Machine learning-aided real-time detection of keyhole pore generation in laser powder bed fusion
Porosity defects are currently a major factor that hinders the widespread adoption of laser-based metal additive manufacturing technologies. One common porosity occurs when an unstable vapor depression zone (keyhole) forms because of excess laser energy input. With simultaneous high-speed synchrotro...
Gespeichert in:
| Veröffentlicht in: | Science (American Association for the Advancement of Science) Jg. 379; H. 6627; S. 89 |
|---|---|
| Hauptverfasser: | , , , , , , , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
United States
06.01.2023
|
| ISSN: | 1095-9203, 1095-9203 |
| Online-Zugang: | Weitere Angaben |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | Porosity defects are currently a major factor that hinders the widespread adoption of laser-based metal additive manufacturing technologies. One common porosity occurs when an unstable vapor depression zone (keyhole) forms because of excess laser energy input. With simultaneous high-speed synchrotron x-ray imaging and thermal imaging, coupled with multiphysics simulations, we discovered two types of keyhole oscillation in laser powder bed fusion of Ti-6Al-4V. Amplifying this understanding with machine learning, we developed an approach for detecting the stochastic keyhole porosity generation events with submillisecond temporal resolution and near-perfect prediction rate. The highly accurate data labeling enabled by operando x-ray imaging allowed us to demonstrate a facile and practical way to adopt our approach in commercial systems. |
|---|---|
| AbstractList | Porosity defects are currently a major factor that hinders the widespread adoption of laser-based metal additive manufacturing technologies. One common porosity occurs when an unstable vapor depression zone (keyhole) forms because of excess laser energy input. With simultaneous high-speed synchrotron x-ray imaging and thermal imaging, coupled with multiphysics simulations, we discovered two types of keyhole oscillation in laser powder bed fusion of Ti-6Al-4V. Amplifying this understanding with machine learning, we developed an approach for detecting the stochastic keyhole porosity generation events with submillisecond temporal resolution and near-perfect prediction rate. The highly accurate data labeling enabled by operando x-ray imaging allowed us to demonstrate a facile and practical way to adopt our approach in commercial systems.Porosity defects are currently a major factor that hinders the widespread adoption of laser-based metal additive manufacturing technologies. One common porosity occurs when an unstable vapor depression zone (keyhole) forms because of excess laser energy input. With simultaneous high-speed synchrotron x-ray imaging and thermal imaging, coupled with multiphysics simulations, we discovered two types of keyhole oscillation in laser powder bed fusion of Ti-6Al-4V. Amplifying this understanding with machine learning, we developed an approach for detecting the stochastic keyhole porosity generation events with submillisecond temporal resolution and near-perfect prediction rate. The highly accurate data labeling enabled by operando x-ray imaging allowed us to demonstrate a facile and practical way to adopt our approach in commercial systems. Porosity defects are currently a major factor that hinders the widespread adoption of laser-based metal additive manufacturing technologies. One common porosity occurs when an unstable vapor depression zone (keyhole) forms because of excess laser energy input. With simultaneous high-speed synchrotron x-ray imaging and thermal imaging, coupled with multiphysics simulations, we discovered two types of keyhole oscillation in laser powder bed fusion of Ti-6Al-4V. Amplifying this understanding with machine learning, we developed an approach for detecting the stochastic keyhole porosity generation events with submillisecond temporal resolution and near-perfect prediction rate. The highly accurate data labeling enabled by operando x-ray imaging allowed us to demonstrate a facile and practical way to adopt our approach in commercial systems. |
| Author | Shevchenko, Pavel Choi, Ann Rollett, Anthony D Chen, Lianyi Fezzaa, Kamel Sun, Tao Gao, Lin Clark, Samuel J Everhart, Wes Ren, Zhongshu |
| Author_xml | – sequence: 1 givenname: Zhongshu orcidid: 0000-0003-4662-2422 surname: Ren fullname: Ren, Zhongshu organization: Department of Materials Science and Engineering, University of Virginia, Charlottesville, VA 22904, USA – sequence: 2 givenname: Lin orcidid: 0000-0001-8988-7354 surname: Gao fullname: Gao, Lin organization: Department of Materials Science and Engineering, University of Virginia, Charlottesville, VA 22904, USA – sequence: 3 givenname: Samuel J orcidid: 0000-0002-8678-3020 surname: Clark fullname: Clark, Samuel J organization: X-ray Science Division, Advanced Photon Source, Argonne National Laboratory, Lemont, IL 60439, USA – sequence: 4 givenname: Kamel orcidid: 0000-0001-6135-8450 surname: Fezzaa fullname: Fezzaa, Kamel organization: X-ray Science Division, Advanced Photon Source, Argonne National Laboratory, Lemont, IL 60439, USA – sequence: 5 givenname: Pavel orcidid: 0000-0002-7847-472X surname: Shevchenko fullname: Shevchenko, Pavel organization: X-ray Science Division, Advanced Photon Source, Argonne National Laboratory, Lemont, IL 60439, USA – sequence: 6 givenname: Ann orcidid: 0000-0001-5233-8423 surname: Choi fullname: Choi, Ann organization: Department of Materials Science and Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA – sequence: 7 givenname: Wes orcidid: 0000-0001-6253-5527 surname: Everhart fullname: Everhart, Wes organization: Kansas City National Security Campus Managed by Honeywell Federal Manufacturing and Technologies, US Department of Energy, Kansas City, MO 64147, USA – sequence: 8 givenname: Anthony D orcidid: 0000-0003-4445-2191 surname: Rollett fullname: Rollett, Anthony D organization: Department of Materials Science and Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA – sequence: 9 givenname: Lianyi orcidid: 0000-0003-3720-398X surname: Chen fullname: Chen, Lianyi organization: Department of Mechanical Engineering, University of Wisconsin-Madison, Madison, WI 53706, USA – sequence: 10 givenname: Tao orcidid: 0000-0002-4881-9774 surname: Sun fullname: Sun, Tao organization: Department of Materials Science and Engineering, University of Virginia, Charlottesville, VA 22904, USA |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/36603080$$D View this record in MEDLINE/PubMed |
| BookMark | eNpNkElPwzAUhC0EogucuSEfuaR4ixsfUcUmFXGBc3Dsl9aQ2MVOhPrvsaBInOY9faORZmbo2AcPCF1QsqCUyetkHHgDC22tkHJ5hKaUqLJQjPDjf_cEzVJ6JyT_ip-iCZeScFKRKXp70mbrPOAOdPTObwrtLFgcQXfF4HrAFgYwgwsehxZ_wH4bOsC7EAFvwEPUP8h53OkEMYMvm6XJEe2YMjpDJ63uEpwfdI5e725fVg_F-vn-cXWzLowo1VCo0ghqiFS5B2moASUFkEq0oHXLKqssKYUxTS6pDG9aUkrFBddWM6UqADZHV7-5uxg-R0hD3btkoOu0hzCmmi0lVUtecZWtlwfr2PRg6110vY77-m8V9g21VmhJ |
| CitedBy_id | crossref_primary_10_1007_s40820_024_01373_w crossref_primary_10_1016_j_actamat_2024_120464 crossref_primary_10_1080_09507116_2024_2317959 crossref_primary_10_1016_j_addma_2023_103810 crossref_primary_10_1016_j_addma_2024_104506 crossref_primary_10_1016_j_mtcomm_2025_112280 crossref_primary_10_1016_j_optlastec_2023_109472 crossref_primary_10_1016_j_compositesb_2023_111039 crossref_primary_10_3390_met15020106 crossref_primary_10_1016_j_optlastec_2024_112009 crossref_primary_10_1080_17452759_2024_2438899 crossref_primary_10_1007_s10845_023_02119_y crossref_primary_10_1016_j_addma_2025_104750 crossref_primary_10_1002_advs_202412554 crossref_primary_10_1016_j_addma_2024_104195 crossref_primary_10_1016_j_ymssp_2024_111936 crossref_primary_10_1080_17452759_2024_2325572 crossref_primary_10_3390_met13101658 crossref_primary_10_1016_j_optlastec_2025_112761 crossref_primary_10_1016_j_matlet_2025_139331 crossref_primary_10_1016_j_addma_2024_104512 crossref_primary_10_1016_j_amf_2025_200212 crossref_primary_10_1038_s41524_023_01172_8 crossref_primary_10_3390_ma17020432 crossref_primary_10_1016_j_amf_2025_200216 crossref_primary_10_1016_j_jmatprotec_2025_118912 crossref_primary_10_1016_j_jmapro_2024_08_003 crossref_primary_10_1016_j_jmrt_2024_08_028 crossref_primary_10_1016_j_jmrt_2025_05_211 crossref_primary_10_1016_j_jallcom_2025_180543 crossref_primary_10_1016_j_mtcomm_2024_110373 crossref_primary_10_1107_S1600577525000323 crossref_primary_10_1016_j_addma_2024_104218 crossref_primary_10_3390_ma16062424 crossref_primary_10_1016_j_addma_2025_104916 crossref_primary_10_1038_s43246_024_00699_7 crossref_primary_10_1016_j_nima_2023_168690 crossref_primary_10_1016_j_pmatsci_2023_101153 crossref_primary_10_1016_j_cirp_2023_03_031 crossref_primary_10_1016_j_addma_2024_104187 crossref_primary_10_1016_j_addma_2025_104886 crossref_primary_10_1016_j_optlastec_2025_112872 crossref_primary_10_1038_s41578_023_00536_2 crossref_primary_10_1016_j_addma_2025_104921 crossref_primary_10_1016_j_matdes_2024_113181 crossref_primary_10_1016_j_addma_2024_104503 crossref_primary_10_1080_0951192X_2025_2452984 crossref_primary_10_1016_j_addma_2024_104502 crossref_primary_10_1016_j_matdes_2025_113767 crossref_primary_10_1016_j_addma_2024_104501 crossref_primary_10_1016_j_revmat_2025_100010 crossref_primary_10_1016_j_engfracmech_2023_109628 crossref_primary_10_2497_jjspm_17D_T17_09 crossref_primary_10_1016_j_jmrt_2024_08_019 crossref_primary_10_1016_j_addlet_2023_100161 crossref_primary_10_1007_s11465_024_0792_4 crossref_primary_10_1007_s12206_024_2401_1 crossref_primary_10_3390_ma17071569 crossref_primary_10_1016_j_engfracmech_2025_111036 crossref_primary_10_1016_j_mtcomm_2023_106979 crossref_primary_10_1016_j_ijfatigue_2024_108428 crossref_primary_10_1016_j_optlastec_2025_112461 crossref_primary_10_1016_j_ijmachtools_2023_104089 crossref_primary_10_1016_j_ijheatmasstransfer_2025_127781 crossref_primary_10_1016_j_jmapro_2025_01_051 crossref_primary_10_1016_j_optlastec_2025_113432 crossref_primary_10_3390_mi15020243 crossref_primary_10_1007_s00170_025_16031_7 crossref_primary_10_1063_5_0252992 crossref_primary_10_1016_j_addma_2024_104576 crossref_primary_10_1016_j_addma_2025_104692 crossref_primary_10_1016_j_jmst_2023_07_072 crossref_primary_10_1016_j_addma_2024_104057 crossref_primary_10_1016_j_jmapro_2025_03_049 crossref_primary_10_1080_17452759_2024_2424463 crossref_primary_10_1016_j_apsusc_2024_159438 crossref_primary_10_1016_j_matdes_2025_113629 crossref_primary_10_1016_j_csite_2024_105097 crossref_primary_10_1016_j_jmst_2023_05_077 crossref_primary_10_3390_s25144401 crossref_primary_10_1007_s10845_024_02355_w crossref_primary_10_1016_j_addma_2025_104736 crossref_primary_10_1007_s11837_024_06922_7 crossref_primary_10_1016_j_addma_2025_104858 crossref_primary_10_2351_7_0001401 crossref_primary_10_1016_j_ijmecsci_2025_110272 crossref_primary_10_1016_j_optlastec_2024_111341 crossref_primary_10_1039_D4MH01022A crossref_primary_10_1016_j_cirp_2024_04_102 crossref_primary_10_1007_s10845_024_02342_1 crossref_primary_10_1016_j_actamat_2025_121515 crossref_primary_10_1016_j_addma_2024_104323 crossref_primary_10_1016_j_matdes_2024_113443 crossref_primary_10_1088_2631_7990_ad2545 crossref_primary_10_1016_j_rio_2025_100865 crossref_primary_10_1016_j_jmapro_2024_08_054 crossref_primary_10_1080_17452759_2025_2500671 crossref_primary_10_1126_science_ado8554 crossref_primary_10_1016_j_addma_2023_103614 crossref_primary_10_1016_j_procir_2025_03_050 crossref_primary_10_1007_s00170_024_13893_1 crossref_primary_10_1016_j_jmatprotec_2023_118032 crossref_primary_10_1016_j_jmatprotec_2023_118153 crossref_primary_10_1038_s41467_024_45913_9 crossref_primary_10_1126_science_abo7579 crossref_primary_10_1038_s41598_024_64214_1 crossref_primary_10_1016_j_jmapro_2024_04_043 crossref_primary_10_1007_s11665_024_10566_8 crossref_primary_10_1016_j_addma_2025_104833 crossref_primary_10_1016_j_jmapro_2025_09_012 crossref_primary_10_1016_j_fmre_2025_08_006 crossref_primary_10_1038_s44359_025_00109_2 crossref_primary_10_3389_fhpcp_2025_1537080 crossref_primary_10_1016_j_jmapro_2025_03_107 crossref_primary_10_1016_j_bioactmat_2024_03_033 crossref_primary_10_1088_2631_7990_acf96a crossref_primary_10_1016_j_engappai_2025_111807 crossref_primary_10_1016_j_addma_2025_104838 crossref_primary_10_1016_j_jmatprotec_2025_119071 crossref_primary_10_1016_j_ijmachtools_2023_104077 crossref_primary_10_1016_j_jmst_2024_01_092 crossref_primary_10_1016_j_optlastec_2024_112175 crossref_primary_10_1038_s44334_024_00003_y crossref_primary_10_1088_2752_5724_ad89e2 crossref_primary_10_1002_adma_202310006 crossref_primary_10_1016_j_ijheatmasstransfer_2025_127279 crossref_primary_10_1038_s41467_025_60164_y crossref_primary_10_1016_j_commatsci_2024_113185 crossref_primary_10_1007_s10845_023_02117_0 crossref_primary_10_3390_mi16080871 crossref_primary_10_1016_j_addma_2023_103756 crossref_primary_10_1088_2631_7990_ada8e4 crossref_primary_10_3390_met15070787 crossref_primary_10_1002_nano_202400149 crossref_primary_10_1016_j_jmapro_2025_06_027 crossref_primary_10_1016_j_addma_2025_104926 crossref_primary_10_3390_jmmp8060269 crossref_primary_10_1007_s00170_024_14858_0 crossref_primary_10_1007_s00170_023_12771_6 crossref_primary_10_1016_j_apsusc_2025_162384 crossref_primary_10_1007_s11760_025_04077_9 crossref_primary_10_1080_10589759_2025_2533389 crossref_primary_10_1016_j_ijfatigue_2024_108624 crossref_primary_10_1016_j_jmapro_2024_04_023 crossref_primary_10_1016_j_addma_2024_104095 crossref_primary_10_1016_j_jmrt_2024_07_135 crossref_primary_10_1016_j_jmrt_2025_09_025 crossref_primary_10_1016_j_addma_2024_104092 crossref_primary_10_1016_j_addma_2023_103642 crossref_primary_10_1016_j_ymssp_2024_111993 crossref_primary_10_3390_ma17092104 crossref_primary_10_1088_2631_7990_aded4f crossref_primary_10_1016_j_neunet_2024_106794 crossref_primary_10_3390_s24134397 crossref_primary_10_1038_s41598_024_63288_1 crossref_primary_10_1016_j_jmst_2025_05_063 crossref_primary_10_1016_j_ymssp_2025_113256 crossref_primary_10_1016_j_addma_2024_104013 crossref_primary_10_1364_AO_558661 crossref_primary_10_1016_j_addma_2023_103923 crossref_primary_10_1016_j_procir_2024_08_122 crossref_primary_10_1080_17452759_2025_2503258 crossref_primary_10_1080_10426914_2025_2469552 crossref_primary_10_1016_j_jmsy_2024_04_013 crossref_primary_10_3390_nano15191462 crossref_primary_10_1016_j_jmst_2024_07_047 crossref_primary_10_1016_j_addma_2024_104403 crossref_primary_10_1007_s40964_024_00637_6 |
| ContentType | Journal Article |
| DBID | NPM 7X8 |
| DOI | 10.1126/science.add4667 |
| DatabaseName | PubMed MEDLINE - Academic |
| DatabaseTitle | PubMed MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic PubMed |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | no_fulltext_linktorsrc |
| Discipline | Sciences (General) Biology |
| EISSN | 1095-9203 |
| ExternalDocumentID | 36603080 |
| Genre | Journal Article |
| GroupedDBID | --- --Z -DZ -ET -~X .-4 ..I .55 .DC 08G 0B8 0R~ 0WA 123 18M 2FS 2KS 2WC 34G 36B 39C 3R3 53G 5RE 66. 6OB 6TJ 7X2 7~K 85S 8F7 AABCJ AACGO AAIKC AAMNW AANCE AAWTO ABCQX ABDBF ABDQB ABEFU ABIVO ABJNI ABOCM ABPLY ABPPZ ABQIJ ABTLG ABWJO ABZEH ACBEA ACBEC ACGFO ACGFS ACGOD ACIWK ACMJI ACNCT ACPRK ACQOY ACUHS ADDRP ADUKH AEGBM AENEX AEUPB AFFNX AFHKK AFQFN AFRAH AGFXO AGNAY AGSOS AHMBA AIDAL AIDUJ AJGZS ALIPV ALMA_UNASSIGNED_HOLDINGS ASPBG AVWKF BKF BLC C45 CS3 DB2 DU5 EBS EMOBN ESX F5P FA8 FEDTE GX1 HZ~ I.T IAO IEA IGG IGS IH2 IHR INH INR IOF IOV IPO IPY ISE JCF JLS JSG JST K-O KCC L7B LSO LU7 M0P MQT MVM N9A NEJ NHB NPM O9- OCB OFXIZ OGEVE OK1 OMK OVD P-O P2P PQQKQ PZZ RHI RXW SC5 SJN TAE TEORI TN5 TWZ UBW UCV UHB UIG UKR UMD UNMZH UQL USG VQA VVN WH7 WI4 X7M XJF XZL Y6R YCJ YIF YIN YK4 YKV YNT YOJ YR2 YR5 YRY YSQ YV5 YWH YYP YZZ ZCA ZE2 ~02 ~G0 ~KM ~ZZ 2XV 7X8 ADXHL AETEA AFBNE |
| ID | FETCH-LOGICAL-c459t-95c41c069d460b1ce964e084feaaf28d9d054ccb6679c3bf0569343ada2998ee2 |
| IEDL.DBID | 7X8 |
| ISICitedReferencesCount | 201 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000920432900009&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1095-9203 |
| IngestDate | Sun Sep 28 01:13:55 EDT 2025 Wed Feb 19 02:24:26 EST 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 6627 |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c459t-95c41c069d460b1ce964e084feaaf28d9d054ccb6679c3bf0569343ada2998ee2 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0003-4662-2422 0000-0002-8678-3020 0000-0002-4881-9774 0000-0001-6253-5527 0000-0003-4445-2191 0000-0001-5233-8423 0000-0001-6135-8450 0000-0001-8988-7354 0000-0002-7847-472X 0000-0003-3720-398X |
| OpenAccessLink | https://www.osti.gov/servlets/purl/1963710 |
| PMID | 36603080 |
| PQID | 2761973839 |
| PQPubID | 23479 |
| ParticipantIDs | proquest_miscellaneous_2761973839 pubmed_primary_36603080 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-Jan-06 20230106 |
| PublicationDateYYYYMMDD | 2023-01-06 |
| PublicationDate_xml | – month: 01 year: 2023 text: 2023-Jan-06 day: 06 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | Science (American Association for the Advancement of Science) |
| PublicationTitleAlternate | Science |
| PublicationYear | 2023 |
| SSID | ssj0009593 |
| Score | 2.713557 |
| Snippet | Porosity defects are currently a major factor that hinders the widespread adoption of laser-based metal additive manufacturing technologies. One common... |
| SourceID | proquest pubmed |
| SourceType | Aggregation Database Index Database |
| StartPage | 89 |
| Title | Machine learning-aided real-time detection of keyhole pore generation in laser powder bed fusion |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/36603080 https://www.proquest.com/docview/2761973839 |
| Volume | 379 |
| WOSCitedRecordID | wos000920432900009&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3NS8MwFA_qFLyo83N-EcGDHqJpm6bJSUQcHtzYQWW3mSbpGEg396H43_uSZijiQfDSHtKG8vreyy8vye-H0KmjoGNUxURHlBKmTELyiOVERCk8H2c595RCT_dZuy26XdkJBbdJ2FY5z4k-UZuhdjXyy9jNtzOYT8mr0StxqlFudTVIaCyiWgJQxnl11hU_SXcj6vQIY5oEap9vh2YuILwZr0Tmf8eXfpxprv_3CzfQWkCY-LpyiTpasOUmWqk0Jz82UT1E8wSfBcrp8y303PJ7Ki0OIhJ94pgjDQZE-UKc_Dw2duo3bZV4WGAIfCeriwG7W9z3vfimQYkBjNsxNLwbuOXQRTFz9bht9Ni8fbi5I0F7gWiWyimRqWaRplyCeWgeaSs5s1SwwipVxMJIA1hP6xxsJ3WSF4CjZMISZRSMb8LaeActlcPS7iEcGWk1F4WAvgCuUGEhrcRSp0oWPFK0gU7m9uyBb7sFC1Xa4WzS-7JoA-1WP6U3qkg4egnnjmqH7v_h7QO06lTifeWEH6JaAZFtj9CyfpsOJuNj7zRwbXdan0MSzP8 |
| linkProvider | ProQuest |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Machine+learning-aided+real-time+detection+of+keyhole+pore+generation+in+laser+powder+bed+fusion&rft.jtitle=Science+%28American+Association+for+the+Advancement+of+Science%29&rft.au=Ren%2C+Zhongshu&rft.au=Gao%2C+Lin&rft.au=Clark%2C+Samuel+J&rft.au=Fezzaa%2C+Kamel&rft.date=2023-01-06&rft.eissn=1095-9203&rft.volume=379&rft.issue=6627&rft.spage=89&rft_id=info:doi/10.1126%2Fscience.add4667&rft_id=info%3Apmid%2F36603080&rft_id=info%3Apmid%2F36603080&rft.externalDocID=36603080 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1095-9203&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1095-9203&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1095-9203&client=summon |