Phenomics based prediction of plant biomass and leaf area in wheat using machine learning approaches.
NIR image
RGB image
high-throughput phenotyping (HTP)
i-traits
machine learning
shoot area
wheat
Journal
Frontiers in plant science
ISSN: 1664-462X
Titre abrégé: Front Plant Sci
Pays: Switzerland
ID NLM: 101568200
Informations de publication
Date de publication:
2023
2023
Historique:
received:
30
04
2023
accepted:
07
06
2023
medline:
14
7
2023
pubmed:
14
7
2023
entrez:
14
7
2023
Statut:
epublish
Résumé
Phenomics has emerged as important tool to bridge the genotype-phenotype gap. To dissect complex traits such as highly dynamic plant growth, and quantification of its component traits over a different growth phase of plant will immensely help dissect genetic basis of biomass production. Based on RGB images, models have been developed to predict biomass recently. However, it is very challenging to find a model performing stable across experiments. In this study, we recorded RGB and NIR images of wheat germplasm and Recombinant Inbred Lines (RILs) of Raj3765xHD2329, and examined the use of multimodal images from RGB, NIR sensors and machine learning models to predict biomass and leaf area non-invasively. The image-based traits (i-Traits) containing geometric features, RGB based indices, RGB colour classes and NIR features were categorized into architectural traits and physiological traits. Total 77 i-Traits were selected for prediction of biomass and leaf area consisting of 35 architectural and 42 physiological traits. We have shown that different biomass related traits such as fresh weight, dry weight and shoot area can be predicted accurately from RGB and NIR images using 16 machine learning models. We applied the models on two consecutive years of experiments and found that measurement accuracies were similar suggesting the generalized nature of models. Results showed that all biomass-related traits could be estimated with about 90% accuracy but the performance of model BLASSO was relatively stable and high in all the traits and experiments. The R Based on the quantification power analysis of i-Traits, the determinants of biomass accumulation were found which contains both architectural and physiological traits. The best predictor i-Trait for fresh weight and dry weight prediction was Area_SV and for shoot area prediction was projected shoot area. These results will be helpful for identification and genetic basis dissection of major determinants of biomass accumulation and also non-invasive high throughput estimation of plant growth during different phenological stages can identify hitherto uncovered genes for biomass production and its deployment in crop improvement for breaking the yield plateau.
Identifiants
pubmed: 37448870
doi: 10.3389/fpls.2023.1214801
pmc: PMC10337996
doi:
Types de publication
Journal Article
Langues
eng
Pagination
1214801Informations de copyright
Copyright © 2023 Singh, Kumar, Elangovan, Vasht, Arya, Duc, Swami, Pawar, Raju, Krishna, Sathee, Dalal, Sahoo and Chinnusamy.
Déclaration de conflit d'intérêts
The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Références
Mol Plant. 2018 Jun 4;11(6):789-805
pubmed: 29614319
In Silico Plants. 2019;1(1):
pubmed: 33381682
Plant Methods. 2020 Mar 18;16:40
pubmed: 32206080
Mol Plant. 2020 Feb 3;13(2):187-214
pubmed: 31981735
Breed Sci. 2019 Mar;69(1):104-116
pubmed: 31086488
Plant Cell. 2014 Dec;26(12):4636-55
pubmed: 25501589
Front Plant Sci. 2017 May 19;8:721
pubmed: 28579992
Curr Biol. 2017 Aug 7;27(15):R770-R783
pubmed: 28787611
J Exp Bot. 2015 Sep;66(18):5481-92
pubmed: 26179580
Nat Rev Genet. 2006 Mar;7(3):229-37
pubmed: 16485021
BMC Proc. 2012 May 21;6 Suppl 2:S10
pubmed: 22640436
New Phytol. 2011 Aug;191(3):895-907
pubmed: 21569033
Plant Methods. 2011 Feb 01;7:2
pubmed: 21284859
Bioinformatics. 2012 Nov 1;28(21):2789-96
pubmed: 22954627
Plant J. 2019 Mar;97(6):1105-1119
pubmed: 30536457
Plant Cell Environ. 2015 Oct;38(10):1980-96
pubmed: 25689277
Trends Plant Sci. 2016 Feb;21(2):110-124
pubmed: 26651918
J Integr Bioinform. 2017 Sep 1;14(3):
pubmed: 28862986
Front Plant Sci. 2018 Jul 09;9:887
pubmed: 30038630
Theor Appl Genet. 2016 Apr;129(4):653-673
pubmed: 26932121
Front Plant Sci. 2020 Jul 10;11:994
pubmed: 32754174
Gigascience. 2018 Feb 1;7(2):
pubmed: 29346559
Biol Rev Camb Philos Soc. 2010 May;85(2):207-16
pubmed: 19930171
Sci Rep. 2013;3:2442
pubmed: 23942574
J Exp Bot. 2015 Apr;66(7):1817-32
pubmed: 25697789
Plant Sci. 2019 May;282:23-39
pubmed: 31003609
Plants (Basel). 2019 Dec 25;9(1):
pubmed: 31881663
Front Plant Sci. 2022 Apr 13;13:758818
pubmed: 35498682
Commun Biol. 2018 Jul 5;1:89
pubmed: 30271970
Sci Rep. 2022 Apr 15;12(1):6256
pubmed: 35428863
Plant Methods. 2022 May 19;18(1):68
pubmed: 35590377
Sci Rep. 2022 Feb 24;12(1):3177
pubmed: 35210494
J Exp Bot. 2020 Sep 19;71(18):5506-5520
pubmed: 32497182
Trends Plant Sci. 2022 Jun;27(6):520-523
pubmed: 35307268
G3 (Bethesda). 2021 Jun 17;11(6):
pubmed: 33822935
Euphytica. 2018;214(1):9
pubmed: 31187787
Plant Methods. 2019 Feb 04;15:10
pubmed: 30740136
Plant Genome. 2015 Nov;8(3):eplantgenome2015.01.0003
pubmed: 33228272
J Exp Bot. 2020 Mar 25;71(6):1885-1898
pubmed: 32097472
Nat Commun. 2016 Nov 17;7:13342
pubmed: 27853175
Science. 2016 Nov 4;354(6312):
pubmed: 27811239
Nat Commun. 2014 Oct 08;5:5087
pubmed: 25295980
Ann Bot. 2007 Apr;99(4):777-83
pubmed: 17353204
BMC Med Res Methodol. 2016 Nov 14;16(1):154
pubmed: 27842498
Theor Appl Genet. 2018 Oct;131(10):2179-2196
pubmed: 30062653
PLoS One. 2015 Mar 31;10(3):e0122913
pubmed: 25826369
Plant Physiol. 2015 Aug;168(4):1476-89
pubmed: 26111541