this record in MEDLINE/PubMed |
| BookMark | eNpNjztPwzAUhS1URB-wMyGPLCnXdhwnY1XxVBEdYI6unWtI1dglTgf-PUUUCZ3hO8OnI50pG4UYiLFLAXMBUtygS_PNzuG8slAaqU7YRGgJmZZCj_71MZumtAEAoWR-xsZKVKIwRk3Y05p6H_sOgyOOoeHLmAa-SIlS6igMPHr-jO6jDcRXhH1owzt_DAP1OMSudXwdh4PW4jads1N_AF0cOWNvd7evy4ds9XL_uFysMsyNGLKmrKDINSoUBkpXelFUyjqjDvGlJ5Te2VxAU0jhjHNoLRjrGvRA4DXIGbv-3d318XNPaai7NjnabjFQ3KdaKqWF0QX8qFdHdW87aupd33bYf9V__-U3eCxgKQ |
| CitedBy_id | crossref_primary_10_1063_5_0251119 crossref_primary_10_1088_2632_2153_abdaf7 crossref_primary_10_1063_5_0135269 crossref_primary_10_1088_0256_307X_37_12_126301 crossref_primary_10_1038_s41524_024_01321_7 crossref_primary_10_3390_ma16083070 crossref_primary_10_1021_acs_jpclett_4c03474 crossref_primary_10_1039_D3MH00125C crossref_primary_10_3390_membranes12100925 crossref_primary_10_1016_j_commatsci_2021_110364 crossref_primary_10_1063_5_0188905 crossref_primary_10_1016_j_actamat_2025_121306 crossref_primary_10_1016_j_actamat_2024_120199 crossref_primary_10_1063_5_0139611 crossref_primary_10_3390_pr12112407 crossref_primary_10_1063_5_0055035 crossref_primary_10_1039_D3NR00399J crossref_primary_10_1016_j_cossms_2021_100975 crossref_primary_10_1021_acs_jpclett_5c00952 crossref_primary_10_1039_D4DD00265B crossref_primary_10_1038_s41467_023_37115_6 crossref_primary_10_1063_5_0088089 crossref_primary_10_1016_j_anucene_2023_110023 crossref_primary_10_1080_00268976_2022_2162456 crossref_primary_10_1002_adma_202102807 crossref_primary_10_1103_PhysRevMaterials_7_103602 crossref_primary_10_1103_PhysRevB_106_054106 crossref_primary_10_1016_j_ijplas_2025_104308 crossref_primary_10_1016_j_matdes_2022_111162 crossref_primary_10_1038_s41524_021_00510_y crossref_primary_10_1016_j_commatsci_2021_110493 crossref_primary_10_1088_1402_4896_acf533 crossref_primary_10_3762_bjnano_14_48 crossref_primary_10_1088_2515_7639_ada996 crossref_primary_10_1016_j_jnucmat_2024_155040 crossref_primary_10_1088_1361_651X_ad585f crossref_primary_10_1007_s10853_023_08672_4 crossref_primary_10_1016_j_jcp_2024_113073 crossref_primary_10_1088_1361_651X_ad2d68 crossref_primary_10_1061_JENMDT_EMENG_6831 crossref_primary_10_1038_s41524_022_00847_y crossref_primary_10_3390_e24081134 crossref_primary_10_1002_jcc_27487 crossref_primary_10_1063_5_0278501 crossref_primary_10_1016_j_mtcomm_2025_112504 crossref_primary_10_1063_5_0280935 crossref_primary_10_1038_s41524_025_01722_2 crossref_primary_10_1088_2632_2153_ad79b5 crossref_primary_10_1038_s41524_023_00964_2 crossref_primary_10_1038_s41524_022_00956_8 crossref_primary_10_1038_s41524_024_01464_7 crossref_primary_10_1038_s41524_020_0339_0 crossref_primary_10_1016_j_jmrt_2025_05_114 crossref_primary_10_1063_5_0216220 crossref_primary_10_1002_adts_202200848 crossref_primary_10_1038_s41524_024_01441_0 crossref_primary_10_1063_5_0173745 crossref_primary_10_1016_j_commatsci_2022_111706 crossref_primary_10_1063_5_0069443 crossref_primary_10_1002_aenm_202202892 crossref_primary_10_1038_s41524_022_00717_7 crossref_primary_10_1088_1361_648X_abe6e1 crossref_primary_10_1111_jace_19934 crossref_primary_10_3390_nano15100769 crossref_primary_10_1016_j_carbon_2022_07_055 crossref_primary_10_3390_ijms25053023 crossref_primary_10_1039_D2MH01279K crossref_primary_10_1016_j_apsusc_2022_156107 crossref_primary_10_1061__ASCE_EM_1943_7889_0002096 crossref_primary_10_1016_j_jechem_2023_01_003 crossref_primary_10_1016_j_mtcomm_2024_110332 crossref_primary_10_1103_g49f_b1x5 crossref_primary_10_1016_j_msea_2021_141817 crossref_primary_10_1103_PhysRevMaterials_9_053807 crossref_primary_10_1103_PhysRevMaterials_9_053805 crossref_primary_10_1007_s40195_025_01894_2 crossref_primary_10_1016_j_mattod_2021_08_012 crossref_primary_10_1016_j_cossms_2024_101201 crossref_primary_10_1103_PhysRevMaterials_9_063601 crossref_primary_10_1016_j_nanoen_2024_109436 crossref_primary_10_1016_j_carbon_2021_09_007 crossref_primary_10_1016_j_jmrt_2025_05_207 crossref_primary_10_1088_1361_648X_ac6f39 crossref_primary_10_1016_j_jcp_2024_113271 crossref_primary_10_1103_PhysRevMaterials_9_043802 crossref_primary_10_1039_D4NR04364B crossref_primary_10_1016_j_jpcs_2022_110909 crossref_primary_10_1016_j_jpowsour_2025_236181 crossref_primary_10_1038_s41524_022_00825_4 crossref_primary_10_1016_j_mtphys_2021_100463 crossref_primary_10_1038_s41524_024_01247_0 crossref_primary_10_1063_5_0087042 crossref_primary_10_1134_S0012501622700026 crossref_primary_10_3390_nano13040696 crossref_primary_10_1016_j_commatsci_2024_113155 crossref_primary_10_1016_j_commatsci_2021_110581 crossref_primary_10_1016_j_ijheatmasstransfer_2022_123307 crossref_primary_10_1073_pnas_2322962121 crossref_primary_10_1016_j_cjche_2020_10_044 crossref_primary_10_1103_PhysRevLett_126_156002 crossref_primary_10_1038_s41524_024_01259_w crossref_primary_10_1002_qua_27389 crossref_primary_10_1016_j_molliq_2024_125402 crossref_primary_10_1038_s41524_025_01754_8 crossref_primary_10_1002_smtd_202301415 crossref_primary_10_1088_1361_651X_ad93ec crossref_primary_10_1515_jnma_2024_0025 crossref_primary_10_1038_s41524_024_01333_3 crossref_primary_10_1063_5_0253010 crossref_primary_10_1557_s43578_023_01239_8 crossref_primary_10_1093_nsr_nwad128 crossref_primary_10_1557_s43579_022_00221_5 crossref_primary_10_1016_j_carbon_2023_118314 crossref_primary_10_1039_D4CP00535J crossref_primary_10_1080_08927022_2022_2156561 crossref_primary_10_3390_nano12213891 crossref_primary_10_1016_j_actamat_2025_121390 crossref_primary_10_1557_s43577_025_00911_0 crossref_primary_10_1088_1367_2630_abc392 crossref_primary_10_1557_s43577_023_00575_8 crossref_primary_10_1016_j_saa_2021_119864 crossref_primary_10_1515_pac_2025_0500 crossref_primary_10_1002_adfm_202418802 crossref_primary_10_1063_5_0096645 crossref_primary_10_1016_j_molliq_2022_120803 crossref_primary_10_1038_s41529_024_00536_9 crossref_primary_10_1016_j_commatsci_2023_112284 crossref_primary_10_1007_s40843_024_3114_4 crossref_primary_10_1016_j_jmrt_2025_08_046 crossref_primary_10_1016_j_jnucmat_2022_154029 crossref_primary_10_1021_acsami_4c16856 crossref_primary_10_1063_5_0218705 crossref_primary_10_1038_s41524_022_00856_x crossref_primary_10_1088_1674_1056_acd5c2 crossref_primary_10_1016_j_actamat_2022_117988 crossref_primary_10_1038_s41929_025_01398_3 crossref_primary_10_3390_cryst13050756 crossref_primary_10_1039_D1SC01825F crossref_primary_10_1063_5_0214588 crossref_primary_10_1103_PhysRevApplied_19_024058 crossref_primary_10_1002_adts_202301171 crossref_primary_10_1038_s41524_021_00508_6 crossref_primary_10_1146_annurev_matsci_100520_015716 crossref_primary_10_1021_jacs_2c07482 crossref_primary_10_1063_5_0013208 crossref_primary_10_1021_acs_jcim_5c01262 crossref_primary_10_1021_acs_jcim_5c00293 crossref_primary_10_1073_pnas_2414074122 crossref_primary_10_1016_j_mtener_2025_102059 crossref_primary_10_1016_j_apmt_2020_100685 crossref_primary_10_1007_s42823_025_00867_w crossref_primary_10_1016_j_molliq_2022_118979 crossref_primary_10_1016_j_commatsci_2023_112486 crossref_primary_10_1021_acs_jpclett_4c03179 crossref_primary_10_1038_s41524_024_01252_3 crossref_primary_10_1039_D3NR06133G crossref_primary_10_1038_s41524_023_01092_7 crossref_primary_10_1016_j_commatsci_2021_110796 crossref_primary_10_1038_s42005_023_01413_8 crossref_primary_10_1016_j_commatsci_2025_113845 crossref_primary_10_1016_j_nxmate_2025_100683 crossref_primary_10_1038_s41586_023_06735_9 crossref_primary_10_1088_2515_7655_abb011 crossref_primary_10_1088_2516_1083_ac1a65 crossref_primary_10_1016_j_commatsci_2021_110960 crossref_primary_10_1088_1361_6528_ad8357 crossref_primary_10_1038_s41524_024_01388_2 crossref_primary_10_1103_PhysRevB_108_125146 crossref_primary_10_1134_S0021364024601155 crossref_primary_10_1016_j_cpc_2025_109730 crossref_primary_10_1038_s41467_021_25134_0 crossref_primary_10_1039_D5CP02189H crossref_primary_10_1146_annurev_matsci_081420_041617 crossref_primary_10_1016_j_carbon_2020_06_007 crossref_primary_10_1063_5_0180818 crossref_primary_10_3390_met13010169 crossref_primary_10_1063_5_0244175 crossref_primary_10_1038_s41524_021_00617_2 crossref_primary_10_1002_adma_202402369 crossref_primary_10_1038_s41598_021_91068_8 crossref_primary_10_1038_s41524_024_01330_6 crossref_primary_10_1038_s41524_025_01580_y crossref_primary_10_1016_j_progpolymsci_2024_101874 crossref_primary_10_1088_2515_7639_ad2983 crossref_primary_10_1016_j_commatsci_2023_112057 crossref_primary_10_1007_s00894_024_06084_y crossref_primary_10_1088_1361_651X_ae0505 crossref_primary_10_1038_s41524_025_01747_7 crossref_primary_10_1016_j_jnucmat_2023_154794 crossref_primary_10_1002_cphc_202200592 crossref_primary_10_1007_s41403_023_00435_6 crossref_primary_10_1007_s44210_025_00054_6 crossref_primary_10_3390_met15010048 crossref_primary_10_1021_acs_jpcc_4c04018 crossref_primary_10_1002_wcms_1645 crossref_primary_10_1021_acs_jpca_5c00391 crossref_primary_10_1016_j_commatsci_2025_113850 crossref_primary_10_1063_5_0155621 crossref_primary_10_1080_15421406_2023_2243691 crossref_primary_10_1016_j_ijmecsci_2025_110471 crossref_primary_10_1007_s44210_025_00065_3 crossref_primary_10_1016_j_commatsci_2021_110752 crossref_primary_10_1063_5_0155618 crossref_primary_10_1088_1741_4326_abe7bd crossref_primary_10_1016_j_ijplas_2021_103157 crossref_primary_10_1002_anie_202501017 crossref_primary_10_1016_j_ijmecsci_2024_109911 crossref_primary_10_1063_5_0122502 crossref_primary_10_1016_j_nanoen_2020_105716 crossref_primary_10_1002_pssb_202400483 crossref_primary_10_1021_acsnano_5c05553 crossref_primary_10_3390_bioengineering9030090 crossref_primary_10_1039_D3QI02410E crossref_primary_10_1038_s41467_020_19267_x crossref_primary_10_1088_1361_651X_adba03 crossref_primary_10_1103_PhysRevMaterials_9_045403 crossref_primary_10_1002_adma_202310455 crossref_primary_10_1038_s41524_023_01134_0 crossref_primary_10_1088_1674_1056_ad01a4 crossref_primary_10_1016_j_commatsci_2025_114063 crossref_primary_10_1557_s43578_023_01152_0 crossref_primary_10_1038_s41524_023_01049_w crossref_primary_10_1063_5_0142127 crossref_primary_10_1002_adma_202412005 crossref_primary_10_1002_aenm_202403876 crossref_primary_10_1016_j_commatsci_2020_109891 crossref_primary_10_1038_s41524_025_01651_0 crossref_primary_10_1016_j_mser_2021_100642 crossref_primary_10_1038_s43588_020_00002_x crossref_primary_10_1088_1361_648X_ac2864 crossref_primary_10_1088_2632_2153_ad95db crossref_primary_10_1103_8w5w_f3kd crossref_primary_10_1038_s41524_020_00367_7 crossref_primary_10_1038_s41524_023_01123_3 crossref_primary_10_1016_j_pmatsci_2022_101018 crossref_primary_10_1103_PhysRevLett_134_036402 crossref_primary_10_1016_j_actamat_2023_119465 crossref_primary_10_1016_j_actamat_2024_120508 crossref_primary_10_1016_j_apsusc_2021_152094 crossref_primary_10_1016_j_commatsci_2023_112655 crossref_primary_10_1038_s41467_025_63221_8 crossref_primary_10_1039_D2ME00149G crossref_primary_10_1007_s00340_021_07582_0 crossref_primary_10_1007_s10008_024_05952_0 crossref_primary_10_1088_2632_2153_abc9fe crossref_primary_10_1088_2632_2153_abc9fd crossref_primary_10_1038_s41524_024_01207_8 crossref_primary_10_1063_5_0129045 crossref_primary_10_1016_j_actamat_2021_116980 crossref_primary_10_1007_s12666_024_03524_4 crossref_primary_10_1038_s41467_020_19168_z crossref_primary_10_1088_2752_5724_ac681d crossref_primary_10_1016_j_actamat_2024_119788 crossref_primary_10_1016_j_commatsci_2023_112526 crossref_primary_10_1038_s41597_023_02200_4 crossref_primary_10_1038_s41557_023_01427_3 crossref_primary_10_1021_jacs_4c01897 crossref_primary_10_1088_2752_5724_acb506 crossref_primary_10_1088_1361_648X_adbba5 crossref_primary_10_3390_molecules28072892 crossref_primary_10_1039_D3NR06468A crossref_primary_10_1039_D5CS00104H crossref_primary_10_3390_en15186599 crossref_primary_10_1016_j_actamat_2024_120408 crossref_primary_10_1038_s41524_024_01264_z crossref_primary_10_1021_acsmaterialslett_5c00093 crossref_primary_10_1016_j_cpc_2020_107679 crossref_primary_10_1063_5_0156682 crossref_primary_10_1016_j_commatsci_2024_113608 crossref_primary_10_1038_s41524_022_00865_w crossref_primary_10_1134_S0022476624040188 crossref_primary_10_1007_s11431_022_2095_7 crossref_primary_10_1134_S0031918X24602178 crossref_primary_10_1016_j_cpc_2023_108896 crossref_primary_10_1088_1361_648X_ad7086 crossref_primary_10_1038_s43588_022_00349_3 crossref_primary_10_1088_2515_7655_abc7f3 crossref_primary_10_1007_s12598_025_03499_1 crossref_primary_10_1002_qua_26956 crossref_primary_10_1039_D5DD00085H crossref_primary_10_1088_2632_2153_adfffd crossref_primary_10_1002_ange_202501017 crossref_primary_10_1038_s41524_024_01251_4 crossref_primary_10_1039_D2CP01560A crossref_primary_10_3389_fmats_2024_1466793 crossref_primary_10_1103_PhysRevMaterials_7_053804 crossref_primary_10_1007_s00205_022_01809_w crossref_primary_10_1016_j_cpc_2023_108883 crossref_primary_10_1016_j_jpowsour_2022_232389 crossref_primary_10_1116_6_0004288 crossref_primary_10_1103_PhysRevLett_132_086301 crossref_primary_10_1007_s10853_021_06865_3 crossref_primary_10_1038_s41524_022_00721_x crossref_primary_10_1111_jace_20128 crossref_primary_10_1016_j_pecs_2023_101084 crossref_primary_10_1103_PhysRevMaterials_7_085601 crossref_primary_10_1557_s43578_022_00783_z crossref_primary_10_1103_PhysRevMaterials_6_043801 crossref_primary_10_1088_1361_651X_ad9d63 crossref_primary_10_1557_s43577_022_00324_3 crossref_primary_10_1557_s43578_023_01167_7 crossref_primary_10_1088_1674_1056_adc661 crossref_primary_10_1039_D5CP00373C crossref_primary_10_1016_j_cpc_2020_107583 crossref_primary_10_1038_s41563_024_01919_8 crossref_primary_10_1038_s41598_023_44265_6 crossref_primary_10_1016_j_ces_2021_117224 crossref_primary_10_1063_5_0016005 crossref_primary_10_1038_s41524_023_01046_z crossref_primary_10_1557_s43580_022_00228_z crossref_primary_10_1016_j_actamat_2023_119041 crossref_primary_10_1088_2632_2153_abcc44 crossref_primary_10_1063_5_0063534 crossref_primary_10_1002_adfm_202417891 crossref_primary_10_1088_1402_4896_ad37ab crossref_primary_10_1038_s41598_022_10658_2 crossref_primary_10_1021_acs_jctc_4c01475 crossref_primary_10_1103_PhysRevB_106_L180101 crossref_primary_10_1038_s41524_023_01120_6 crossref_primary_10_1088_2632_2153_ad4ae5 crossref_primary_10_1557_s43578_023_01023_8 crossref_primary_10_1039_D0SC00594K crossref_primary_10_1038_s41524_024_01227_4 crossref_primary_10_1016_j_commatsci_2021_111180 crossref_primary_10_1038_s41524_024_01205_w crossref_primary_10_1038_s41467_021_21488_7 crossref_primary_10_1016_j_commatsci_2023_112715 crossref_primary_10_1039_D3MH00314K crossref_primary_10_1063_5_0158783 crossref_primary_10_1002_aidi_202500031 crossref_primary_10_1515_pac_2022_0202 crossref_primary_10_1002_chem_202401148 crossref_primary_10_1016_j_ijpvp_2021_104514 crossref_primary_10_1016_j_cpc_2021_108171 crossref_primary_10_1002_adfm_202313188 crossref_primary_10_1038_s41524_025_01550_4 crossref_primary_10_1103_vtyl_j1nz crossref_primary_10_1088_1361_651X_ad5dd2 crossref_primary_10_1103_tszb_gfxr crossref_primary_10_1016_j_scriptamat_2025_116568 crossref_primary_10_1039_D5TA00982K crossref_primary_10_1016_j_jallcom_2023_169964 crossref_primary_10_1088_1361_648X_ae0111 crossref_primary_10_1002_mgea_58 crossref_primary_10_1002_aenm_202202279 crossref_primary_10_1016_j_compositesb_2024_111452 crossref_primary_10_1557_s43578_023_01183_7 crossref_primary_10_1038_s43246_024_00603_3 crossref_primary_10_1038_s41578_021_00340_w crossref_primary_10_1038_s41524_021_00559_9 crossref_primary_10_1038_s41524_022_00696_9 crossref_primary_10_1016_j_molliq_2023_121751 crossref_primary_10_1016_j_ultramic_2022_113644 crossref_primary_10_1073_pnas_2005847117 crossref_primary_10_1080_00268976_2024_2381617 crossref_primary_10_1038_s41524_022_00771_1 crossref_primary_10_1088_1361_651X_adf56d crossref_primary_10_1016_j_physb_2025_417499 crossref_primary_10_3389_fenrg_2025_1621807 crossref_primary_10_1016_j_commatsci_2024_113074 crossref_primary_10_1038_s41524_025_01742_y crossref_primary_10_1002_adem_202302043 crossref_primary_10_1016_j_jcp_2024_113102 crossref_primary_10_1063_5_0031249 crossref_primary_10_1134_S0036024424702418 crossref_primary_10_1016_j_cma_2020_113500 crossref_primary_10_1039_D4NR00929K crossref_primary_10_1016_j_jmst_2024_10_052 crossref_primary_10_1088_2515_7655_abc96f crossref_primary_10_1039_D5CP00532A crossref_primary_10_1016_j_commatsci_2022_111660 crossref_primary_10_1016_j_surfin_2023_103442 crossref_primary_10_1063_5_0013826 crossref_primary_10_1007_s40843_024_2851_9 crossref_primary_10_1016_j_rineng_2025_106626 crossref_primary_10_1021_acs_jctc_5c00402 crossref_primary_10_1021_jacs_4c17739 crossref_primary_10_1039_D1SC02136B crossref_primary_10_1063_5_0262323 crossref_primary_10_1016_j_cis_2024_103312 crossref_primary_10_1016_j_commatsci_2021_111012 crossref_primary_10_1016_j_matchemphys_2023_128053 crossref_primary_10_1134_S0022476624080109 crossref_primary_10_1063_5_0146122 crossref_primary_10_1088_1361_648X_ac7f73 crossref_primary_10_1088_2632_2153_acf115 crossref_primary_10_3389_fenrg_2021_695902 crossref_primary_10_1016_j_commatsci_2023_112624 crossref_primary_10_1016_j_commatsci_2024_112925 crossref_primary_10_1016_j_jechem_2025_08_058 crossref_primary_10_1016_j_mser_2024_100825 crossref_primary_10_1016_j_scriptamat_2022_114803 crossref_primary_10_1039_D4NR02114B crossref_primary_10_1021_acs_jpcc_5c02777 crossref_primary_10_1063_5_0151833 crossref_primary_10_1038_s41524_023_01053_0 crossref_primary_10_1016_j_commatsci_2021_111028 crossref_primary_10_1140_epjb_s10051_021_00233_5 crossref_primary_10_3390_ceramics7010015 crossref_primary_10_1016_j_actamat_2025_120924 crossref_primary_10_1038_s41578_020_00255_y crossref_primary_10_1002_adma_202305758 crossref_primary_10_1103_PhysRevResearch_6_013292 crossref_primary_10_1038_s41524_023_01184_4 crossref_primary_10_1016_j_commatsci_2023_112732 crossref_primary_10_1016_j_mtcomm_2025_113871 crossref_primary_10_1088_2632_2153_abfe7c crossref_primary_10_1021_acs_langmuir_4c04578 crossref_primary_10_1016_j_icheatmasstransfer_2025_109231 crossref_primary_10_1021_acselectrochem_4c00102 crossref_primary_10_1038_s41567_025_02925_6 crossref_primary_10_1038_s41524_025_01599_1 crossref_primary_10_1039_D2SC02980D crossref_primary_10_1063_5_0206215 crossref_primary_10_1103_q4nm_qyk4 crossref_primary_10_1038_s43246_025_00766_7 crossref_primary_10_1016_j_physb_2025_417281 crossref_primary_10_1038_s41467_024_47422_1 crossref_primary_10_1016_j_jnucmat_2024_155011 crossref_primary_10_1016_j_actamat_2024_119742 crossref_primary_10_1103_PhysRevMaterials_6_063802 crossref_primary_10_1016_j_corsci_2024_112541 crossref_primary_10_1016_j_jcp_2023_112030 crossref_primary_10_1038_s41524_022_00872_x crossref_primary_10_1063_5_0009550 crossref_primary_10_1016_j_mtphys_2024_101386 crossref_primary_10_1016_j_jnucmat_2024_155016 crossref_primary_10_3390_nano13222938 crossref_primary_10_1038_s41524_024_01390_8 crossref_primary_10_1038_s43588_023_00561_9 crossref_primary_10_1016_j_matdes_2023_112012 |
| ContentType | Journal Article |
| DBID | NPM 7X8 |
| DOI | 10.1021/acs.jpca.9b08723 |
| DatabaseName | PubMed MEDLINE - Academic |
| DatabaseTitle | PubMed MEDLINE - Academic |
| DatabaseTitleList | PubMed MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | no_fulltext_linktorsrc |
| Discipline | Chemistry |
| EISSN | 1520-5215 |
| ExternalDocumentID | 31916773 |
| Genre | Journal Article |
| GroupedDBID | --- -~X .DC .K2 123 29L 4.4 53G 55A 5VS 7~N 85S AABXI ABJNI ABMVS ABPPZ ABQRX ABUCX ACBEA ACGFS ACNCT ACS ADHLV AEESW AENEX AFEFF AHGAQ ALMA_UNASSIGNED_HOLDINGS AQSVZ BAANH CS3 CUPRZ D0L DU5 EBS ED~ F5P GGK GNL IH9 IHE JG~ NPM PZZ RNS ROL TAE TN5 UI2 UKR UPT VF5 VG9 VQA W1F WH7 XSW YQT YZZ ~02 7X8 ABBLG ABLBI |
| ID | FETCH-LOGICAL-a471t-d890645a3a1708c8f1693bc73737f8fea2fcb410d621c7ccabb07bcdaf0e0f502 |
| IEDL.DBID | 7X8 |
| ISICitedReferencesCount | 667 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000510531200016&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1520-5215 |
| IngestDate | Fri Jul 11 10:26:34 EDT 2025 Thu Jan 02 22:59:07 EST 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 4 |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-a471t-d890645a3a1708c8f1693bc73737f8fea2fcb410d621c7ccabb07bcdaf0e0f502 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0002-2734-7720 0000-0001-5726-2587 0000-0002-1501-5550 0000-0002-1220-1542 0000-0001-8008-7043 |
| OpenAccessLink | https://resolver.sub.uni-goettingen.de/purl?gro-2/73507 |
| PMID | 31916773 |
| PQID | 2335175600 |
| PQPubID | 23479 |
| ParticipantIDs | proquest_miscellaneous_2335175600 pubmed_primary_31916773 |
| PublicationCentury | 2000 |
| PublicationDate | 2020-01-30 |
| PublicationDateYYYYMMDD | 2020-01-30 |
| PublicationDate_xml | – month: 01 year: 2020 text: 2020-01-30 day: 30 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | The journal of physical chemistry. A, Molecules, spectroscopy, kinetics, environment, & general theory |
| PublicationTitleAlternate | J Phys Chem A |
| PublicationYear | 2020 |
| SSID | ssj0001324 |
| Score | 2.72623 |
| Snippet | Machine learning of the quantitative relationship between local environment descriptors and the potential energy surface of a system of atoms has emerged as a... |
| SourceID | proquest pubmed |
| SourceType | Aggregation Database Index Database |
| StartPage | 731 |
| Title | Performance and Cost Assessment of Machine Learning Interatomic Potentials |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/31916773 https://www.proquest.com/docview/2335175600 |
| Volume | 124 |
| WOSCitedRecordID | wos000510531200016&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8NAEF7UCnrx_agvVvC67SbZzW5OUopFhJYcFHor-xQFk2qiv9_ZNLUnQZBAboHs7jDffDOz8yF0Qzl1CTWacKM0YYxakgmfEi8zJzNqnWSqEZsQk4mcTrO8TbhVbVvl0ic2jtqWJuTI-3GScIA6wOfb-TsJqlGhutpKaKyjTgKhTLBqMV1NCwem1VSVOVAkgCnelikB1vrKVL3XuVG9TFMpgljRbwFmAzSj3f_-4h7aaUNMPFjYxD5ac8UB2hould0O0UO-ui2AVWHxsKxqPPiZ0YlLj8dNk6XD7fzVZ9ykDoGhv70YnJd1aDICyz1CT6O7x-E9aTUViAIYqomFA0gZV4mKBJVG-jCMRRuRwOOldyr2RrOI2jSOjIDj1ZoKbazy1FHPaXyMNoqycKcIAzPUPNDJTGvmMqZjK6g22mvOQvNcF10vt2kGCwyFCFW48rOarTaqi04Wez2bL4ZrzMAlRKkQydkfvj5H23GgvzSk0C5Qx8O63SXaNF_1S_Vx1RgDvCf5-BuwM7_D |
| linkProvider | ProQuest |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Performance+and+Cost+Assessment+of+Machine+Learning+Interatomic+Potentials&rft.jtitle=The+journal+of+physical+chemistry.+A%2C+Molecules%2C+spectroscopy%2C+kinetics%2C+environment%2C+%26+general+theory&rft.au=Zuo%2C+Yunxing&rft.au=Chen%2C+Chi&rft.au=Li%2C+Xiangguo&rft.au=Deng%2C+Zhi&rft.date=2020-01-30&rft.eissn=1520-5215&rft.volume=124&rft.issue=4&rft.spage=731&rft_id=info:doi/10.1021%2Facs.jpca.9b08723&rft_id=info%3Apmid%2F31916773&rft_id=info%3Apmid%2F31916773&rft.externalDocID=31916773 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1520-5215&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1520-5215&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1520-5215&client=summon |