Active learning of linearly parametrized interatomic potentials
[Display omitted] This paper introduces an active learning approach to the fitting of machine learning interatomic potentials. Our approach is based on the D-optimality criterion for selecting atomic configurations on which the potential is fitted. It is shown that the proposed active learning appro...
Saved in:
| Published in | Computational materials science Vol. 140; pp. 171 - 180 |
|---|---|
| Main Authors | , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier B.V
01.12.2017
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | [Display omitted]
This paper introduces an active learning approach to the fitting of machine learning interatomic potentials. Our approach is based on the D-optimality criterion for selecting atomic configurations on which the potential is fitted. It is shown that the proposed active learning approach is highly efficient in training potentials on the fly, ensuring that no extrapolation is attempted and leading to a completely reliable atomistic simulation without any significant decrease in accuracy. We apply our approach to molecular dynamics and structure relaxation, and we argue that it can be applied, in principle, to any other type of atomistic simulation. The software, test cases, and examples of usage are published at http://gitlab.skoltech.ru/shapeev/mlip/. |
|---|---|
| AbstractList | [Display omitted]
This paper introduces an active learning approach to the fitting of machine learning interatomic potentials. Our approach is based on the D-optimality criterion for selecting atomic configurations on which the potential is fitted. It is shown that the proposed active learning approach is highly efficient in training potentials on the fly, ensuring that no extrapolation is attempted and leading to a completely reliable atomistic simulation without any significant decrease in accuracy. We apply our approach to molecular dynamics and structure relaxation, and we argue that it can be applied, in principle, to any other type of atomistic simulation. The software, test cases, and examples of usage are published at http://gitlab.skoltech.ru/shapeev/mlip/. |
| Author | Podryabinkin, Evgeny V. Shapeev, Alexander V. |
| Author_xml | – sequence: 1 givenname: Evgeny V. surname: Podryabinkin fullname: Podryabinkin, Evgeny V. email: e.podryabinkin@skoltech.ru – sequence: 2 givenname: Alexander V. surname: Shapeev fullname: Shapeev, Alexander V. email: a.shapeev@skoltech.ru |
| BookMark | eNqNkE1LAzEQhoNUsK3-BvcP7DrZz-xBpBStQsGLnkM2mZUpu0nJhkL99aZUPHjRw_AyMM8L8yzYzDqLjN1yyDjw-m6XaTeOKkyashx4k4HIoOAXbM5F06YggM_YHNq8SSGv6iu2mKYdRLIV-Zw9rHSgAyYDKm_JfiSuTwaycRuOyV55NWLw9IkmIRvQq-BG0sneBbSB1DBds8s-Bt5855K9Pz2-rZ_T7evmZb3aprosypAaQF0ZLDBH5KhU17QV78uy01gr1VZVF0crYXgpdNeKhuu8AVN0vYG6hKJYsvtzr_Zumjz2UlNQgZwNXtEgOciTDbmTPzbkyYYEIaONyDe_-L2nUfnjP8jVmcT43oHQy3iBVqMhjzpI4-jPji_KMIP0 |
| CitedBy_id | crossref_primary_10_1103_PhysRevB_109_115430 crossref_primary_10_1063_5_0135269 crossref_primary_10_1038_s41524_020_0283_z crossref_primary_10_1038_s41524_024_01321_7 crossref_primary_10_1088_2632_2153_ad5074 crossref_primary_10_1039_D3MH00125C crossref_primary_10_1063_1_5078687 crossref_primary_10_1016_j_cpc_2019_02_007 crossref_primary_10_1063_5_0188905 crossref_primary_10_1016_j_commatsci_2021_110360 crossref_primary_10_1016_j_actamat_2024_120199 crossref_primary_10_1063_5_0139611 crossref_primary_10_1038_s41467_023_44525_z crossref_primary_10_1016_j_est_2025_116099 crossref_primary_10_1038_s43246_024_00487_3 crossref_primary_10_1016_j_carbon_2024_119533 crossref_primary_10_1080_08927022_2018_1447107 crossref_primary_10_1038_s41467_023_37115_6 crossref_primary_10_1038_s41467_018_06169_2 crossref_primary_10_1016_j_jallcom_2019_06_318 crossref_primary_10_1002_adma_202102807 crossref_primary_10_1021_acs_jpcc_4c02309 crossref_primary_10_1021_acsmaterialsau_2c00057 crossref_primary_10_1038_s41524_021_00510_y crossref_primary_10_1103_PhysRevMaterials_8_033601 crossref_primary_10_1038_s41524_021_00630_5 crossref_primary_10_1149_1945_7111_ad7326 crossref_primary_10_1021_acs_chemmater_4c01351 crossref_primary_10_1021_acs_jctc_3c00488 crossref_primary_10_1111_jace_17779 crossref_primary_10_1016_j_mtnano_2022_100280 crossref_primary_10_1039_D1SC01000J crossref_primary_10_1039_D4NH00487F crossref_primary_10_1021_acs_chemrev_0c00004 crossref_primary_10_1103_PhysRevB_100_104110 crossref_primary_10_1002_cjoc_202100299 crossref_primary_10_1557_mrs_2020_163 crossref_primary_10_1016_j_jmst_2024_03_027 crossref_primary_10_1021_acs_jctc_2c00643 crossref_primary_10_1063_5_0216220 crossref_primary_10_1021_acs_chemrev_8b00026 crossref_primary_10_1021_acs_jpcc_4c00028 crossref_primary_10_1016_j_commatsci_2022_111709 crossref_primary_10_1021_acs_jpclett_9b03664 crossref_primary_10_1063_5_0106617 crossref_primary_10_1103_PhysRevMaterials_4_113602 crossref_primary_10_1063_5_0069443 crossref_primary_10_1103_PhysRevB_99_064114 crossref_primary_10_1039_D2RA08086A crossref_primary_10_1039_D3SC02482B crossref_primary_10_1063_5_0160326 crossref_primary_10_1103_PhysRevB_100_014105 crossref_primary_10_1149_1945_7111_ad9991 crossref_primary_10_1021_acs_jpclett_8b01939 crossref_primary_10_1016_j_carbon_2023_118293 crossref_primary_10_1016_j_flatc_2022_100446 crossref_primary_10_7566_JPSJ_92_074002 crossref_primary_10_1021_acs_jctc_1c00166 crossref_primary_10_1021_acs_jpcc_9b08691 crossref_primary_10_1063_1_5023802 crossref_primary_10_1088_2632_2153_ace418 crossref_primary_10_1038_s41524_023_00988_8 crossref_primary_10_1111_jace_19932 crossref_primary_10_1007_s40843_023_2836_0 crossref_primary_10_1038_s41524_023_01073_w crossref_primary_10_1103_PhysRevMaterials_7_093802 crossref_primary_10_1021_acs_chemmater_2c03658 crossref_primary_10_1021_acs_jctc_8b00110 crossref_primary_10_1016_j_commatsci_2021_110567 crossref_primary_10_1107_S1600576724009282 crossref_primary_10_1103_PhysRevB_110_214202 crossref_primary_10_1016_j_jnoncrysol_2025_123486 crossref_primary_10_1021_acs_jpca_2c05459 crossref_primary_10_1007_s00339_024_08237_5 crossref_primary_10_1016_j_commatsci_2019_109333 crossref_primary_10_1016_j_jnucmat_2021_153113 crossref_primary_10_1103_PhysRevB_102_041121 crossref_primary_10_1016_j_actamat_2023_118734 crossref_primary_10_31857_S1234567824110090 crossref_primary_10_1038_s41597_020_0473_z crossref_primary_10_1103_PhysRevB_104_104102 crossref_primary_10_1016_j_flatc_2022_100347 crossref_primary_10_1038_s41524_023_00967_z crossref_primary_10_1103_PhysRevB_108_174103 crossref_primary_10_1016_j_fuel_2022_125340 crossref_primary_10_1016_j_mtphys_2021_100463 crossref_primary_10_1103_PhysRevB_100_174101 crossref_primary_10_1063_5_0087165 crossref_primary_10_1134_S0012501622700026 crossref_primary_10_26599_JAC_2024_9220935 crossref_primary_10_1016_j_carbon_2021_12_039 crossref_primary_10_1038_s41467_021_21376_0 crossref_primary_10_1063_5_0246178 crossref_primary_10_1103_PhysRevLett_126_156002 crossref_primary_10_1038_s41524_021_00685_4 crossref_primary_10_1016_j_molliq_2024_125402 crossref_primary_10_1021_acs_jctc_3c00279 crossref_primary_10_1063_1_5019779 crossref_primary_10_1016_j_jmst_2023_04_074 crossref_primary_10_1021_acs_jpca_1c02529 crossref_primary_10_1039_D1TA04987A crossref_primary_10_1088_1361_651X_ad93ec crossref_primary_10_1038_s41524_024_01333_3 crossref_primary_10_1039_D2CP04411K crossref_primary_10_1557_s43578_023_01239_8 crossref_primary_10_1016_j_actamat_2025_120748 crossref_primary_10_1021_acsami_3c15399 crossref_primary_10_1093_nsr_nwad128 crossref_primary_10_1557_s43579_022_00221_5 crossref_primary_10_3367_UFNe_2021_05_039187 crossref_primary_10_1021_acs_jctc_9b00805 crossref_primary_10_1021_acs_jpcc_3c06648 crossref_primary_10_1016_j_commatsci_2024_113409 crossref_primary_10_1080_08927022_2022_2156561 crossref_primary_10_1088_1367_2630_abc392 crossref_primary_10_1021_acs_jpca_9b08723 crossref_primary_10_1039_D1NR06449E 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_1007_s40843_024_3114_4 crossref_primary_10_1021_acsami_1c04583 crossref_primary_10_1146_annurev_chembioeng_092120_020803 crossref_primary_10_1063_5_0121805 crossref_primary_10_1063_5_0187892 crossref_primary_10_1103_PhysRevB_101_115132 crossref_primary_10_1039_D3CP01348K crossref_primary_10_1063_5_0057051 crossref_primary_10_1038_s41524_022_00856_x crossref_primary_10_1021_acs_jpcc_4c04575 crossref_primary_10_1016_j_actamat_2022_117988 crossref_primary_10_1063_5_0099929 crossref_primary_10_1016_j_ceramint_2022_11_319 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_024_01506_0 crossref_primary_10_1103_PhysRevMaterials_6_013804 crossref_primary_10_1103_PhysRevB_102_184305 crossref_primary_10_1038_s41524_023_01104_6 crossref_primary_10_1038_s41467_024_47999_7 crossref_primary_10_1038_s41524_021_00508_6 crossref_primary_10_1016_j_commatsci_2023_112376 crossref_primary_10_1039_D4DD00183D crossref_primary_10_1146_annurev_matsci_100520_015716 crossref_primary_10_1021_jacs_2c07482 crossref_primary_10_1016_j_actamat_2024_120124 crossref_primary_10_1021_acs_jctc_1c00821 crossref_primary_10_1002_jcc_26790 crossref_primary_10_1021_acs_chemrev_4c00572 crossref_primary_10_1063_5_0025310 crossref_primary_10_1016_j_chemphys_2021_111347 crossref_primary_10_1016_j_apmt_2020_100685 crossref_primary_10_1016_j_ijthermalsci_2025_109876 crossref_primary_10_1103_PhysRevB_107_104103 crossref_primary_10_1039_D0MH00787K crossref_primary_10_1002_batt_202000262 crossref_primary_10_1039_D3YA00057E crossref_primary_10_1038_s41524_024_01252_3 crossref_primary_10_1063_5_0023005 crossref_primary_10_1021_acs_jctc_3c01051 crossref_primary_10_1016_j_commatsci_2021_110796 crossref_primary_10_1039_D2CP05976B crossref_primary_10_1021_acs_jcim_1c00007 crossref_primary_10_1039_D3CP04729F crossref_primary_10_1080_27660400_2023_2269948 crossref_primary_10_1063_1_5016317 crossref_primary_10_1063_1_5017641 crossref_primary_10_1088_2632_2153_aba373 crossref_primary_10_1021_acs_jcim_1c01125 crossref_primary_10_1039_D3CP03845A crossref_primary_10_1063_5_0237656 crossref_primary_10_1016_j_ijheatmasstransfer_2021_121589 crossref_primary_10_1016_j_cossms_2025_101214 crossref_primary_10_1038_s41524_024_01342_2 crossref_primary_10_1016_j_commatsci_2024_113331 crossref_primary_10_1038_s41524_019_0236_6 crossref_primary_10_1134_S0021364024601155 crossref_primary_10_1016_j_commatsci_2024_113459 crossref_primary_10_1038_s41524_024_01278_7 crossref_primary_10_1103_PhysRevB_107_125160 crossref_primary_10_1134_S1063776123120208 crossref_primary_10_1016_j_ensm_2023_103023 crossref_primary_10_1063_5_0244175 crossref_primary_10_1016_j_commatsci_2025_113719 crossref_primary_10_1016_j_physrep_2021_08_002 crossref_primary_10_1002_adma_202402369 crossref_primary_10_1063_1_5121519 crossref_primary_10_1016_j_commatsci_2024_113422 crossref_primary_10_1007_s00894_024_06084_y crossref_primary_10_1038_s41467_019_12875_2 crossref_primary_10_1063_5_0255385 crossref_primary_10_1103_PhysRevMaterials_7_113606 crossref_primary_10_1103_PhysRevB_97_184307 crossref_primary_10_1016_j_carbon_2020_05_105 crossref_primary_10_3390_ma16010235 crossref_primary_10_1103_PhysRevMaterials_7_033803 crossref_primary_10_1063_5_0038516 crossref_primary_10_1088_2515_7639_ab8c2d crossref_primary_10_1016_j_commatsci_2024_113433 crossref_primary_10_1007_s44379_024_00008_6 crossref_primary_10_1038_s41524_024_01254_1 crossref_primary_10_1063_5_0155621 crossref_primary_10_1063_5_0027643 crossref_primary_10_1021_acs_chemrev_0c01303 crossref_primary_10_1063_5_0155618 crossref_primary_10_1021_acsnano_3c10201 crossref_primary_10_1021_acs_jctc_8b00524 crossref_primary_10_1038_s41598_017_08455_3 crossref_primary_10_1021_prechem_4c00051 crossref_primary_10_1103_PhysRevB_100_144308 crossref_primary_10_1021_acs_jpclett_4c02934 crossref_primary_10_1063_1_5011181 crossref_primary_10_1021_acs_jctc_3c00822 crossref_primary_10_1021_acs_jctc_3c00944 crossref_primary_10_1063_5_0222355 crossref_primary_10_1021_acs_jctc_1c00527 crossref_primary_10_1021_acs_jctc_1c00769 crossref_primary_10_3389_fenrg_2022_1043064 crossref_primary_10_1002_pssr_202100632 crossref_primary_10_1021_acs_chemmater_2c01954 crossref_primary_10_1002_adma_202204038 crossref_primary_10_1021_acs_jpcc_9b04207 crossref_primary_10_1021_acs_jctc_4c00474 crossref_primary_10_1103_PhysRevLett_120_156001 crossref_primary_10_1021_acsami_0c17285 crossref_primary_10_1063_5_0143211 crossref_primary_10_1038_s41563_020_0777_6 crossref_primary_10_1038_s41524_020_00477_2 crossref_primary_10_1002_adma_202200924 crossref_primary_10_1016_j_taml_2023_100481 crossref_primary_10_1002_adma_201902765 crossref_primary_10_1063_5_0158710 crossref_primary_10_1146_annurev_physchem_082720_034254 crossref_primary_10_1002_aenm_202403876 crossref_primary_10_1016_j_mser_2021_100642 crossref_primary_10_1016_j_mser_2021_100645 crossref_primary_10_1103_PhysRevB_105_165141 crossref_primary_10_1103_PhysRevB_109_075201 crossref_primary_10_1038_s41524_023_01123_3 crossref_primary_10_1016_j_pmatsci_2022_101018 crossref_primary_10_1038_s41467_024_45840_9 crossref_primary_10_1021_acs_chemrev_1c00107 crossref_primary_10_1021_acs_chemmater_0c01894 crossref_primary_10_1039_D4CP04578E crossref_primary_10_1021_acs_jctc_1c00783 crossref_primary_10_1039_D2DD00078D crossref_primary_10_1021_acs_chemrev_1c00022 crossref_primary_10_1016_j_commatsci_2023_112535 crossref_primary_10_1103_PhysRevMaterials_7_043801 crossref_primary_10_1063_1_5051772 crossref_primary_10_1021_acs_jpclett_0c02357 crossref_primary_10_1016_j_eng_2023_02_019 crossref_primary_10_1002_wcms_1564 crossref_primary_10_1038_s43246_023_00389_w crossref_primary_10_1063_5_0155887 crossref_primary_10_1039_D4CP01801J crossref_primary_10_1088_2632_2153_abc9fe crossref_primary_10_1103_PhysRevMaterials_6_033801 crossref_primary_10_1063_5_0036097 crossref_primary_10_1063_5_0013059 crossref_primary_10_1088_2632_2153_ad9fce crossref_primary_10_1016_j_actamat_2021_116980 crossref_primary_10_1088_1361_651X_ada050 crossref_primary_10_1088_2752_5724_ac681d crossref_primary_10_1038_s41597_023_02200_4 crossref_primary_10_1021_acs_jctc_4c01552 crossref_primary_10_1088_2752_5724_acb506 crossref_primary_10_1039_D3MH00736G crossref_primary_10_1021_acs_chemmater_9b04663 crossref_primary_10_1103_PhysRevB_109_075426 crossref_primary_10_1016_j_matt_2023_05_035 crossref_primary_10_1016_j_commatsci_2018_09_031 crossref_primary_10_1002_ange_201909987 crossref_primary_10_1016_j_cpc_2020_107679 crossref_primary_10_1021_acs_jpcb_8b11905 crossref_primary_10_1016_j_molliq_2024_126152 crossref_primary_10_1063_5_0021965 crossref_primary_10_1134_S0022476624040188 crossref_primary_10_1134_S0031918X24602178 crossref_primary_10_1021_acs_chemrev_0c00868 crossref_primary_10_1134_S0021364023600234 crossref_primary_10_1021_acs_chemrev_0c00749 crossref_primary_10_1021_acs_jctc_4c00039 crossref_primary_10_1039_D0RE00232A crossref_primary_10_1103_PhysRevLett_131_236101 crossref_primary_10_1038_s43588_023_00407_4 crossref_primary_10_1016_j_jnucmat_2022_154183 crossref_primary_10_1016_j_cpc_2020_107206 crossref_primary_10_1103_PhysRevMaterials_5_073801 crossref_primary_10_1016_j_mtcomm_2022_104900 crossref_primary_10_1021_acs_jpclett_4c00322 crossref_primary_10_1038_s41524_024_01251_4 crossref_primary_10_1016_j_cplett_2024_141620 crossref_primary_10_3389_fmats_2024_1466793 crossref_primary_10_1021_acsaem_3c01429 crossref_primary_10_1021_acs_jctc_8b00908 crossref_primary_10_1103_PhysRevMaterials_7_053804 crossref_primary_10_1038_s41467_020_20212_1 crossref_primary_10_1016_j_drudis_2024_103985 crossref_primary_10_1116_6_0004288 crossref_primary_10_1021_acs_jpcc_2c09008 crossref_primary_10_1038_s41524_022_00721_x crossref_primary_10_3390_batteries8100194 crossref_primary_10_1016_j_actamat_2024_120200 crossref_primary_10_1021_jacs_1c10640 crossref_primary_10_1016_j_carbon_2022_03_068 crossref_primary_10_1016_j_ijheatmasstransfer_2024_125404 crossref_primary_10_1557_s43578_022_00783_z crossref_primary_10_1039_D2CP03893E crossref_primary_10_1063_5_0005347 crossref_primary_10_1103_PhysRevMaterials_3_043605 crossref_primary_10_1039_C8CP06919K crossref_primary_10_1103_PhysRevB_105_075107 crossref_primary_10_1088_1361_651X_ad9d63 crossref_primary_10_1002_adfm_202418750 crossref_primary_10_1016_j_patter_2023_100863 crossref_primary_10_1021_acs_jctc_4c01582 crossref_primary_10_1021_acs_jctc_4c01225 crossref_primary_10_1016_j_mtla_2023_101718 crossref_primary_10_1016_j_commt_2024_100018 crossref_primary_10_1063_5_0016004 crossref_primary_10_1038_s43588_023_00406_5 crossref_primary_10_1103_PhysRevMaterials_6_040301 crossref_primary_10_1038_s41524_019_0218_8 crossref_primary_10_1063_5_0063534 crossref_primary_10_1002_adfm_202417891 crossref_primary_10_1126_sciadv_aav6490 crossref_primary_10_1088_2632_2153_abe663 crossref_primary_10_1021_acs_jctc_3c00710 crossref_primary_10_1038_s41524_023_01120_6 crossref_primary_10_1103_PhysRevMaterials_8_025402 crossref_primary_10_1021_acsami_2c16254 crossref_primary_10_1039_C8CP06037A crossref_primary_10_1039_D3CP00746D crossref_primary_10_1038_s41524_024_01227_4 crossref_primary_10_1021_acs_chemmater_2c01430 crossref_primary_10_1038_s41467_021_21488_7 crossref_primary_10_1016_j_commatsci_2019_03_049 crossref_primary_10_1016_j_commatsci_2023_112715 crossref_primary_10_1063_5_0158783 crossref_primary_10_1103_PhysRevB_105_245404 crossref_primary_10_1103_PhysRevB_109_094120 crossref_primary_10_1063_5_0006498 crossref_primary_10_1140_epjb_s10051_021_00156_1 crossref_primary_10_1021_acs_jctc_9b00001 crossref_primary_10_1557_s43578_023_01194_4 crossref_primary_10_1016_j_ijpvp_2021_104514 crossref_primary_10_1063_5_0208577 crossref_primary_10_1038_s41467_020_19093_1 crossref_primary_10_1016_j_commatsci_2022_111330 crossref_primary_10_1103_PhysRevB_104_235205 crossref_primary_10_1016_j_carbon_2022_08_077 crossref_primary_10_1103_PhysRevB_109_094117 crossref_primary_10_1063_5_0007473 crossref_primary_10_1063_1_5126336 crossref_primary_10_1103_PhysRevB_103_094116 crossref_primary_10_1021_acsami_3c07242 crossref_primary_10_1103_PhysRevMaterials_5_113802 crossref_primary_10_1038_s41524_025_01563_z crossref_primary_10_1103_PhysRevB_102_075427 crossref_primary_10_31857_S004445102312012X crossref_primary_10_1063_5_0033778 crossref_primary_10_1021_acs_chemrev_0c01060 crossref_primary_10_1557_s43579_023_00478_4 crossref_primary_10_1016_j_jiec_2024_11_050 crossref_primary_10_1063_5_0133023 crossref_primary_10_31857_S1234567823050099 crossref_primary_10_1016_j_mtphys_2024_101590 crossref_primary_10_1016_j_tsf_2021_138927 crossref_primary_10_1103_PhysRevX_8_041048 crossref_primary_10_1103_PhysRevB_99_184305 crossref_primary_10_1016_j_commatsci_2024_113074 crossref_primary_10_1021_acs_jctc_1c01001 crossref_primary_10_1063_1_5116420 crossref_primary_10_1103_PhysRevMaterials_3_023804 crossref_primary_10_1002_anie_201909987 crossref_primary_10_1063_1_5127561 crossref_primary_10_1103_PhysRevResearch_5_013180 crossref_primary_10_1016_j_cap_2024_07_001 crossref_primary_10_1063_5_0008309 crossref_primary_10_1103_PhysRevB_105_045403 crossref_primary_10_1038_s41467_022_32294_0 crossref_primary_10_1103_PhysRevB_104_094310 crossref_primary_10_1088_2515_7639_ab7cbb crossref_primary_10_1021_acscatal_1c05419 crossref_primary_10_1021_acs_jpcb_2c03746 crossref_primary_10_1088_2632_2153_abfd96 crossref_primary_10_1103_PhysRevLett_124_086102 crossref_primary_10_1088_1361_6528_ac5cfd crossref_primary_10_1021_acs_chemmater_3c00993 crossref_primary_10_1016_j_polymer_2024_127416 crossref_primary_10_1039_D2DD00133K crossref_primary_10_1088_2632_2153_abe294 crossref_primary_10_1103_PhysRevMaterials_8_115407 crossref_primary_10_1557_jmr_2019_50 crossref_primary_10_1021_acs_jctc_7b01195 crossref_primary_10_1021_acs_jpcc_3c04950 crossref_primary_10_1103_PhysRevE_102_052125 crossref_primary_10_1134_S0022476624080109 crossref_primary_10_1103_PhysRevMaterials_5_103803 crossref_primary_10_1016_j_commatsci_2019_04_043 crossref_primary_10_1103_PhysRevB_106_L161110 crossref_primary_10_1103_PhysRevB_100_104103 crossref_primary_10_1038_s41598_022_18366_7 crossref_primary_10_1038_s41524_019_0153_8 crossref_primary_10_1103_PhysRevMaterials_5_053805 crossref_primary_10_1103_PhysRevB_107_144103 crossref_primary_10_1103_PhysRevB_110_014427 crossref_primary_10_1088_1361_648X_ad9657 crossref_primary_10_1038_s41578_020_00255_y crossref_primary_10_1088_0256_307X_41_6_066101 crossref_primary_10_29141_2949_477X_2023_2_4_2 crossref_primary_10_1039_D2DD00034B crossref_primary_10_1002_aenm_201903242 crossref_primary_10_1021_acs_jpclett_0c01061 crossref_primary_10_1039_D2TA02202H crossref_primary_10_1039_D2CP05793J crossref_primary_10_1063_5_0136574 crossref_primary_10_1021_acs_jpcb_3c07187 crossref_primary_10_1063_5_0065694 crossref_primary_10_1088_2516_1075_ac572f crossref_primary_10_1073_pnas_2110077118 crossref_primary_10_1021_acs_jpclett_3c00293 crossref_primary_10_1063_5_0206215 crossref_primary_10_1021_acs_jpca_3c07129 crossref_primary_10_1038_s41467_024_47422_1 crossref_primary_10_1039_D0CE01260B 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_1021_acs_jpcc_0c00047 crossref_primary_10_1038_s41524_022_00872_x crossref_primary_10_3390_coatings12081171 crossref_primary_10_1126_science_adr8450 crossref_primary_10_1063_1_5005095 crossref_primary_10_1016_j_carbon_2021_10_059 crossref_primary_10_1038_s41524_024_01390_8 |
| Cites_doi | 10.1103/PhysRevLett.114.096405 10.1016/j.commatsci.2015.07.046 10.1103/PhysRevLett.104.136403 10.1103/PhysRevB.92.094306 10.1016/0039-6028(94)00731-4 10.1039/c1cp21668f 10.1016/0927-0256(96)00008-0 10.1063/1.1839852 10.1103/PhysRevB.57.R13985 10.1103/PhysRevLett.93.165501 10.1103/PhysRevB.90.104108 10.1016/j.jcp.2014.12.018 10.1021/acs.jctc.5b00211 10.1103/PhysRevLett.108.058301 10.1103/PhysRevLett.108.253002 10.1002/qua.24795 10.1103/PhysRevLett.77.3865 10.1039/C4CP04751F 10.1016/j.commatsci.2016.12.007 10.1103/PhysRevB.54.11169 10.1002/qua.24836 10.1002/qua.25115 10.1103/PhysRevB.95.094203 10.1103/PhysRevLett.98.146401 10.1063/1.4961886 10.1214/aoms/1177729893 10.1103/PhysRevB.88.054104 10.1103/PhysRevB.95.214302 10.1103/PhysRevB.50.17953 10.1016/j.commatsci.2015.11.047 10.1103/PhysRevB.47.558 10.1002/qua.24917 10.1063/1.3553717 10.1103/PhysRevB.87.184115 10.1137/15M1054183 10.1103/PhysRevLett.93.175503 10.1002/(SICI)1521-3951(199909)215:1<809::AID-PSSB809>3.0.CO;2-0 |
| ContentType | Journal Article |
| Copyright | 2017 Elsevier B.V. |
| Copyright_xml | – notice: 2017 Elsevier B.V. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.commatsci.2017.08.031 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1879-0801 |
| EndPage | 180 |
| ExternalDocumentID | 10_1016_j_commatsci_2017_08_031 S0927025617304536 |
| GroupedDBID | --K --M .DC .~1 0R~ 1B1 1~. 1~5 29F 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JN AABXZ AACTN AAEDT AAEDW AAEPC AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO ABFNM ABMAC ABXDB ABXRA ABYKQ ACDAQ ACGFS ACNNM ACRLP ADBBV ADEZE ADMUD AEBSH AECPX AEKER AENEX AEZYN AFKWA AFRZQ AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AI. AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA HLZ HVGLF HZ~ IHE J1W JJJVA KOM LG9 M24 M41 MAGPM MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG RNS ROL RPZ SBC SDF SDG SES SEW SMS SPC SPCBC SPD SSM SST SSZ T5K VH1 WUQ XPP ZMT ~G- AATTM AAXKI AAYWO AAYXX ABJNI ABWVN ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGCQF AGQPQ AGRNS AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP BNPGV CITATION SSH |
| ID | FETCH-LOGICAL-c434t-d0ec5de3e2ee1eaab7951f44bce6aa955b955ca8d148cb9871c270d3bfd064033 |
| IEDL.DBID | .~1 |
| ISSN | 0927-0256 |
| IngestDate | Thu Apr 24 23:07:43 EDT 2025 Tue Jul 01 02:00:52 EDT 2025 Fri Feb 23 02:27:23 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Atomistic simulation Interatomic potential Active learning Learning on the fly Moment tensor potentials Machine learning |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c434t-d0ec5de3e2ee1eaab7951f44bce6aa955b955ca8d148cb9871c270d3bfd064033 |
| PageCount | 10 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_commatsci_2017_08_031 crossref_primary_10_1016_j_commatsci_2017_08_031 elsevier_sciencedirect_doi_10_1016_j_commatsci_2017_08_031 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2017-12-01 |
| PublicationDateYYYYMMDD | 2017-12-01 |
| PublicationDate_xml | – month: 12 year: 2017 text: 2017-12-01 day: 01 |
| PublicationDecade | 2010 |
| PublicationTitle | Computational materials science |
| PublicationYear | 2017 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Boes, Groenenboom, Keith, Kitchin (b0055) 2016; 116 Kresse, Furthmüller (b0205) 1996; 54 Behler (b0045) 2014; 26 Behler, Parrinello (b0050) 2007; 98 Li, Kermode, De Vita (b0145) 2015; 114 Perdew, Burke, Ernzerhof (b0215) 1996; 77 Skylaris, Haynes, Mostofi, Payne (b0010) 2005; 122 Finnis (b0020) 2003; vol. 1 Kresse, Furthmüller (b0200) 1996; 6 Kresse, Hafner (b0195) 1993; 47 Natarajan, Morawietz, Behler (b0075) 2015; 17 Artrith, Urban (b0130) 2016; 114 De Vita, Car (b0180) 1997; vol. 491 Sherman, Morrison (b0190) 1950; 21 Artacho, Sánchez-Portal, Ordejón, García, Soler (b0005) 1999; 215 Artrith, Kolpak (b0025) 2015; 110 Voter, Sørensen (b0230) 1998; vol. 538 Voter (b0220) 1998; 57 Mills, Jónsson, Schenter (b0225) 1995; 324 Szlachta, Bartók, Csányi (b0085) 2014; 90 Botu, Chapman, Ramprasad (b0170) 2017; 129 Goreinov, Oseledets, Savostyanov, Tyrtyshnikov, Zamarashkin (b0175) 2010 Shapeev (b0080) 2016; 14 Botu, Ramprasad (b0140) 2015; 92 Csányi, Albaret, Payne, De Vita (b0185) 2004; 93 B. Settles, Active learning literature survey, Computer Sciences Technical Report 1648, University of Wisconsin–Madison, 2009. Bartók, Payne, Kondor, Csányi (b0035) 2010; 104 Glielmo, Sollich, De Vita (b0150) 2017; 95 Dolgirev, Kruglov, Oganov (b0060) 2016; 6 Rupp, Tkatchenko, Müller, Von Lilienfeld (b0100) 2012; 108 Smith, Isayev, Roitberg (b0125) 2017; 21 Deringer, Csányi (b0135) 2017; 95 Frederiksen, Jacobsen, Brown, Sethna (b0160) 2004; 93 Manzhos, Dawes, Carrington (b0070) 2015; 115 Behler (b0040) 2011; 13 T. Mueller, A.G. Kusne, R. Ramprasad, Machine learning in materials science: recent progress and emerging applications, Rev. Comput. Chem. Bartók, Gillan, Manby, Csányi (b0030) 2013; 88 Faber, Lindmaa, von Lilienfeld, Armiento (b0095) 2015; 115 Behler (b0120) 2011; 134 Botu, Ramprasad (b0165) 2015; 115 Bartók, Kondor, Csányi (b0115) 2013; 87 Bowler, Miyazaki (b0015) 2010; 22 Thompson, Swiler, Trott, Foiles, Tucker (b0090) 2015; 285 Gastegger, Marquetand (b0065) 2015; 11 Snyder, Rupp, Hansen, Müller, Burke (b0105) 2012; 108 Blöchl (b0210) 1994; 50 Boes (10.1016/j.commatsci.2017.08.031_b0055) 2016; 116 Kresse (10.1016/j.commatsci.2017.08.031_b0200) 1996; 6 Thompson (10.1016/j.commatsci.2017.08.031_b0090) 2015; 285 Behler (10.1016/j.commatsci.2017.08.031_b0050) 2007; 98 Li (10.1016/j.commatsci.2017.08.031_b0145) 2015; 114 Goreinov (10.1016/j.commatsci.2017.08.031_b0175) 2010 Bowler (10.1016/j.commatsci.2017.08.031_b0015) 2010; 22 Voter (10.1016/j.commatsci.2017.08.031_b0220) 1998; 57 Behler (10.1016/j.commatsci.2017.08.031_b0040) 2011; 13 Deringer (10.1016/j.commatsci.2017.08.031_b0135) 2017; 95 Artacho (10.1016/j.commatsci.2017.08.031_b0005) 1999; 215 Botu (10.1016/j.commatsci.2017.08.031_b0140) 2015; 92 Artrith (10.1016/j.commatsci.2017.08.031_b0025) 2015; 110 Natarajan (10.1016/j.commatsci.2017.08.031_b0075) 2015; 17 Csányi (10.1016/j.commatsci.2017.08.031_b0185) 2004; 93 Artrith (10.1016/j.commatsci.2017.08.031_b0130) 2016; 114 Finnis (10.1016/j.commatsci.2017.08.031_b0020) 2003; vol. 1 Blöchl (10.1016/j.commatsci.2017.08.031_b0210) 1994; 50 Bartók (10.1016/j.commatsci.2017.08.031_b0115) 2013; 87 Skylaris (10.1016/j.commatsci.2017.08.031_b0010) 2005; 122 Botu (10.1016/j.commatsci.2017.08.031_b0165) 2015; 115 Shapeev (10.1016/j.commatsci.2017.08.031_b0080) 2016; 14 Rupp (10.1016/j.commatsci.2017.08.031_b0100) 2012; 108 Kresse (10.1016/j.commatsci.2017.08.031_b0195) 1993; 47 Frederiksen (10.1016/j.commatsci.2017.08.031_b0160) 2004; 93 De Vita (10.1016/j.commatsci.2017.08.031_b0180) 1997; vol. 491 Sherman (10.1016/j.commatsci.2017.08.031_b0190) 1950; 21 Smith (10.1016/j.commatsci.2017.08.031_b0125) 2017; 21 Dolgirev (10.1016/j.commatsci.2017.08.031_b0060) 2016; 6 Behler (10.1016/j.commatsci.2017.08.031_b0045) 2014; 26 Botu (10.1016/j.commatsci.2017.08.031_b0170) 2017; 129 Voter (10.1016/j.commatsci.2017.08.031_b0230) 1998; vol. 538 Perdew (10.1016/j.commatsci.2017.08.031_b0215) 1996; 77 10.1016/j.commatsci.2017.08.031_b0110 Gastegger (10.1016/j.commatsci.2017.08.031_b0065) 2015; 11 10.1016/j.commatsci.2017.08.031_b0155 Snyder (10.1016/j.commatsci.2017.08.031_b0105) 2012; 108 Mills (10.1016/j.commatsci.2017.08.031_b0225) 1995; 324 Manzhos (10.1016/j.commatsci.2017.08.031_b0070) 2015; 115 Faber (10.1016/j.commatsci.2017.08.031_b0095) 2015; 115 Glielmo (10.1016/j.commatsci.2017.08.031_b0150) 2017; 95 Behler (10.1016/j.commatsci.2017.08.031_b0120) 2011; 134 Szlachta (10.1016/j.commatsci.2017.08.031_b0085) 2014; 90 Kresse (10.1016/j.commatsci.2017.08.031_b0205) 1996; 54 Bartók (10.1016/j.commatsci.2017.08.031_b0030) 2013; 88 Bartók (10.1016/j.commatsci.2017.08.031_b0035) 2010; 104 |
| References_xml | – volume: 215 start-page: 809 year: 1999 end-page: 817 ident: b0005 article-title: Linear-scaling ab-initio calculations for large and complex systems publication-title: Physica Status Solidi (b) – volume: 98 start-page: 146401 year: 2007 ident: b0050 article-title: Generalized neural-network representation of high-dimensional potential-energy surfaces publication-title: Phys. Rev. Lett. – volume: vol. 1 year: 2003 ident: b0020 publication-title: Interatomic Forces in Condensed Matter – volume: 95 start-page: 214302 year: 2017 ident: b0150 article-title: Accurate interatomic force fields via machine learning with covariant kernels publication-title: Phys. Rev. B – volume: vol. 538 start-page: 427 year: 1998 ident: b0230 article-title: Accelerating atomistic simulations of defect dynamics: hyperdynamics, parallel replica dynamics, and temperature-accelerated dynamics publication-title: MRS Proceedings – volume: 13 start-page: 17930 year: 2011 end-page: 17955 ident: b0040 article-title: Neural network potential-energy surfaces in chemistry: a tool for large-scale simulations publication-title: Phys. Chem. Chem. Phys. – volume: 17 start-page: 8356 year: 2015 end-page: 8371 ident: b0075 article-title: Representing the potential-energy surface of protonated water clusters by high-dimensional neural network potentials publication-title: Phys. Chem. Chem. Phys. – volume: 6 start-page: 15 year: 1996 end-page: 50 ident: b0200 article-title: Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set publication-title: Comput. Mater. Sci. – volume: 88 start-page: 054104 year: 2013 ident: b0030 article-title: Machine-learning approach for one-and two-body corrections to density functional theory: applications to molecular and condensed water publication-title: Phys. Rev. B – volume: 87 start-page: 184115 year: 2013 ident: b0115 article-title: On representing chemical environments publication-title: Phys. Rev. B – volume: 324 start-page: 305 year: 1995 end-page: 337 ident: b0225 article-title: Reversible work transition state theory: application to dissociative adsorption of hydrogen publication-title: Surface Sci. – volume: 129 start-page: 332 year: 2017 end-page: 335 ident: b0170 article-title: A study of adatom ripening on an al (111) surface with machine learning force fields publication-title: Comput. Mater. Sci. – volume: 22 start-page: 074207 year: 2010 ident: b0015 article-title: Calculations for millions of atoms with density functional theory: linear scaling shows its potential publication-title: J. Phys.: Condensed Matter – volume: 21 start-page: 124 year: 1950 end-page: 127 ident: b0190 article-title: Adjustment of an inverse matrix corresponding to a change in one element of a given matrix publication-title: Ann. Math. Stat. – volume: 77 start-page: 3865 year: 1996 ident: b0215 article-title: Generalized gradient approximation made simple publication-title: Phys. Rev. Lett. – volume: 57 start-page: R13985 year: 1998 ident: b0220 article-title: Parallel replica method for dynamics of infrequent events publication-title: Phys. Rev. B – volume: 134 start-page: 074106 year: 2011 ident: b0120 article-title: Atom-centered symmetry functions for constructing high-dimensional neural network potentials publication-title: J. Chem. Phys. – reference: T. Mueller, A.G. Kusne, R. Ramprasad, Machine learning in materials science: recent progress and emerging applications, Rev. Comput. Chem. – start-page: 247 year: 2010 end-page: 256 ident: b0175 article-title: How to find a good submatrix publication-title: Matrix Methods: Theory, Algorithms, Applications – volume: 90 start-page: 104108 year: 2014 ident: b0085 article-title: Accuracy and transferability of Gaussian approximation potential models for tungsten publication-title: Phys. Rev. B – volume: 6 start-page: 085318 year: 2016 ident: b0060 article-title: Machine learning scheme for fast extraction of chemically interpretable interatomic potentials publication-title: AIP Adv. – volume: 92 start-page: 094306 year: 2015 ident: b0140 article-title: Learning scheme to predict atomic forces and accelerate materials simulations publication-title: Phys. Rev. B – reference: B. Settles, Active learning literature survey, Computer Sciences Technical Report 1648, University of Wisconsin–Madison, 2009. – volume: 11 start-page: 2187 year: 2015 end-page: 2198 ident: b0065 article-title: High-dimensional neural network potentials for organic reactions and an improved training algorithm publication-title: J. Chem. Theory Comput. – volume: 14 start-page: 1153 year: 2016 end-page: 1173 ident: b0080 article-title: Moment tensor potentials publication-title: Multiscale Model. Simul. – volume: 93 start-page: 165501 year: 2004 ident: b0160 article-title: Bayesian ensemble approach to error estimation of interatomic potentials publication-title: Phys. Rev. Lett. – volume: 115 start-page: 1074 year: 2015 end-page: 1083 ident: b0165 article-title: Adaptive machine learning framework to accelerate ab initio molecular dynamics publication-title: Int. J. Quantum Chem. – volume: 47 start-page: 558 year: 1993 ident: b0195 article-title: Ab initio molecular dynamics for liquid metals publication-title: Phys. Rev. B – volume: 116 start-page: 979 year: 2016 end-page: 987 ident: b0055 article-title: Neural network and ReaxFF comparison for Au properties publication-title: Int. J. Quantum Chem. – volume: vol. 491 start-page: 473 year: 1997 ident: b0180 article-title: A novel scheme for accurate MD simulations of large systems publication-title: MRS Proceedings – volume: 114 start-page: 135 year: 2016 end-page: 150 ident: b0130 article-title: An implementation of artificial neural-network potentials for atomistic materials simulations: performance for tio 2 publication-title: Comput. Mater. Sci. – volume: 108 start-page: 253002 year: 2012 ident: b0105 article-title: Finding density functionals with machine learning publication-title: Phys. Rev. Lett. – volume: 122 start-page: 084119 year: 2005 ident: b0010 article-title: Introducing ONETEP: linear-scaling density functional simulations on parallel computers publication-title: J. Chem. Phys. – volume: 114 start-page: 096405 year: 2015 ident: b0145 article-title: Molecular dynamics with on-the-fly machine learning of quantum-mechanical forces publication-title: Phys. Rev. Lett. – volume: 104 start-page: 136403 year: 2010 ident: b0035 article-title: Gaussian approximation potentials: the accuracy of quantum mechanics, without the electrons publication-title: Phys. Rev. Lett. – volume: 108 start-page: 058301 year: 2012 ident: b0100 article-title: Fast and accurate modeling of molecular atomization energies with machine learning publication-title: Phys. Rev. Lett. – volume: 285 start-page: 316 year: 2015 end-page: 330 ident: b0090 article-title: Spectral neighbor analysis method for automated generation of quantum-accurate interatomic potentials publication-title: J. Comput. Phys. – volume: 26 start-page: 183001 year: 2014 ident: b0045 article-title: Representing potential energy surfaces by high-dimensional neural network potentials publication-title: J. Phys.: Condensed Matter – volume: 93 start-page: 175503 year: 2004 ident: b0185 article-title: Learn on the fly: a hybrid classical and quantum-mechanical molecular dynamics simulation publication-title: Phys. Rev. Lett. – volume: 115 start-page: 1012 year: 2015 end-page: 1020 ident: b0070 article-title: Neural network-based approaches for building high dimensional and quantum dynamics-friendly potential energy surfaces publication-title: Int. J. Quantum Chem. – volume: 50 start-page: 17953 year: 1994 ident: b0210 article-title: Projector augmented-wave method publication-title: Phys. Rev. B – volume: 110 start-page: 20 year: 2015 end-page: 28 ident: b0025 article-title: Grand canonical molecular dynamics simulations of Cu–Au nanoalloys in thermal equilibrium using reactive ANN potentials publication-title: Comput. Mater. Sci. – volume: 115 start-page: 1094 year: 2015 end-page: 1101 ident: b0095 article-title: Crystal structure representations for machine learning models of formation energies publication-title: Int. J. Quantum Chem. – volume: 21 start-page: 124 year: 2017 end-page: 127 ident: b0125 article-title: Ani-1: an extensible neural network potential with DFT accuracy at force field computational cost publication-title: Chem. Sci. – volume: 54 start-page: 11169 year: 1996 ident: b0205 article-title: Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set publication-title: Phys. Rev. B – volume: 95 start-page: 094203 year: 2017 ident: b0135 article-title: Machine learning based interatomic potential for amorphous carbon publication-title: Phys. Rev. B – volume: 114 start-page: 096405 year: 2015 ident: 10.1016/j.commatsci.2017.08.031_b0145 article-title: Molecular dynamics with on-the-fly machine learning of quantum-mechanical forces publication-title: Phys. Rev. Lett. doi: 10.1103/PhysRevLett.114.096405 – volume: 110 start-page: 20 year: 2015 ident: 10.1016/j.commatsci.2017.08.031_b0025 article-title: Grand canonical molecular dynamics simulations of Cu–Au nanoalloys in thermal equilibrium using reactive ANN potentials publication-title: Comput. Mater. Sci. doi: 10.1016/j.commatsci.2015.07.046 – volume: 104 start-page: 136403 year: 2010 ident: 10.1016/j.commatsci.2017.08.031_b0035 article-title: Gaussian approximation potentials: the accuracy of quantum mechanics, without the electrons publication-title: Phys. Rev. Lett. doi: 10.1103/PhysRevLett.104.136403 – volume: 92 start-page: 094306 issue: 9 year: 2015 ident: 10.1016/j.commatsci.2017.08.031_b0140 article-title: Learning scheme to predict atomic forces and accelerate materials simulations publication-title: Phys. Rev. B doi: 10.1103/PhysRevB.92.094306 – volume: 324 start-page: 305 issue: 2–3 year: 1995 ident: 10.1016/j.commatsci.2017.08.031_b0225 article-title: Reversible work transition state theory: application to dissociative adsorption of hydrogen publication-title: Surface Sci. doi: 10.1016/0039-6028(94)00731-4 – volume: 13 start-page: 17930 issue: 40 year: 2011 ident: 10.1016/j.commatsci.2017.08.031_b0040 article-title: Neural network potential-energy surfaces in chemistry: a tool for large-scale simulations publication-title: Phys. Chem. Chem. Phys. doi: 10.1039/c1cp21668f – ident: 10.1016/j.commatsci.2017.08.031_b0110 – volume: vol. 538 start-page: 427 year: 1998 ident: 10.1016/j.commatsci.2017.08.031_b0230 article-title: Accelerating atomistic simulations of defect dynamics: hyperdynamics, parallel replica dynamics, and temperature-accelerated dynamics – volume: 6 start-page: 15 issue: 1 year: 1996 ident: 10.1016/j.commatsci.2017.08.031_b0200 article-title: Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set publication-title: Comput. Mater. Sci. doi: 10.1016/0927-0256(96)00008-0 – volume: 122 start-page: 084119 issue: 8 year: 2005 ident: 10.1016/j.commatsci.2017.08.031_b0010 article-title: Introducing ONETEP: linear-scaling density functional simulations on parallel computers publication-title: J. Chem. Phys. doi: 10.1063/1.1839852 – volume: 57 start-page: R13985 issue: 22 year: 1998 ident: 10.1016/j.commatsci.2017.08.031_b0220 article-title: Parallel replica method for dynamics of infrequent events publication-title: Phys. Rev. B doi: 10.1103/PhysRevB.57.R13985 – volume: 21 start-page: 124 issue: 1 year: 2017 ident: 10.1016/j.commatsci.2017.08.031_b0125 article-title: Ani-1: an extensible neural network potential with DFT accuracy at force field computational cost publication-title: Chem. Sci. – volume: 93 start-page: 165501 issue: 16 year: 2004 ident: 10.1016/j.commatsci.2017.08.031_b0160 article-title: Bayesian ensemble approach to error estimation of interatomic potentials publication-title: Phys. Rev. Lett. doi: 10.1103/PhysRevLett.93.165501 – volume: 90 start-page: 104108 issue: 10 year: 2014 ident: 10.1016/j.commatsci.2017.08.031_b0085 article-title: Accuracy and transferability of Gaussian approximation potential models for tungsten publication-title: Phys. Rev. B doi: 10.1103/PhysRevB.90.104108 – volume: 285 start-page: 316 year: 2015 ident: 10.1016/j.commatsci.2017.08.031_b0090 article-title: Spectral neighbor analysis method for automated generation of quantum-accurate interatomic potentials publication-title: J. Comput. Phys. doi: 10.1016/j.jcp.2014.12.018 – volume: 11 start-page: 2187 issue: 5 year: 2015 ident: 10.1016/j.commatsci.2017.08.031_b0065 article-title: High-dimensional neural network potentials for organic reactions and an improved training algorithm publication-title: J. Chem. Theory Comput. doi: 10.1021/acs.jctc.5b00211 – volume: 108 start-page: 058301 issue: 5 year: 2012 ident: 10.1016/j.commatsci.2017.08.031_b0100 article-title: Fast and accurate modeling of molecular atomization energies with machine learning publication-title: Phys. Rev. Lett. doi: 10.1103/PhysRevLett.108.058301 – volume: 108 start-page: 253002 issue: 25 year: 2012 ident: 10.1016/j.commatsci.2017.08.031_b0105 article-title: Finding density functionals with machine learning publication-title: Phys. Rev. Lett. doi: 10.1103/PhysRevLett.108.253002 – volume: vol. 1 year: 2003 ident: 10.1016/j.commatsci.2017.08.031_b0020 – start-page: 247 year: 2010 ident: 10.1016/j.commatsci.2017.08.031_b0175 article-title: How to find a good submatrix – volume: 115 start-page: 1012 issue: 16 year: 2015 ident: 10.1016/j.commatsci.2017.08.031_b0070 article-title: Neural network-based approaches for building high dimensional and quantum dynamics-friendly potential energy surfaces publication-title: Int. J. Quantum Chem. doi: 10.1002/qua.24795 – volume: 77 start-page: 3865 issue: 18 year: 1996 ident: 10.1016/j.commatsci.2017.08.031_b0215 article-title: Generalized gradient approximation made simple publication-title: Phys. Rev. Lett. doi: 10.1103/PhysRevLett.77.3865 – volume: 26 start-page: 183001 issue: 18 year: 2014 ident: 10.1016/j.commatsci.2017.08.031_b0045 article-title: Representing potential energy surfaces by high-dimensional neural network potentials publication-title: J. Phys.: Condensed Matter – volume: 17 start-page: 8356 issue: 13 year: 2015 ident: 10.1016/j.commatsci.2017.08.031_b0075 article-title: Representing the potential-energy surface of protonated water clusters by high-dimensional neural network potentials publication-title: Phys. Chem. Chem. Phys. doi: 10.1039/C4CP04751F – volume: 129 start-page: 332 year: 2017 ident: 10.1016/j.commatsci.2017.08.031_b0170 article-title: A study of adatom ripening on an al (111) surface with machine learning force fields publication-title: Comput. Mater. Sci. doi: 10.1016/j.commatsci.2016.12.007 – volume: 54 start-page: 11169 issue: 16 year: 1996 ident: 10.1016/j.commatsci.2017.08.031_b0205 article-title: Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set publication-title: Phys. Rev. B doi: 10.1103/PhysRevB.54.11169 – volume: 115 start-page: 1074 issue: 16 year: 2015 ident: 10.1016/j.commatsci.2017.08.031_b0165 article-title: Adaptive machine learning framework to accelerate ab initio molecular dynamics publication-title: Int. J. Quantum Chem. doi: 10.1002/qua.24836 – volume: 116 start-page: 979 issue: 13 year: 2016 ident: 10.1016/j.commatsci.2017.08.031_b0055 article-title: Neural network and ReaxFF comparison for Au properties publication-title: Int. J. Quantum Chem. doi: 10.1002/qua.25115 – volume: 95 start-page: 094203 year: 2017 ident: 10.1016/j.commatsci.2017.08.031_b0135 article-title: Machine learning based interatomic potential for amorphous carbon publication-title: Phys. Rev. B doi: 10.1103/PhysRevB.95.094203 – volume: 98 start-page: 146401 issue: 14 year: 2007 ident: 10.1016/j.commatsci.2017.08.031_b0050 article-title: Generalized neural-network representation of high-dimensional potential-energy surfaces publication-title: Phys. Rev. Lett. doi: 10.1103/PhysRevLett.98.146401 – volume: 6 start-page: 085318 issue: 8 year: 2016 ident: 10.1016/j.commatsci.2017.08.031_b0060 article-title: Machine learning scheme for fast extraction of chemically interpretable interatomic potentials publication-title: AIP Adv. doi: 10.1063/1.4961886 – ident: 10.1016/j.commatsci.2017.08.031_b0155 – volume: 21 start-page: 124 issue: 1 year: 1950 ident: 10.1016/j.commatsci.2017.08.031_b0190 article-title: Adjustment of an inverse matrix corresponding to a change in one element of a given matrix publication-title: Ann. Math. Stat. doi: 10.1214/aoms/1177729893 – volume: 22 start-page: 074207 issue: 7 year: 2010 ident: 10.1016/j.commatsci.2017.08.031_b0015 article-title: Calculations for millions of atoms with density functional theory: linear scaling shows its potential publication-title: J. Phys.: Condensed Matter – volume: 88 start-page: 054104 issue: 5 year: 2013 ident: 10.1016/j.commatsci.2017.08.031_b0030 article-title: Machine-learning approach for one-and two-body corrections to density functional theory: applications to molecular and condensed water publication-title: Phys. Rev. B doi: 10.1103/PhysRevB.88.054104 – volume: 95 start-page: 214302 year: 2017 ident: 10.1016/j.commatsci.2017.08.031_b0150 article-title: Accurate interatomic force fields via machine learning with covariant kernels publication-title: Phys. Rev. B doi: 10.1103/PhysRevB.95.214302 – volume: 50 start-page: 17953 issue: 24 year: 1994 ident: 10.1016/j.commatsci.2017.08.031_b0210 article-title: Projector augmented-wave method publication-title: Phys. Rev. B doi: 10.1103/PhysRevB.50.17953 – volume: 114 start-page: 135 year: 2016 ident: 10.1016/j.commatsci.2017.08.031_b0130 article-title: An implementation of artificial neural-network potentials for atomistic materials simulations: performance for tio 2 publication-title: Comput. Mater. Sci. doi: 10.1016/j.commatsci.2015.11.047 – volume: vol. 491 start-page: 473 year: 1997 ident: 10.1016/j.commatsci.2017.08.031_b0180 article-title: A novel scheme for accurate MD simulations of large systems – volume: 47 start-page: 558 issue: 1 year: 1993 ident: 10.1016/j.commatsci.2017.08.031_b0195 article-title: Ab initio molecular dynamics for liquid metals publication-title: Phys. Rev. B doi: 10.1103/PhysRevB.47.558 – volume: 115 start-page: 1094 issue: 16 year: 2015 ident: 10.1016/j.commatsci.2017.08.031_b0095 article-title: Crystal structure representations for machine learning models of formation energies publication-title: Int. J. Quantum Chem. doi: 10.1002/qua.24917 – volume: 134 start-page: 074106 issue: 7 year: 2011 ident: 10.1016/j.commatsci.2017.08.031_b0120 article-title: Atom-centered symmetry functions for constructing high-dimensional neural network potentials publication-title: J. Chem. Phys. doi: 10.1063/1.3553717 – volume: 87 start-page: 184115 issue: 18 year: 2013 ident: 10.1016/j.commatsci.2017.08.031_b0115 article-title: On representing chemical environments publication-title: Phys. Rev. B doi: 10.1103/PhysRevB.87.184115 – volume: 14 start-page: 1153 issue: 3 year: 2016 ident: 10.1016/j.commatsci.2017.08.031_b0080 article-title: Moment tensor potentials publication-title: Multiscale Model. Simul. doi: 10.1137/15M1054183 – volume: 93 start-page: 175503 issue: 17 year: 2004 ident: 10.1016/j.commatsci.2017.08.031_b0185 article-title: Learn on the fly: a hybrid classical and quantum-mechanical molecular dynamics simulation publication-title: Phys. Rev. Lett. doi: 10.1103/PhysRevLett.93.175503 – volume: 215 start-page: 809 issue: 1 year: 1999 ident: 10.1016/j.commatsci.2017.08.031_b0005 article-title: Linear-scaling ab-initio calculations for large and complex systems publication-title: Physica Status Solidi (b) doi: 10.1002/(SICI)1521-3951(199909)215:1<809::AID-PSSB809>3.0.CO;2-0 |
| SSID | ssj0016982 |
| Score | 2.6435528 |
| Snippet | [Display omitted]
This paper introduces an active learning approach to the fitting of machine learning interatomic potentials. Our approach is based on the... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 171 |
| SubjectTerms | Active learning Atomistic simulation Interatomic potential Learning on the fly Machine learning Moment tensor potentials |
| Title | Active learning of linearly parametrized interatomic potentials |
| URI | https://dx.doi.org/10.1016/j.commatsci.2017.08.031 |
| Volume | 140 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LSwMxEB5KvehBfGJ9lBy8xu5usi8vUoqlKvaihd6WTTaRiu0WWS8e_O3O7KO0IPTgYQ-7ZMIyTL5MmMn3AVzb2FM60jHXrme5tGHKUxH5PDOktxo5vipLMc_jYDSRj1N_2oJBcxeG2ipr7K8wvUTr-kuv9mZvOZv1XpyY7lLh_h9StU8Q7baUIUX5zc-qzcMN4lIwigZzGr3R44VzY16Is1OPV1hyeQr37x1qbdcZHsB-nS6yfvVHh9AyiyPYWyMRPIa7fglZrNZ_eGO5ZZQ7EnMxI2bvOYlmfZuMETUEVdXnM82WeUF9Qhh8JzAZ3r8ORryWReBaClnwzDHaR18azxjXpKkKMUuyUiptgjSNfV_ho9Mow5OOVjGeiDQ6KhPKZlS2E-IU2ot8Yc6ABSJUgUCE0yqUuBQR7BzlZB6RkllMrDoQNK5IdM0ZTtIVH0nTHPaerHyYkA8TErUUbgecleGyos3YbnLb-DrZiIAEwX2b8fl_jC9gl96qJpVLaBefX-YKU41CdctY6sJO_-FpNP4Ft4LWQA |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8NAEB5qe1AP4hPrMwevS5Nunl6kFEtqHxdb6G3JbjZSsQ8kXvz1ziSb0oLgwUMuSSYJH5tvZ5nZ7wN4yKK2VKGKmHLaGXOzIGEJDz2WavJbDW1PFqWY0diPp-7LzJvVoFvthaG2SsP9JacXbG3OtAyarfV83nq1I9pLhfN_QNU-7u9Bg9SpvDo0Ov1BPN4UE_yo8Iyi-xkF7LR54eMxNcQXUJtXUMh5cuf3SWpr4ukdw5HJGK1O-VEnUNPLUzjc0hE8g6dOwVqWsYB4s1aZRekjiRdbJO69IN-sb51apA5BhfXFXFnrVU6tQjj-zmHae550Y2acEZhyuZuz1NbKQzh1W2tHJ4kMMFHKXFcq7SdJ5HkSD5WEKS52lIxwUaQQq5TLLKXKHecXUF-ulvoSLJ8H0udIckoGLv6NyHe2tNM26ZJlmFs1wa-gEMrIhpN7xYeo-sPexQZDQRgK8rXkThPsTeC6VM74O-SxwlrsDAKB_P5X8NV_gu9hP56MhmLYHw-u4YCulD0rN1DPP7_0LWYeubwzI-sHFiTY8Q |
| 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=Active+learning+of+linearly+parametrized+interatomic+potentials&rft.jtitle=Computational+materials+science&rft.au=Podryabinkin%2C+Evgeny+V.&rft.au=Shapeev%2C+Alexander+V.&rft.date=2017-12-01&rft.issn=0927-0256&rft.volume=140&rft.spage=171&rft.epage=180&rft_id=info:doi/10.1016%2Fj.commatsci.2017.08.031&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_commatsci_2017_08_031 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0927-0256&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0927-0256&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0927-0256&client=summon |