EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SUnSeT: spectral unmixing of hyperspectral images for phenotyping soybean seed traits

Seok Won Jeong, Jae Il Lyu, HwangWeon Jeong, Jeongho Baek, Jung-Kyung Moon, Chaewon Lee, Myoung-Goo Choi, Kyoung-Hwan Kim, Youn-Il Park

Plant Cell Reports · 2024

DOI: 10.1007/s00299-024-03249-0 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Plant Cell Reports, 2024. Verfasst von Seok Won Jeong und 8 weiteren Autor:innen. Beteiligte Einrichtung: Biological Sciences, Chungnam National University, 99 Daehagro, Youseong, Daejon, 34134, Korea. Hauptthemen laut MEDLINE: Glycine max, Seeds, Phenotype. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 75 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Rural Development Administration, Korea Research Institute of Bioscience and Biotechnology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Key message Hyperspectral features enable accurate classification of soybean seeds using linear discriminant analysis and GWAS for novel seed trait genes . Abstract Evaluating crop seed traits such as size, shape, and color is crucial for assessing seed quality and improving agricultural productivity. The introduction of the SUnSet toolbox, which employs hyperspectral sensor-derived image analysis, addresses this necessity. In a validation test involving 420 seed accessions from the Korean Soybean Core Collections, the pixel purity index algorithm identified seed- specific hyperspectral endmembers to facilitate segmentation. Various metrics extracted from ventral and lateral side images facilitated the categorization of seeds into three size groups and four shape groups. Additionally, quantitative RGB triplets representing seven seed coat colors, averaged reflectance spectra, and pigment indices were acquired. Machine learning models, trained on a dataset comprising 420 accession seeds and 199 predictors encompassing seed size, shape, and reflectance spectra, achieved accuracy rates of 95.8% for linear discriminant analysis model. Furthermore, a genome-wide association study utilizing hyperspectral features uncovered associations between seed traits and genes governing seed pigmentation and shapes. This comprehensive approach underscores the effectiveness of SUnSet in advancing precision agriculture through meticulous seed trait analysis.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Glycine maxSeedsPhenotypeGenome-Wide Association StudyHyperspectral ImagingPigmentationImage Processing, Computer-AssistedAlgorithmsMachine Learning

Stichwörter der Autor:innen

EndmembersGenome-wide association studyHyperspectral imagesKorean soybean core collectionLinear discriminant analysisSeed phenotypingSpectral unmixing

Autor:innen und Institutionen

  • Biological Sciences, Chungnam National University, 99 Daehagro, Youseong, Daejon, 34134, Korea.
  • Gene Engineering Division, National Institute of Agricultural Sciences, 370 Nongsaengmyeongro, Jeonju, Jeollabuk-do, 54874, Korea.
  • Crop Foundation Research Division, National Institute of Crop Sciences, 181 Hyeoksinro, Wanju, Jeollabuk-do, 55365, Korea.
  • Crop Cultivation and Environment Research Division, National Institute of Crop Sciences, 54 Seohoro, Suwon, Kyounggi-do, 16613, Korea.
  • Wheat Research Team, National Institute of Crop Sciences, RDA, 181 Hyeoksinro, Wanju, Jeollabuk-do, 55365, Korea.
  • Biological Sciences, Chungnam National University, 99 Daehagro, Youseong, Daejon, 34134, Korea. yipark@cnu.ac.kr.

Förderung

  • Rural Development Administration
  • Korea Research Institute of Bioscience and Biotechnology

Zitieren

APA

Jeong, S. W., Lyu, J. I., Jeong, H., Baek, J., Moon, J. K., Lee, C., Choi, M. G., Kim, K. H., & Park, Y. I. (2024). SUnSeT: spectral unmixing of hyperspectral images for phenotyping soybean seed traits. Plant Cell Reports. https://doi.org/10.1007/s00299-024-03249-0

Vancouver

Jeong SW, Lyu JI, Jeong H, Baek J, Moon JK, Lee C, et al. SUnSeT: spectral unmixing of hyperspectral images for phenotyping soybean seed traits. Plant Cell Reports. 2024. doi:10.1007/s00299-024-03249-0

BibTeX
@article{Jeong2024,
  author = {Jeong, Seok Won and Lyu, Jae Il and Jeong, HwangWeon and Baek, Jeongho and Moon, Jung-Kyung and Lee, Chaewon and Choi, Myoung-Goo and Kim, Kyoung-Hwan and Park, Youn-Il},
  title = {SUnSeT: spectral unmixing of hyperspectral images for phenotyping soybean seed traits},
  journal = {Plant Cell Reports},
  year = {2024},
  doi = {10.1007/s00299-024-03249-0}
}
Kostenlos starten →