Machine Learning Using Digitized Herbarium Specimens to Advance Phenological Research.
biodiversity
climate change
deep learning
machine learning
phenology
Journal
Bioscience
ISSN: 0006-3568
Titre abrégé: Bioscience
Pays: England
ID NLM: 0231737
Informations de publication
Date de publication:
01 Jul 2020
01 Jul 2020
Historique:
entrez:
16
7
2020
pubmed:
16
7
2020
medline:
16
7
2020
Statut:
ppublish
Résumé
Machine learning (ML) has great potential to drive scientific discovery by harvesting data from images of herbarium specimens-preserved plant material curated in natural history collections-but ML techniques have only recently been applied to this rich resource. ML has particularly strong prospects for the study of plant phenological events such as growth and reproduction. As a major indicator of climate change, driver of ecological processes, and critical determinant of plant fitness, plant phenology is an important frontier for the application of ML techniques for science and society. In the present article, we describe a generalized, modular ML workflow for extracting phenological data from images of herbarium specimens, and we discuss the advantages, limitations, and potential future improvements of this workflow. Strategic research and investment in specimen-based ML methods, along with the aggregation of herbarium specimen data, may give rise to a better understanding of life on Earth.
Identifiants
pubmed: 32665738
doi: 10.1093/biosci/biaa044
pii: biaa044
pmc: PMC7340542
doi:
Types de publication
Journal Article
Langues
eng
Pagination
610-620Informations de copyright
© The Author(s) 2020. Published by Oxford University Press on behalf of the American Institute of Biological Sciences.
Références
Proc Natl Acad Sci U S A. 2018 May 1;115(18):4613-4618
pubmed: 29666265
Science. 2013 Mar 29;339(6127):1611-5
pubmed: 23449999
Ecol Lett. 2019 Apr;22(4):616-623
pubmed: 30714287
New Phytol. 2017 Jul;215(1):479-488
pubmed: 28394023
Bioscience. 2020 Jan 1;70(1):23-30
pubmed: 31949317
Int J Biometeorol. 2014 Sep;58(7):1693-7
pubmed: 24018848
Front Plant Sci. 2018 May 01;9:517
pubmed: 29765382
Appl Plant Sci. 2018 Feb 28;6(2):e1022
pubmed: 29732253
Nature. 2003 Jan 2;421(6918):37-42
pubmed: 12511946
Glob Chang Biol. 2013 Jul;19(7):2229-39
pubmed: 23529770
Proc Natl Acad Sci U S A. 2018 Jun 19;115(25):E5716-E5725
pubmed: 29871948
Appl Plant Sci. 2019 Mar 20;7(3):e01233
pubmed: 30937225
Biol Lett. 2014 Nov;10(11):20140586
pubmed: 25411378
Proc Natl Acad Sci U S A. 2017 Sep 26;114(39):10432-10437
pubmed: 28827339
Am J Bot. 2014 Aug;101(8):1293-300
pubmed: 25156979
Nature. 2015 May 28;521(7553):436-44
pubmed: 26017442
BMC Evol Biol. 2016 Nov 16;16(1):248
pubmed: 27852219
Int J Biometeorol. 2019 Jan;63(1):61-72
pubmed: 30382351
Appl Plant Sci. 2019 Mar 07;7(3):e01231
pubmed: 30937223
Nature. 2017 Feb 2;542(7639):115-118
pubmed: 28117445
Proc Biol Sci. 2011 Aug 22;278(1717):2437-45
pubmed: 21227965
Nature. 2012 May 02;485(7399):494-7
pubmed: 22622576
BMC Evol Biol. 2017 Aug 11;17(1):181
pubmed: 28797242
Philos Trans R Soc Lond B Biol Sci. 2018 Nov 19;374(1763):
pubmed: 30455209
Ecology. 2019 Feb;100(2):e02568
pubmed: 30499218
Am J Bot. 2017 Apr;104(4):505-508
pubmed: 28400413
Proc Natl Acad Sci U S A. 2005 Jul 19;102(29):10218-20
pubmed: 16006524
Trends Ecol Evol. 2007 Jul;22(7):357-65
pubmed: 17478009
Appl Plant Sci. 2019 Jul 12;7(7):e11276
pubmed: 31346508
Glob Chang Biol. 2018 Dec;24(12):5972-5984
pubmed: 30218548
Trends Ecol Evol. 2017 Jul;32(7):531-546
pubmed: 28465044