Explainable Machine Learning for Scientific Insights and Discoveries

Machine learning methods have been remarkably successful for a wide range of application areas in the extraction of essential information from data. An exciting and relatively recent development is the uptake of machine learning in the natural sciences, where the major goal is to obtain novel scient...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE access Ročník 8; s. 42200 - 42216
Hlavní autoři: Roscher, Ribana, Bohn, Bastian, Duarte, Marco F., Garcke, Jochen
Médium: Journal Article
Jazyk:angličtina
Vydáno: Piscataway IEEE 2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
ISSN:2169-3536, 2169-3536
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Machine learning methods have been remarkably successful for a wide range of application areas in the extraction of essential information from data. An exciting and relatively recent development is the uptake of machine learning in the natural sciences, where the major goal is to obtain novel scientific insights and discoveries from observational or simulated data. A prerequisite for obtaining a scientific outcome is domain knowledge, which is needed to gain explainability, but also to enhance scientific consistency. In this article, we review explainable machine learning in view of applications in the natural sciences and discuss three core elements that we identified as relevant in this context: transparency, interpretability, and explainability. With respect to these core elements, we provide a survey of recent scientific works that incorporate machine learning and the way that explainable machine learning is used in combination with domain knowledge from the application areas.
AbstractList Machine learning methods have been remarkably successful for a wide range of application areas in the extraction of essential information from data. An exciting and relatively recent development is the uptake of machine learning in the natural sciences, where the major goal is to obtain novel scientific insights and discoveries from observational or simulated data. A prerequisite for obtaining a scientific outcome is domain knowledge, which is needed to gain explainability, but also to enhance scientific consistency. In this article, we review explainable machine learning in view of applications in the natural sciences and discuss three core elements that we identified as relevant in this context: transparency, interpretability, and explainability. With respect to these core elements, we provide a survey of recent scientific works that incorporate machine learning and the way that explainable machine learning is used in combination with domain knowledge from the application areas.
Author Duarte, Marco F.
Bohn, Bastian
Roscher, Ribana
Garcke, Jochen
Author_xml – sequence: 1
  givenname: Ribana
  surname: Roscher
  fullname: Roscher, Ribana
  organization: Institute of Geodesy and Geoinformation, University of Bonn, Bonn, Germany
– sequence: 2
  givenname: Bastian
  surname: Bohn
  fullname: Bohn, Bastian
  organization: Institute for Numerical Simulation, University of Bonn, Bonn, Germany
– sequence: 3
  givenname: Marco F.
  surname: Duarte
  fullname: Duarte, Marco F.
  organization: Department of Electrical and Computer Engineering, University of Massachusetts Amherst, Amherst, MA, USA
– sequence: 4
  givenname: Jochen
  orcidid: 0000-0002-8334-3695
  surname: Garcke
  fullname: Garcke, Jochen
  email: jochen.garcke@scai.fraunhofer.de
  organization: Institute for Numerical Simulation, University of Bonn, Bonn, Germany
BookMark eNp9kcFuGyEQhlGVSnVcP4EvK_VsFxYWlmPkOK0lRzm4PSMWBhtrCy5squTtg7tOVeWQucxoNN8_A_81ugoxAEJzgpeEYPn1ZrVa73bLGtd4WUvBiZQf0KQmXC5oQ_nVf_UnNMv5iEu0pdWICbpdP5167YPueqjutTn4ANUWdAo-7CsXU7UzHsLgnTfVJmS_Pwy50sFWtz6b-AeSh_wZfXS6zzC75Cn6ebf-sfq-2D5826xutgvDBBsWrDW14x1o0oBlwIjoajDWcHC46VhLBcW8VFYK5gB40xLLreSWNEJbR-kUbUZdG_VRnZL_pdOzitqrv42Y9kqnwZseFBa6KzsIrikwzrmW5f3E0s50RVO4ovVl1Dql-PsR8qCO8TGFcr6qWcMEbaRoy5Qcp0yKOSdwyvhBDz6GIWnfK4LV2QM1eqDOHqiLB4Wlb9jXi9-n5iPlAeAfITEWovzPC-1tlEU
CODEN IAECCG
CitedBy_id crossref_primary_10_1007_s10601_024_09372_9
crossref_primary_10_1016_j_rse_2023_113628
crossref_primary_10_1016_j_compchemeng_2020_106834
crossref_primary_10_1016_j_jhydrol_2023_129696
crossref_primary_10_1016_j_websem_2023_100806
crossref_primary_10_1016_j_jweia_2022_105027
crossref_primary_10_1371_journal_pclm_0000465
crossref_primary_10_1016_j_plrev_2024_10_011
crossref_primary_10_3390_make4010008
crossref_primary_10_1002_ange_202103272
crossref_primary_10_3390_atmos16050491
crossref_primary_10_1016_j_commatsci_2021_110360
crossref_primary_10_1007_s10710_022_09435_x
crossref_primary_10_1109_MSP_2022_3149471
crossref_primary_10_3390_e24010067
crossref_primary_10_1016_j_earscirev_2020_103359
crossref_primary_10_1016_j_ijfatigue_2021_106356
crossref_primary_10_3390_jcs9030100
crossref_primary_10_3390_w14081230
crossref_primary_10_1007_s10462_022_10275_5
crossref_primary_10_1111_2041_210X_13686
crossref_primary_10_1109_MGRS_2020_3043504
crossref_primary_10_1109_ACCESS_2025_3555926
crossref_primary_10_1038_s41467_024_47228_1
crossref_primary_10_1126_science_abm4470
crossref_primary_10_1088_2632_2153_ad5a60
crossref_primary_10_1016_j_cpc_2025_109761
crossref_primary_10_1016_j_ins_2023_03_066
crossref_primary_10_3390_fire6050190
crossref_primary_10_3390_galaxies9040086
crossref_primary_10_1016_j_jii_2025_100910
crossref_primary_10_1103_PhysRevX_11_031044
crossref_primary_10_1109_ACCESS_2025_3531501
crossref_primary_10_1016_j_rse_2022_113217
crossref_primary_10_1080_15732479_2024_2311911
crossref_primary_10_1145_3583558
crossref_primary_10_3390_fluids7030116
crossref_primary_10_1038_s41598_023_35963_2
crossref_primary_10_1038_s41598_023_39886_w
crossref_primary_10_1016_j_buildenv_2023_110369
crossref_primary_10_1016_j_isprsjprs_2023_11_022
crossref_primary_10_3390_infrastructures8120170
crossref_primary_10_3390_healthcare10040667
crossref_primary_10_1007_s11604_023_01466_3
crossref_primary_10_1007_s10037_024_00207_x
crossref_primary_10_1109_JIOT_2025_3568884
crossref_primary_10_1016_j_soildyn_2024_109071
crossref_primary_10_1016_j_artmed_2022_102394
crossref_primary_10_3389_fgene_2021_618277
crossref_primary_10_1002_cjce_25562
crossref_primary_10_1088_2632_2153_ac9ae8
crossref_primary_10_1038_s41612_022_00269_z
crossref_primary_10_1007_s11023_025_09724_1
crossref_primary_10_1109_TCBB_2022_3191392
crossref_primary_10_1016_j_chemosphere_2023_138975
crossref_primary_10_1016_j_jmapro_2022_09_011
crossref_primary_10_3390_machines11030322
crossref_primary_10_2322_tjsass_66_164
crossref_primary_10_1007_s00521_022_07650_2
crossref_primary_10_1148_rg_220105
crossref_primary_10_1109_JSTARS_2023_3273122
crossref_primary_10_3390_math10234408
crossref_primary_10_1016_j_cjca_2022_02_010
crossref_primary_10_1016_j_apenergy_2023_122351
crossref_primary_10_1016_j_jrmge_2024_09_015
crossref_primary_10_1080_10106049_2022_2076928
crossref_primary_10_1190_geo2022_0594_1
crossref_primary_10_1515_auto_2024_0104
crossref_primary_10_3390_pr9081456
crossref_primary_10_1007_s43681_025_00831_4
crossref_primary_10_1016_j_gexplo_2024_107478
crossref_primary_10_1016_j_est_2023_109057
crossref_primary_10_1108_IJWIS_03_2021_0022
crossref_primary_10_61435_ijred_2024_60387
crossref_primary_10_1016_j_rse_2023_113776
crossref_primary_10_1088_2634_4505_ad63c9
crossref_primary_10_1109_ACCESS_2024_3477553
crossref_primary_10_3389_fmed_2022_1037647
crossref_primary_10_1109_TCSS_2023_3281674
crossref_primary_10_1007_s40685_020_00134_w
crossref_primary_10_1063_5_0045561
crossref_primary_10_1016_j_jmb_2022_167684
crossref_primary_10_1016_j_compag_2025_109990
crossref_primary_10_1057_s41599_023_01505_4
crossref_primary_10_1007_s41976_025_00240_5
crossref_primary_10_1007_s40192_021_00247_y
crossref_primary_10_1038_s41612_023_00387_2
crossref_primary_10_1155_2022_6293856
crossref_primary_10_1038_s41598_023_40513_x
crossref_primary_10_1016_j_oceaneng_2022_111396
crossref_primary_10_1002_wat2_1698
crossref_primary_10_1007_s12665_025_12174_8
crossref_primary_10_1016_j_oneear_2025_101233
crossref_primary_10_1016_j_ifacol_2021_08_273
crossref_primary_10_1016_j_jobe_2025_113956
crossref_primary_10_1017_dce_2025_15
crossref_primary_10_3390_pr10122680
crossref_primary_10_1051_0004_6361_202040152
crossref_primary_10_1109_JSTARS_2020_3039012
crossref_primary_10_1109_MSMC_2020_3036365
crossref_primary_10_1029_2021WR030185
crossref_primary_10_3390_hydrology10020050
crossref_primary_10_1186_s12911_024_02582_4
crossref_primary_10_1049_gtd2_12385
crossref_primary_10_1016_j_ins_2022_11_083
crossref_primary_10_1002_ppap_70035
crossref_primary_10_1061_JIDEDH_IRENG_10441
crossref_primary_10_51847_5P5Jo37fEX
crossref_primary_10_1109_ACCESS_2021_3113381
crossref_primary_10_1007_s10845_022_01999_w
crossref_primary_10_1109_JSTARS_2025_3593779
crossref_primary_10_3389_fams_2024_1355726
crossref_primary_10_1016_j_wasman_2025_114903
crossref_primary_10_1016_j_envdev_2025_101298
crossref_primary_10_1007_s00330_023_09967_5
crossref_primary_10_1002_ecs2_4477
crossref_primary_10_18270_rcfc_4288
crossref_primary_10_1016_j_ijmmb_2022_12_005
crossref_primary_10_1080_17452759_2023_2266641
crossref_primary_10_3390_ani13010120
crossref_primary_10_1016_j_mfglet_2024_09_138
crossref_primary_10_1016_j_jhydrol_2023_129160
crossref_primary_10_1371_journal_pone_0327960
crossref_primary_10_1016_j_advwatres_2023_104463
crossref_primary_10_1093_joc_jqaf036
crossref_primary_10_1007_s11740_024_01306_x
crossref_primary_10_3390_rs13101892
crossref_primary_10_1007_s10489_022_04297_3
crossref_primary_10_1002_2688_8319_12158
crossref_primary_10_1016_j_jmsy_2024_09_009
crossref_primary_10_1109_ACCESS_2025_3562053
crossref_primary_10_1146_annurev_statistics_040120_030919
crossref_primary_10_1002_aisy_202500101
crossref_primary_10_1016_j_eswa_2022_119056
crossref_primary_10_1016_j_mtcomm_2023_105806
crossref_primary_10_1007_s10618_023_00924_w
crossref_primary_10_1088_2632_2153_ad9137
crossref_primary_10_1007_s42979_022_01360_1
crossref_primary_10_1016_j_jtrangeo_2022_103310
crossref_primary_10_1016_j_jcp_2020_110079
crossref_primary_10_1109_TNNLS_2024_3409567
crossref_primary_10_1016_j_ins_2023_118944
crossref_primary_10_1007_s42947_022_00213_7
crossref_primary_10_1016_j_cageo_2022_105248
crossref_primary_10_1016_j_rineng_2024_103328
crossref_primary_10_1111_ele_13462
crossref_primary_10_1007_s00170_022_10444_4
crossref_primary_10_1109_LGRS_2022_3161959
crossref_primary_10_1109_ACCESS_2025_3546720
crossref_primary_10_1145_3644073
crossref_primary_10_1093_jamiaopen_ooae035
crossref_primary_10_1007_s11943_023_00330_0
crossref_primary_10_1080_00207543_2025_2513574
crossref_primary_10_1016_j_ecolind_2025_113308
crossref_primary_10_1016_j_jbi_2022_104278
crossref_primary_10_1364_JOCN_470812
crossref_primary_10_3390_app12178669
crossref_primary_10_1016_j_rser_2024_114804
crossref_primary_10_1007_s11783_024_1780_y
crossref_primary_10_1111_exsy_70017
crossref_primary_10_1016_j_jmsy_2022_04_004
crossref_primary_10_1109_JLT_2021_3106714
crossref_primary_10_1016_j_jag_2022_102869
crossref_primary_10_1103_PhysRevResearch_4_043090
crossref_primary_10_1016_j_jisa_2025_103971
crossref_primary_10_3390_jcm14176201
crossref_primary_10_1016_j_compbiomed_2024_108076
crossref_primary_10_1038_s41467_024_51433_3
crossref_primary_10_3390_bioengineering12060592
crossref_primary_10_3390_s20247326
crossref_primary_10_1007_s10462_023_10525_0
crossref_primary_10_5194_essd_13_3013_2021
crossref_primary_10_1109_TIM_2023_3334350
crossref_primary_10_1007_s00521_022_08100_9
crossref_primary_10_1016_j_amc_2022_127182
crossref_primary_10_1016_j_aei_2024_102843
crossref_primary_10_3390_buildings12060734
crossref_primary_10_1088_2977_3504_ada77b
crossref_primary_10_1109_JBHI_2022_3185290
crossref_primary_10_1007_s11943_023_00331_z
crossref_primary_10_1016_j_engstruct_2024_118271
crossref_primary_10_1016_j_patcog_2024_110794
crossref_primary_10_4213_rm10009
crossref_primary_10_1016_j_segan_2025_101818
crossref_primary_10_1109_ACCESS_2021_3112397
crossref_primary_10_1016_j_jag_2021_102574
crossref_primary_10_1186_s40561_024_00343_4
crossref_primary_10_1109_TNNLS_2022_3190364
crossref_primary_10_1016_j_coche_2022_100818
crossref_primary_10_1016_j_jmsy_2021_10_013
crossref_primary_10_32604_cmc_2022_029969
crossref_primary_10_3390_plants11243485
crossref_primary_10_1016_j_matt_2022_04_016
crossref_primary_10_1109_TVCG_2024_3487974
crossref_primary_10_1109_ACCESS_2025_3539392
crossref_primary_10_3390_s21093004
crossref_primary_10_3390_molecules29153512
crossref_primary_10_1016_j_jksuci_2022_09_005
crossref_primary_10_1186_s40658_022_00522_7
crossref_primary_10_3390_app15168854
crossref_primary_10_1155_2022_2068353
crossref_primary_10_1371_journal_pone_0280987
crossref_primary_10_1016_j_chemolab_2021_104331
crossref_primary_10_1016_j_inffus_2025_102996
crossref_primary_10_1007_s11431_024_2714_4
crossref_primary_10_1080_07294360_2024_2445575
crossref_primary_10_3390_math10152819
crossref_primary_10_1109_TIM_2025_3551952
crossref_primary_10_1007_s00521_022_07942_7
crossref_primary_10_1007_s10596_023_10244_z
crossref_primary_10_1109_MSP_2022_3153277
crossref_primary_10_3390_mti6100095
crossref_primary_10_1080_10447318_2025_2502983
crossref_primary_10_1016_j_eswa_2025_127131
crossref_primary_10_1109_ACCESS_2021_3075620
crossref_primary_10_1007_s10021_022_00789_y
crossref_primary_10_1016_j_inffus_2021_05_009
crossref_primary_10_1007_s00521_022_08042_2
crossref_primary_10_1088_2632_2153_ac09d6
crossref_primary_10_1002_sta4_325
crossref_primary_10_2514_1_J063387
crossref_primary_10_3389_feart_2023_1217384
crossref_primary_10_1038_s43017_025_00697_4
crossref_primary_10_1016_j_chemolab_2021_104354
crossref_primary_10_1016_j_infsof_2024_107448
crossref_primary_10_1063_5_0151290
crossref_primary_10_1038_s41524_022_00884_7
crossref_primary_10_1145_3543847
crossref_primary_10_1007_s11095_022_03448_y
crossref_primary_10_1016_j_buildenv_2022_108894
crossref_primary_10_1016_j_envpol_2023_121832
crossref_primary_10_1038_s41524_023_01133_1
crossref_primary_10_1016_j_cscm_2022_e01059
crossref_primary_10_1038_s41467_023_37418_8
crossref_primary_10_1038_s41598_022_16342_9
crossref_primary_10_1002_aic_17687
crossref_primary_10_1016_j_expneurol_2020_113526
crossref_primary_10_1007_s42979_022_01137_6
crossref_primary_10_1016_j_jsv_2021_116196
crossref_primary_10_1109_ACCESS_2025_3599281
crossref_primary_10_3390_inorganics11030117
crossref_primary_10_3390_make5010006
crossref_primary_10_1109_JPROC_2021_3060483
crossref_primary_10_3390_math11030708
crossref_primary_10_1007_s10664_024_10450_y
crossref_primary_10_1038_s41540_022_00218_9
crossref_primary_10_1111_ffe_13800
crossref_primary_10_2478_vjls_2022_0006
crossref_primary_10_3390_app10196800
crossref_primary_10_1016_j_datak_2024_102285
crossref_primary_10_1080_00084433_2025_2471617
crossref_primary_10_1007_s40747_022_00705_w
crossref_primary_10_1016_j_heliyon_2024_e32930
crossref_primary_10_1007_s42484_024_00191_y
crossref_primary_10_1016_j_eswa_2024_124982
crossref_primary_10_1088_2632_2153_abda08
crossref_primary_10_1016_j_jenvman_2024_121299
crossref_primary_10_1002_ange_201909987
crossref_primary_10_1002_adma_202205294
crossref_primary_10_1002_ange_201909989
crossref_primary_10_1002_adma_202208683
crossref_primary_10_1002_poc_4458
crossref_primary_10_1016_j_apenergy_2024_123550
crossref_primary_10_3390_w14101657
crossref_primary_10_1109_TDSC_2021_3117348
crossref_primary_10_3389_frai_2023_1278118
crossref_primary_10_1038_s41467_023_43809_8
crossref_primary_10_3233_IDT_230065
crossref_primary_10_3389_frwa_2021_745563
crossref_primary_10_3390_jcm12144830
crossref_primary_10_1051_e3sconf_202456601007
crossref_primary_10_1016_j_compeleceng_2023_108918
crossref_primary_10_1080_00207543_2023_2238083
crossref_primary_10_1016_j_eswa_2024_124733
crossref_primary_10_1016_j_cosrev_2021_100452
crossref_primary_10_1007_s44206_024_00142_x
crossref_primary_10_1016_j_cag_2023_06_010
crossref_primary_10_1016_j_toxlet_2025_03_008
crossref_primary_10_1515_labmed_2023_0011
crossref_primary_10_1002_smr_2549
crossref_primary_10_1109_ACCESS_2023_3324906
crossref_primary_10_1109_JSTARS_2022_3159277
crossref_primary_10_1186_s10033_021_00587_y
crossref_primary_10_1016_j_mfglet_2024_09_181
crossref_primary_10_1016_j_comptc_2021_113389
crossref_primary_10_7717_peerj_cs_1188
crossref_primary_10_1016_j_ins_2022_12_012
crossref_primary_10_3390_s21134363
crossref_primary_10_1007_s10838_022_09625_2
crossref_primary_10_1016_j_apenergy_2022_120575
crossref_primary_10_1177_14759217241260254
crossref_primary_10_3390_electronics14050963
crossref_primary_10_1016_j_sab_2022_106490
crossref_primary_10_1088_1748_9326_abfde9
crossref_primary_10_1016_j_rse_2024_114494
crossref_primary_10_29026_oea_2022_210147
crossref_primary_10_1103_PRXQuantum_5_020364
crossref_primary_10_1002_rnc_6457
crossref_primary_10_1016_j_jenvman_2021_112719
crossref_primary_10_1038_s41746_023_00925_5
crossref_primary_10_1016_j_childyouth_2024_107454
crossref_primary_10_1007_s11276_023_03599_9
crossref_primary_10_1111_jedm_12333
crossref_primary_10_1177_10422587221128268
crossref_primary_10_1070_RM10009
crossref_primary_10_1109_TPAMI_2024_3388275
crossref_primary_10_3390_rs12172779
crossref_primary_10_1016_j_engfracmech_2023_109242
crossref_primary_10_1002_asl_1150
crossref_primary_10_3390_bdcc8120171
crossref_primary_10_3390_agronomy15081902
crossref_primary_10_1007_s12283_023_00402_y
crossref_primary_10_1029_2024WR037398
crossref_primary_10_1029_2022WR032183
crossref_primary_10_1016_j_ymssp_2022_110059
crossref_primary_10_1016_j_est_2023_107576
crossref_primary_10_1016_j_buildenv_2024_111394
crossref_primary_10_1080_19427867_2023_2214758
crossref_primary_10_1016_j_nbt_2023_06_002
crossref_primary_10_2139_ssrn_5073392
crossref_primary_10_1007_s11023_024_09691_z
crossref_primary_10_1109_LGRS_2023_3244064
crossref_primary_10_1007_s00477_025_02984_4
crossref_primary_10_1016_j_adapen_2025_100242
crossref_primary_10_1016_j_physrep_2021_10_005
crossref_primary_10_1134_S2070048223020175
crossref_primary_10_3390_jimaging7110245
crossref_primary_10_3390_app142210413
crossref_primary_10_1007_s11356_023_28285_3
crossref_primary_10_1029_2023WR036297
crossref_primary_10_1007_s11740_022_01115_0
crossref_primary_10_3390_info15080460
crossref_primary_10_1016_j_compbiomed_2022_106192
crossref_primary_10_1016_j_compositesa_2024_108019
crossref_primary_10_1093_pnasnexus_pgae461
crossref_primary_10_1029_2021WR031808
crossref_primary_10_1016_j_jwpe_2024_106185
crossref_primary_10_3389_fnhum_2024_1305164
crossref_primary_10_1016_j_compchemeng_2021_107470
crossref_primary_10_1016_j_ejor_2024_06_033
crossref_primary_10_1016_j_mtcomm_2023_106545
crossref_primary_10_3390_rs15184585
crossref_primary_10_1016_j_simpat_2023_102811
crossref_primary_10_1016_j_rineng_2025_107414
crossref_primary_10_1109_LGRS_2024_3404596
crossref_primary_10_3390_app15063139
crossref_primary_10_1109_ACCESS_2024_3420415
crossref_primary_10_1109_ACCESS_2024_3380895
crossref_primary_10_1007_s42979_023_02590_7
crossref_primary_10_1016_j_artmed_2023_102494
crossref_primary_10_3390_make3030037
crossref_primary_10_3390_s22124398
crossref_primary_10_1093_bib_bbae384
crossref_primary_10_3389_frwa_2022_961954
crossref_primary_10_1002_anie_202103272
crossref_primary_10_1088_2632_2153_ac4f69
crossref_primary_10_1109_TGRS_2024_3412629
crossref_primary_10_3390_ijerph20010675
crossref_primary_10_1111_ejss_70071
crossref_primary_10_22207_JPAM_18_1_42
crossref_primary_10_3390_fire8070273
crossref_primary_10_1016_j_neucom_2021_07_100
crossref_primary_10_1038_s12276_024_01243_w
crossref_primary_10_1186_s40645_023_00574_y
crossref_primary_10_1088_2632_2153_adf9bd
crossref_primary_10_3390_infrastructures9120213
crossref_primary_10_1016_j_asr_2025_03_067
crossref_primary_10_1016_j_ifacol_2022_04_202
crossref_primary_10_1016_j_autcon_2025_105992
crossref_primary_10_1002_anie_201909987
crossref_primary_10_1109_TGRS_2022_3140324
crossref_primary_10_3390_en17133295
crossref_primary_10_1002_anie_201909989
crossref_primary_10_1186_s12911_023_02192_6
crossref_primary_10_3390_vetsci10020101
crossref_primary_10_1016_j_adapen_2025_100239
crossref_primary_10_1016_j_envsoft_2020_104954
crossref_primary_10_1007_s12559_023_10219_3
crossref_primary_10_2196_73996
crossref_primary_10_3390_app11052199
crossref_primary_10_3390_batteries11080285
crossref_primary_10_3390_app15105732
crossref_primary_10_1111_tgis_13271
crossref_primary_10_3390_land13050639
crossref_primary_10_1002_batt_202300457
crossref_primary_10_1007_s13218_024_00878_1
crossref_primary_10_1103_PhysRevResearch_7_033042
crossref_primary_10_1038_s41598_024_74875_7
crossref_primary_10_1111_ejss_70161
crossref_primary_10_1016_j_ijpe_2025_109688
crossref_primary_10_1080_17538947_2025_2504137
crossref_primary_10_1007_s10098_020_01993_x
crossref_primary_10_1016_j_artint_2025_104323
crossref_primary_10_1016_j_eswa_2022_118588
crossref_primary_10_1038_s41524_022_00751_5
crossref_primary_10_1016_j_ejps_2025_107173
crossref_primary_10_1016_j_icte_2024_09_008
crossref_primary_10_5194_gmd_18_3707_2025
crossref_primary_10_1016_j_smhl_2022_100347
crossref_primary_10_1016_j_jmatprotec_2023_117908
crossref_primary_10_1002_adma_202106776
crossref_primary_10_1039_D2NR03240F
crossref_primary_10_1016_j_patrec_2021_06_030
crossref_primary_10_1051_0004_6361_202245770
crossref_primary_10_3390_biomedicines13040836
crossref_primary_10_32604_cmc_2025_057359
crossref_primary_10_1016_j_geoderma_2024_117094
crossref_primary_10_1016_j_eneco_2023_106822
crossref_primary_10_1111_ejss_70172
crossref_primary_10_1007_s11135_025_02275_8
crossref_primary_10_3390_rs15204912
crossref_primary_10_2514_1_J061673
crossref_primary_10_1109_ACCESS_2025_3548645
crossref_primary_10_1016_j_engstruct_2023_116231
crossref_primary_10_1016_j_neucom_2024_128111
crossref_primary_10_1088_2633_1357_abec9e
crossref_primary_10_1111_tgis_70034
crossref_primary_10_1016_j_neunet_2022_03_022
crossref_primary_10_1016_j_matt_2023_01_011
crossref_primary_10_2139_ssrn_5384395
crossref_primary_10_1016_j_matdes_2023_112128
crossref_primary_10_3389_fsufs_2024_1363744
crossref_primary_10_1016_j_envpol_2023_121484
crossref_primary_10_1186_s13040_024_00378_w
crossref_primary_10_3389_fmars_2025_1562504
crossref_primary_10_1016_j_compchemeng_2020_107071
crossref_primary_10_1016_j_rineng_2025_106770
crossref_primary_10_1088_2516_1075_ac572f
crossref_primary_10_1140_epjb_s10051_024_00778_1
crossref_primary_10_1016_j_jenvman_2024_120392
crossref_primary_10_1016_j_media_2022_102594
crossref_primary_10_1002_bit_28499
crossref_primary_10_1038_s41598_024_74150_9
crossref_primary_10_1371_journal_pone_0300640
crossref_primary_10_3390_rs17010127
crossref_primary_10_1186_s40634_023_00683_z
crossref_primary_10_17586_2226_1494_2025_25_3_373_386
crossref_primary_10_3390_ijms252312905
crossref_primary_10_1007_s00466_023_02328_5
crossref_primary_10_1007_s41064_022_00217_9
crossref_primary_10_1016_j_compbiomed_2021_104886
crossref_primary_10_1109_TGRS_2025_3595267
crossref_primary_10_1038_s41598_025_05394_2
crossref_primary_10_1021_acsestengg_5c00100
crossref_primary_10_1016_j_cie_2023_109261
crossref_primary_10_32604_cmes_2023_044255
crossref_primary_10_1186_s42162_022_00241_4
crossref_primary_10_1007_s10994_024_06548_5
crossref_primary_10_1016_j_epsr_2022_108489
Cites_doi 10.1016/j.asoc.2018.03.021
10.1073/pnas.1816531116
10.1109/TKDE.2017.2720168
10.1007/s11229-012-0109-8
10.1145/2980179.2982421
10.1073/pnas.1716999115
10.1039/C5MH00282F
10.1109/CVPR.2015.7298903
10.1038/ncomms13890
10.1098/rsif.2017.0387
10.1103/PhysRevB.99.060404
10.1016/j.jag.2017.07.019
10.1001/jamanetworkopen.2019.14645
10.1073/pnas.1302752110
10.1016/j.coisb.2019.04.001
10.1145/3292500.3330921
10.1109/CVPR.2016.383
10.1016/j.media.2019.01.012
10.1038/nmeth.4627
10.1016/j.dsp.2017.10.011
10.1002/widm.1
10.1016/0950-7051(96)81920-4
10.1038/s41524-019-0248-2
10.1073/pnas.1517384113
10.1103/RevModPhys.91.045002
10.1037/0033-2909.110.3.499
10.1002/widm.1312
10.1016/j.artint.2018.07.007
10.1103/PhysRevB.99.104410
10.1016/j.acha.2015.06.008
10.1145/2816795.2818129
10.1021/acs.chemmater.6b01054
10.1016/j.jcp.2017.07.050
10.1145/3236009
10.1016/j.jcp.2016.05.003
10.1038/nbt.3711
10.1038/s41586-019-0912-1
10.1007/s10237-016-0854-6
10.1137/16M1086637
10.1038/s41586-018-0337-2
10.1145/3282486
10.3847/2041-8213/aaf23b
10.1609/aimag.v38i3.2741
10.1126/sciadv.1602614
10.1016/j.jcp.2017.11.039
10.1007/978-0-387-39351-3
10.1371/journal.pcbi.1006565
10.1038/s41573-019-0050-3
10.1017/jfm.2016.615
10.1002/9780470747278
10.1145/3233231
10.1007/s10994-018-5739-8
10.1017/9781108380690
10.1109/TMBMC.2016.2633265
10.1007/s12572-018-0237-6
10.1145/3287560.3287574
10.1073/pnas.1620045114
10.1177/0146167294201001
10.1016/j.jcp.2019.04.015
10.1214/009053607000000677
10.1038/s41467-018-07210-0
10.1109/TVCG.2018.2843369
10.1038/s41467-019-08987-4
10.1038/scientificamerican0483-122
10.1007/s00162-018-0480-2
10.1109/IJCNN.2018.8489767
10.1103/PhysRevE.99.023304
10.1103/PhysRevB.94.195105
10.1103/PhysRevE.95.062122
10.1109/TKDE.2018.2861006
10.1109/ACCESS.2018.2870052
10.1109/TMI.2015.2456188
10.1109/IGARSS.2019.8898749
10.1016/j.joule.2017.10.006
10.1088/1367-2630/aa57bf
10.1145/2939672.2939778
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020
DBID 97E
ESBDL
RIA
RIE
AAYXX
CITATION
7SC
7SP
7SR
8BQ
8FD
JG9
JQ2
L7M
L~C
L~D
DOA
DOI 10.1109/ACCESS.2020.2976199
DatabaseName IEEE Xplore (IEEE)
IEEE Xplore Open Access Journals
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Engineered Materials Abstracts
METADEX
Technology Research Database
Materials Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
Materials Research Database
Engineered Materials Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Advanced Technologies Database with Aerospace
METADEX
Computer and Information Systems Abstracts Professional
DatabaseTitleList Materials Research Database


Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2169-3536
EndPage 42216
ExternalDocumentID oai_doaj_org_article_07abd4e1023e4666a93531d3bcbd6d7f
10_1109_ACCESS_2020_2976199
9007737
Genre orig-research
GrantInformation_xml – fundername: Fraunhofer Cluster of Excellence Cognitive Internet Technologies
– fundername: Deutsche Forschungsgemeinschaft
  funderid: 10.13039/501100001659
GroupedDBID 0R~
4.4
5VS
6IK
97E
AAJGR
ABAZT
ABVLG
ACGFS
ADBBV
AGSQL
ALMA_UNASSIGNED_HOLDINGS
BCNDV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
EBS
EJD
ESBDL
GROUPED_DOAJ
IPLJI
JAVBF
KQ8
M43
M~E
O9-
OCL
OK1
RIA
RIE
RNS
AAYXX
CITATION
7SC
7SP
7SR
8BQ
8FD
JG9
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c474t-48c2f6bea15ed4e417b2ecdc6ef05b483730605bd974fee6581d6d96d157adf33
IEDL.DBID DOA
ISICitedReferencesCount 622
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000525389000018&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2169-3536
IngestDate Fri Oct 03 12:53:06 EDT 2025
Mon Jun 30 04:06:51 EDT 2025
Tue Nov 18 22:19:02 EST 2025
Sat Nov 29 02:42:00 EST 2025
Wed Aug 27 02:35:28 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Language English
License https://creativecommons.org/licenses/by/4.0/legalcode
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c474t-48c2f6bea15ed4e417b2ecdc6ef05b483730605bd974fee6581d6d96d157adf33
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-8334-3695
OpenAccessLink https://doaj.org/article/07abd4e1023e4666a93531d3bcbd6d7f
PQID 2454735978
PQPubID 4845423
PageCount 17
ParticipantIDs crossref_citationtrail_10_1109_ACCESS_2020_2976199
ieee_primary_9007737
proquest_journals_2454735978
doaj_primary_oai_doaj_org_article_07abd4e1023e4666a93531d3bcbd6d7f
crossref_primary_10_1109_ACCESS_2020_2976199
PublicationCentury 2000
PublicationDate 20200000
2020-00-00
20200101
2020-01-01
PublicationDateYYYYMMDD 2020-01-01
PublicationDate_xml – year: 2020
  text: 20200000
PublicationDecade 2020
PublicationPlace Piscataway
PublicationPlace_xml – name: Piscataway
PublicationTitle IEEE access
PublicationTitleAbbrev Access
PublicationYear 2020
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref56
ref59
ref58
li (ref91) 2019
brookes (ref48) 2019
ehrhardt (ref7) 2017
choi (ref76) 2016
saltelli (ref19) 2004
eigel (ref57) 2018
ref51
singh (ref75) 2017
ref45
lerer (ref39) 2016
ref42
ref41
ref44
ref43
iten (ref100) 2018
ref8
ref9
samek (ref1) 2018; 1
ref3
ref5
ref35
ref34
ref37
ref30
ref33
pinho (ref68) 2018; 5
ref32
olah (ref22) 2018; 3
abbasi-asl (ref70) 2018
ouyang (ref94) 2018; 2
ref38
ye (ref101) 2018
li (ref40) 2016
ref24
ref26
ref25
ref20
ref21
ref28
ref27
ref29
tompson (ref49) 2017
breen (ref46) 2018
deming (ref74) 2016
chang (ref52) 2017
schölkopf (ref117) 2019
monszpart (ref55) 2016; 35
wu (ref54) 2016
ref12
ref97
frigg (ref4) 2018
goodfellow (ref14) 2016
macdonald (ref23) 2019
ref99
ref98
ref10
raissi (ref36) 2017
ref17
camps-valls (ref105) 2018; 68
ref16
ref18
ladický (ref50) 2015; 34
liao (ref31) 2017
ref93
ref95
butler (ref108) 2018; 559
von rueden (ref2) 2019
ref89
ref86
doshi-velez (ref6) 2017
ref88
ref87
meila (ref92) 2018
groth (ref67) 2018
ref82
ref81
ref84
ref83
dai (ref90) 2018
ref80
ref78
ref109
ref106
ref107
ref104
ref77
ref102
rieger (ref79) 2019
tanaka (ref96) 2019
ref71
ref111
ref112
ref73
ref72
tsang (ref103) 2018
ref110
brookes (ref47) 2018
ref69
ref64
ref115
ref63
charles (ref15) 2018
ref66
ref113
ref65
ref114
stewart (ref53) 2017; 1
brunton (ref85) 2016; 113
rasmussen (ref13) 2006
ref60
ref62
ref61
james murdoch (ref11) 2019
pearl (ref116) 2011
References_xml – year: 2011
  ident: ref116
  publication-title: Causality Models Reasoning and Inference
– volume: 68
  year: 2018
  ident: ref105
  article-title: Physics-aware Gaussian processes in remote sensing
  publication-title: Appl Soft Comput
  doi: 10.1016/j.asoc.2018.03.021
– year: 2018
  ident: ref46
  article-title: Deep learning model integration of remotely sensed and SWAT-simulated regional soil moisture
  publication-title: AGU Fall Meeting Abstracts
– start-page: 1
  year: 2018
  ident: ref103
  article-title: Detecting statistical interactions from neural network weights
  publication-title: Proc ICLR
– ident: ref99
  doi: 10.1073/pnas.1816531116
– year: 2018
  ident: ref57
  article-title: Variational Monte Carlo-bridging concepts of machine learning and high dimensional partial differential equations
  publication-title: arXiv 1810 01348
– ident: ref35
  doi: 10.1109/TKDE.2017.2720168
– start-page: 7
  year: 2016
  ident: ref54
  article-title: Physics 101: Learning physical object properties from unlabeled videos
  publication-title: Proc Brit Mach Vis Conf
– ident: ref30
  doi: 10.1007/s11229-012-0109-8
– year: 2017
  ident: ref36
  article-title: Physics informed deep learning (part II): Data-driven discovery of nonlinear partial differential equations
  publication-title: arXiv 1711 10566
– volume: 35
  start-page: 1
  year: 2016
  ident: ref55
  article-title: SMASH: Physics-guided reconstruction of collisions from videos
  publication-title: ACM Trans Graph
  doi: 10.1145/2980179.2982421
– ident: ref66
  doi: 10.1073/pnas.1716999115
– ident: ref59
  doi: 10.1039/C5MH00282F
– start-page: 430
  year: 2016
  ident: ref39
  article-title: Learning physical intuition of block towers by example
  publication-title: Proc 33rd Int Conf Mach Learn
– ident: ref45
  doi: 10.1109/CVPR.2015.7298903
– ident: ref104
  doi: 10.1038/ncomms13890
– ident: ref111
  doi: 10.1098/rsif.2017.0387
– ident: ref106
  doi: 10.1103/PhysRevB.99.060404
– ident: ref51
  doi: 10.1016/j.jag.2017.07.019
– ident: ref72
  doi: 10.1001/jamanetworkopen.2019.14645
– ident: ref88
  doi: 10.1073/pnas.1302752110
– year: 2019
  ident: ref23
  article-title: A rate-distortion framework for explaining neural network decisions
  publication-title: arXiv 1905 11092
– year: 2017
  ident: ref31
  article-title: Object-oriented deep learning
– ident: ref112
  doi: 10.1016/j.coisb.2019.04.001
– ident: ref102
  doi: 10.1145/3292500.3330921
– ident: ref56
  doi: 10.1109/CVPR.2016.383
– start-page: 702
  year: 2018
  ident: ref67
  article-title: Shapestacks: Learning vision-based physical intuition for generalised object stacking
  publication-title: Proc Eur Conf Comput Vis (ECCV)
– ident: ref73
  doi: 10.1016/j.media.2019.01.012
– ident: ref98
  doi: 10.1038/nmeth.4627
– ident: ref10
  doi: 10.1016/j.dsp.2017.10.011
– ident: ref26
  doi: 10.1002/widm.1
– ident: ref17
  doi: 10.1016/0950-7051(96)81920-4
– start-page: 3504
  year: 2016
  ident: ref76
  article-title: Retain: An interpretable predictive model for healthcare using reverse time attention mechanism
  publication-title: Proc Adv Neural Inf Process Syst
– start-page: 8535
  year: 2019
  ident: ref96
  article-title: From deep learning to mechanistic understanding in neuroscience: The structure of retinal prediction
  publication-title: Proc Adv Neural Inf Process Syst
– year: 2018
  ident: ref92
  article-title: A regression approach for explaining manifold embedding coordinates
  publication-title: arXiv 1811 11891
– year: 2018
  ident: ref100
  article-title: Discovering physical concepts with neural networks
  publication-title: arXiv 1807 10300
– ident: ref78
  doi: 10.1038/s41524-019-0248-2
– volume: 113
  start-page: 3932
  year: 2016
  ident: ref85
  article-title: Discovering governing equations from data by sparse identification of nonlinear dynamical systems
  publication-title: Proc Nat Acad Sci USA
  doi: 10.1073/pnas.1517384113
– year: 2016
  ident: ref74
  article-title: Genetic architect: Discovering genomic structure with learned neural architectures
  publication-title: arXiv 1605 07156
– ident: ref109
  doi: 10.1103/RevModPhys.91.045002
– ident: ref34
  doi: 10.1037/0033-2909.110.3.499
– ident: ref113
  doi: 10.1002/widm.1312
– volume: 3
  start-page: 10e
  year: 2018
  ident: ref22
  article-title: The building blocks of interpretability
  publication-title: Distillation
– ident: ref29
  doi: 10.1016/j.artint.2018.07.007
– ident: ref107
  doi: 10.1103/PhysRevB.99.104410
– ident: ref81
  doi: 10.1016/j.acha.2015.06.008
– volume: 34
  start-page: 1
  year: 2015
  ident: ref50
  article-title: Data-driven fluid simulations using regression forests
  publication-title: ACM Trans Graph
  doi: 10.1145/2816795.2818129
– ident: ref42
  doi: 10.1021/acs.chemmater.6b01054
– ident: ref61
  doi: 10.1016/j.jcp.2017.07.050
– ident: ref8
  doi: 10.1145/3236009
– ident: ref64
  doi: 10.1016/j.jcp.2016.05.003
– ident: ref110
  doi: 10.1038/nbt.3711
– year: 2019
  ident: ref117
  article-title: Causality for machine learning
  publication-title: arXiv 1911 10500
– ident: ref37
  doi: 10.1038/s41586-019-0912-1
– start-page: 3424
  year: 2017
  ident: ref49
  article-title: Accelerating Eulerian fluid simulation with convolutional networks
  publication-title: Proc ICML
– volume: 1
  start-page: 1
  year: 2017
  ident: ref53
  article-title: Label-free supervision of neural networks with physics and domain knowledge
  publication-title: Proc AAAI
– year: 2018
  ident: ref47
  article-title: Design by adaptive sampling
  publication-title: arXiv 1810 03714
– ident: ref58
  doi: 10.1007/s10237-016-0854-6
– volume: 1
  start-page: 39
  year: 2018
  ident: ref1
  article-title: Explainable artificial intelligence: Understanding, visualizing and interpreting deep learning models
  publication-title: ITU J ICT Discoveries-Impact Artif Intell (AI) Commun Netw Services
– ident: ref89
  doi: 10.1137/16M1086637
– start-page: 1
  year: 2017
  ident: ref52
  article-title: A compositional object-based approach to learning physical dynamics
  publication-title: Proc ICLR
– year: 2019
  ident: ref11
  article-title: Interpretable machine learning: Definitions, methods, and applications
  publication-title: arXiv 1901 04592
– year: 2006
  ident: ref13
  publication-title: Gaussian Processes for Machine Learning
– volume: 559
  start-page: 547
  year: 2018
  ident: ref108
  article-title: Machine learning for molecular and materials science
  publication-title: Nature
  doi: 10.1038/s41586-018-0337-2
– ident: ref3
  doi: 10.1145/3282486
– year: 2019
  ident: ref2
  article-title: Informed machine learning - a taxonomy and survey of integrating knowledge into learning systems
  publication-title: arXiv 1903 12394
– year: 2017
  ident: ref7
  article-title: Learning a physical long-term predictor
  publication-title: arXiv 1703 00247
– year: 2018
  ident: ref70
  article-title: The deeptune framework for modeling and characterizing neurons in visual cortex area v4
  publication-title: BioRxiv
– ident: ref44
  doi: 10.3847/2041-8213/aaf23b
– ident: ref32
  doi: 10.1609/aimag.v38i3.2741
– year: 2004
  ident: ref19
  publication-title: Sensitivity Analysis in Practice A Guide to Assessing Scientific Models
– ident: ref87
  doi: 10.1126/sciadv.1602614
– year: 2018
  ident: ref15
  article-title: Interpreting deep learning: The machine learning rorschach test?
  publication-title: arXiv 1806 00148
– ident: ref43
  doi: 10.1016/j.jcp.2017.11.039
– start-page: 1
  year: 2018
  ident: ref90
  article-title: Syntax-directed variational autoencoder for structured data
  publication-title: Proc ICLR
– ident: ref24
  doi: 10.1007/978-0-387-39351-3
– ident: ref69
  doi: 10.1371/journal.pcbi.1006565
– ident: ref114
  doi: 10.1038/s41573-019-0050-3
– ident: ref62
  doi: 10.1017/jfm.2016.615
– ident: ref25
  doi: 10.1002/9780470747278
– ident: ref9
  doi: 10.1145/3233231
– year: 2019
  ident: ref79
  article-title: Interpretations are useful: Penalizing explanations to align neural networks with prior knowledge
  publication-title: arXiv 1909 13584
– ident: ref71
  doi: 10.1007/s10994-018-5739-8
– ident: ref5
  doi: 10.1017/9781108380690
– ident: ref86
  doi: 10.1109/TMBMC.2016.2633265
– year: 2016
  ident: ref40
  article-title: To fall or not to fall: A visual approach to physical stability prediction
  publication-title: arXiv 1604 00066
– ident: ref95
  doi: 10.1007/s12572-018-0237-6
– year: 2019
  ident: ref48
  article-title: Conditioning by adaptive sampling for robust design
  publication-title: arXiv 1901 10060
– ident: ref28
  doi: 10.1145/3287560.3287574
– start-page: 87
  year: 2018
  ident: ref101
  article-title: Interpretable intuitive physics model
  publication-title: Proc Eur Conf Comput Vis (ECCV)
– ident: ref80
  doi: 10.1073/pnas.1620045114
– ident: ref33
  doi: 10.1177/0146167294201001
– ident: ref82
  doi: 10.1016/j.jcp.2019.04.015
– year: 2018
  ident: ref4
  article-title: Scientific representation
  publication-title: The Stanford Encyclopedia of Philosophy
– volume: 5
  start-page: 180
  year: 2018
  ident: ref68
  article-title: Individual brain charting, a high-resolution fMRI dataset for cognitive mapping
  publication-title: Data Science Journal
– ident: ref12
  doi: 10.1214/009053607000000677
– year: 2017
  ident: ref6
  article-title: Towards a rigorous science of interpretable machine learning
  publication-title: arXiv 1702 08608
– ident: ref97
  doi: 10.1038/s41467-018-07210-0
– ident: ref21
  doi: 10.1109/TVCG.2018.2843369
– volume: 2
  start-page: 1
  year: 2018
  ident: ref94
  article-title: SISSO: A compressed-sensing method for identifying the best low-dimensional descriptor in an immensity of offered candidates
  publication-title: Phys Rev Mater
– start-page: 6785
  year: 2017
  ident: ref75
  article-title: Attend and predict: Understanding gene regulation by selective attention on chromatin
  publication-title: Proc Adv Neural Inf Process Syst
– year: 2019
  ident: ref91
  article-title: Neural-guided symbolic regression with asymptotic constraints
  publication-title: arXiv 1901 07714
– ident: ref27
  doi: 10.1038/s41467-019-08987-4
– ident: ref38
  doi: 10.1038/scientificamerican0483-122
– ident: ref63
  doi: 10.1007/s00162-018-0480-2
– ident: ref77
  doi: 10.1109/IJCNN.2018.8489767
– ident: ref16
  doi: 10.1103/PhysRevE.99.023304
– ident: ref84
  doi: 10.1103/PhysRevB.94.195105
– ident: ref83
  doi: 10.1103/PhysRevE.95.062122
– ident: ref115
  doi: 10.1109/TKDE.2018.2861006
– ident: ref20
  doi: 10.1109/ACCESS.2018.2870052
– year: 2016
  ident: ref14
  publication-title: Deep Learning
– ident: ref65
  doi: 10.1109/TMI.2015.2456188
– ident: ref41
  doi: 10.1109/IGARSS.2019.8898749
– ident: ref60
  doi: 10.1016/j.joule.2017.10.006
– ident: ref93
  doi: 10.1088/1367-2630/aa57bf
– ident: ref18
  doi: 10.1145/2939672.2939778
SSID ssj0000816957
Score 2.6630812
Snippet Machine learning methods have been remarkably successful for a wide range of application areas in the extraction of essential information from data. An...
SourceID doaj
proquest
crossref
ieee
SourceType Open Website
Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 42200
SubjectTerms Approximation algorithms
Biological system modeling
Data mining
Data models
Domains
Explainable machine learning
informed machine learning
interpretability
Kernel
Machine learning
Mathematical model
scientific consistency
transparency
SummonAdditionalLinks – databaseName: IEEE Electronic Library (IEL)
  dbid: RIE
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8QwEB5UPOjBt7i-yMHjVvtIm81RV0UPLh4UvIU0DxGkit319zuTxqIogrdQkpDky-tLZ74BOLLeao4nXyI89wnOkBr3QaOT0ufeSC6z3PIQbEJMJqOHB3k7B8PeF8Y5F4zP3DElw798-2Jm9FR2Ikl8phDzMC9E1flq9e8pFEBCliIKC2WpPDkdj7EPSAHz9DiXRNflt8MnaPTHoCo_duJwvFyu_q9ha7ASr5HstMN9HeZcswHLX8QFN-GczOuibxS7CTaTjkU51UeGd1UW1nWwFWLXTUssvWW6sez8qTVk2YkkegvuLy_uxldJjJmQGC74FEfb5L6qnc5KZ7njmahzZ6ypnE_LmuTjkSNgyiKP8M7h_SOzlZWVzUqhrS-KbVhoXhq3A6zAajwvUkNOliO8RmmDZExLIzNfWF4NIP8cTGWioDjFtXhWgVikUnUIKEJARQQGMOwLvXZ6Gn9nPyOU-qwkhh0-4PCruLZUKnSNfSURCseRjmlZ4M5ii9rU2DfhB7BJkPWVRLQGsP-JuYoLt1U5D8GYkVvv_l5qD5aogd0rzD4sTN9m7gAWzfv0qX07DHPyA96I3wM
  priority: 102
  providerName: IEEE
Title Explainable Machine Learning for Scientific Insights and Discoveries
URI https://ieeexplore.ieee.org/document/9007737
https://www.proquest.com/docview/2454735978
https://doaj.org/article/07abd4e1023e4666a93531d3bcbd6d7f
Volume 8
WOSCitedRecordID wos000525389000018&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2169-3536
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000816957
  issn: 2169-3536
  databaseCode: DOA
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2169-3536
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000816957
  issn: 2169-3536
  databaseCode: M~E
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV07T8MwELZQxQADAgoiUCoPjIQmsRPXY-lDMLRiAKmb5fiBKqGAmsLIb-fsuFUREiwsURQ5D38-n--Lzt8hdKWtlhRWvphZamOwkBL8oJJxbjOrOOVppqkvNsFms_58zh-2Sn25nLBGHrgBrpcwWWpqnMKAoRBrS07AbDQpVakLzazzvgnjW2TK--B-WvCcBZmhNOG9wXAIPQJCmCU3GXfknX9birxifyix8sMv-8VmcogOQpSIB83XHaEdUx2j_S3twDYauey5sPUJT31KpMFBLfUZQyiK_bT1qUD4vqodCa-xrDQeLWrlEjeBI5-gp8n4cXgXh5IIsaKMrgBMldmiNDLNDaBCU1ZmRmlVGJvkpVOHBwoAZxpogjUGwosUUOKFTnMmtSXkFLWq18qcIUzgMZaSRLk9lH2IkqQCriW54qklmhYRytboCBX0wl3ZihfheUPCRQOpcJCKAGmErjc3vTVyGb83v3Wwb5o6rWt_ASxABAsQf1lAhNpu0DYP4U6iiLAIddaDKMK8rEVGfa1loM7n__HqC7TnutP8kumg1mr5bi7RrvpYLepl15skHKef467fWPgFz0PkgA
linkProvider Directory of Open Access Journals
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT9wwEB7RpVLbA49C1eVVHzgSSBwnXh9hAYEKKw5U4mY5flRIVUBk6e_vjGMiEBUSNyuyLdufX58z8w3ArgvOCDz5MhlEyHCGNLgPWpNVgQerhCq4EzHYhJzNJjc36moB9gZfGO99ND7z-5SM__LdnX2kp7IDReIzpfwAi5UQPO-9tYYXFQohoSqZpIWKXB0cTqfYCySBPN_nigi7enH8RJX-FFbl1V4cD5jT5fc1bQWW0kWSHfbIr8KCb7_Cl2fygmtwTAZ2yTuKXUarSc-SoOpvhrdVFld2tBZi521HPL1jpnXs-LazZNuJNHodfp2eXE_PshQ1IbNCijmOt-WhbrwpKu-EF4VsuLfO1j7kVUMC8sgSMOWQSQTv8QZSuNqp2hWVNC6U5TcYtXet_w6sxGqCKHNLbpYTvEgZi3TMKKuKUDpRj4E_Daa2SVKcIlv80ZFa5Er3CGhCQCcExrA3FLrvFTXezn5EKA1ZSQ47fsDh12l16VyaBvtKMhReICEzqsS9xZWNbbBvMoxhjSAbKklojWHrCXOdlm6nuYjhmJFdb_y_1A_4dHZ9eaEvzmc_N-EzNbZ_k9mC0fzh0W_DR_t3fts97MT5-Q-eQuJK
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=Explainable+Machine+Learning+for+Scientific+Insights+and+Discoveries&rft.jtitle=IEEE+access&rft.au=Roscher%2C+Ribana&rft.au=Bohn%2C+Bastian&rft.au=Duarte%2C+Marco+F.&rft.au=Garcke%2C+Jochen&rft.date=2020&rft.issn=2169-3536&rft.eissn=2169-3536&rft.volume=8&rft.spage=42200&rft.epage=42216&rft_id=info:doi/10.1109%2FACCESS.2020.2976199&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_ACCESS_2020_2976199
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2169-3536&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2169-3536&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2169-3536&client=summon