{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T08:02:34Z","timestamp":1790841754750,"version":"4.1.0"},"reference-count":33,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DBI2223512"],"award-info":[{"award-number":["DBI2223512"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DBI2223508"],"award-info":[{"award-number":["DBI2223508"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["bsapubs.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Appl Plant Sci"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Premise<\/jats:title>\n                    <jats:p>Herbarium specimens represent critical historical records of plant phenology, yet automating annotation of reproductive structures remains challenging given the diversity of floral morphologies, specimen age and quality, and image quality.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Here, we present a machine learning pipeline that uses an ensemble modeling approach to detect flowers on herbarium specimens and deliver these data to the phenology research community. After testing multiple strategies for generating training data, we found that in\u2010house expert\u2010curated annotations were essential for producing reliable results.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Expert validation found that the modeling pipeline detected present floral structures with relatively strong accuracy but had moderately high false negative rates. Applying the ensemble to our filtered final image dataset of 22 million records resulted in 11.1 million records labeled with flowers present. However, only 2.9 million of these contained the complete metadata necessary for downstream phenology research, highlighting the need for full label digitization efforts.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The dataset presented here represents a large compilation of historical herbarium\u2010derived phenology records available as a resource for the phenology community. We end by demonstrating how integrating these machine\u2010labeled records into Phenobase, a publicly available phenology database, expands taxonomic and temporal coverage for large\u2010scale phenological analyses.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/aps3.70085","type":"journal-article","created":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T07:45:25Z","timestamp":1790840725000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Petal to the metal: The slow road to automating large\u2010scale phenology labeling for herbarium specimens"],"prefix":"10.1002","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5928-7515","authenticated-orcid":false,"given":"Erin L.","family":"Grady","sequence":"first","affiliation":[{"name":"Florida Museum of Natural History University of Florida Gainesville Florida USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raphael","family":"LaFrance","sequence":"additional","affiliation":[{"name":"Florida Museum of Natural History University of Florida Gainesville Florida USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0925-3421","authenticated-orcid":false,"given":"Daijiang","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Botany University of Wisconsin\u2013Madison Madison Wisconsin USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0846-2819","authenticated-orcid":false,"given":"Russell","family":"Dinnage","sequence":"additional","affiliation":[{"name":"Department of Biological Sciences University of Alberta Edmonton Alberta Canada"},{"name":"Alberta Machine Intelligence Institute Edmonton Alberta Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2528-6394","authenticated-orcid":false,"given":"Ellen G.","family":"Denny","sequence":"additional","affiliation":[{"name":"USA National Phenology Network, School of Natural Resources and the Environment University of Arizona Tucson Arizona USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5905-1617","authenticated-orcid":false,"given":"John","family":"Deck","sequence":"additional","affiliation":[{"name":"Berkeley Natural History Museums University of California Berkeley California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6682-1504","authenticated-orcid":false,"given":"Robert P.","family":"Guralnick","sequence":"additional","affiliation":[{"name":"Florida Museum of Natural History University of Florida Gainesville Florida USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,10,1]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1002\/aps3.11370"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1093\/biosci\/biac061"},{"key":"e_1_2_8_4_1","unstructured":"Cubuk E. D. B.Zoph D.Mane V.Vasudevan andQ. V.Le.2018. AutoAugment: Learning augmentation policies from data. arXiv:1805.09501 [preprint]. Available athttps:\/\/doi.org\/10.48550\/arXiv.1805.09501[posted 24 May 2018; accessed 21 August 2026]."},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.3732\/ajb.1500237"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1705248114"},{"key":"e_1_2_8_7_1","doi-asserted-by":"crossref","unstructured":"Deng J. W.Dong R.Socher L. J.Li K.Li andL.Fei\u2010Fei.2009. ImageNet: A large\u2010scale hierarchical image database 248\u2013255. 2009 IEEE Conference on Computer Vision and Pattern Recognition 20\u201324 June 2009 Miami Florida USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1111\/2041-210X.70081"},{"key":"e_1_2_8_9_1","unstructured":"Dosovitskiy A. L.Beyer A.Kolesnikov D.Weissenborn X.Zhai T.Unterthiner M.Dehghani et al.2021. An image is worth 16\u00d716 words: Transformers for image recognition at scale. arXiv 11929 [preprint]. Available athttps:\/\/doi.org\/10.48550\/arXiv.2010.11929[revision posted 3 June 2021; accessed 4 September 2026]."},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1111\/1365-2745.13926"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1002\/aps3.11368"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1002\/aps3.70067"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1038\/s43247-024-01807-8"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2022.101641"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1440-1703.2003.00630.x"},{"key":"e_1_2_8_16_1","unstructured":"Loshchilov I. andF.Hutter.2019. Decoupled weight decay regularization. In: International Conference on Learning Representations (ICLR 2019). arXiv:1711.05101v3 [preprint]. Available at:https:\/\/arxiv.org\/abs\/1711.05101[submitted 14 November 2017; revised 4 January 2019; accessed 4 September 2026]."},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1002\/aps3.1233"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.anai.2021.07.012"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2486.2006.01193.x"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00484-019-01719-9"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1093\/biosci\/biaa044"},{"key":"e_1_2_8_22_1","unstructured":"Phenobase Collaboration.2026. Phenobase Web Application. Available at websitehttps:\/\/phenobase.netlify.app\/"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.agrformet.2012.09.012"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2003.1439"},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.3732\/ajb.1700281"},{"key":"e_1_2_8_26_1","doi-asserted-by":"publisher","DOI":"10.1002\/aps3.1028"},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2018.00517"},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.32604\/cmes.2025.063063"},{"key":"e_1_2_8_29_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41559-019-0880-8"},{"key":"e_1_2_8_30_1","doi-asserted-by":"publisher","DOI":"10.1111\/nph.70139"},{"key":"e_1_2_8_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tree.2017.03.015"},{"key":"e_1_2_8_32_1","doi-asserted-by":"publisher","DOI":"10.9734\/ijecc\/2023\/v13i113179"},{"key":"e_1_2_8_33_1","doi-asserted-by":"publisher","DOI":"10.3897\/BDJ.8.e57090"},{"key":"e_1_2_8_34_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1006337"}],"container-title":["Applications in Plant Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/bsapubs.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/aps3.70085","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/bsapubs.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/aps3.70085","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/bsapubs.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/aps3.70085","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T07:45:29Z","timestamp":1790840729000},"score":1,"resource":{"primary":{"URL":"https:\/\/bsapubs.onlinelibrary.wiley.com\/doi\/10.1002\/aps3.70085"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,1]]},"references-count":33,"alternative-id":["10.1002\/aps3.70085"],"URL":"https:\/\/doi.org\/10.1002\/aps3.70085","archive":["Portico"],"relation":{},"ISSN":["2168-0450","2168-0450"],"issn-type":[{"value":"2168-0450","type":"print"},{"value":"2168-0450","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,1]]},"assertion":[{"value":"2025-12-19","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-03","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-10-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70085"}}