Scholarlink

<p>Digital seed phenotyping offers an efficient and objective alternative to conventional, labor-intensive methods for morphological characterization in plant breeding programs. In castor bean, rapid and reliable tools are essential to support genetic improvement. This study evaluated the potential of digital phenotyping for seed characterization and its application in breeding. Seeds from 65 accessions (2023) and 51 accessions (2024) were photographed with an RGB camera and processed in ImageJ® for extraction of morphological traits. Agreement between digital and manual measurements was assessed by correlation and Bland–Altman analysis, while machine learning models were trained to predict hundred-seed weight (HSW). Genetic diversity was explored using principal component analysis (PCA) and clustering, and variance components and heritability were estimated with mixed linear models. Digital phenotyping showed strong agreement with manual measurements (r = 0.95–0.97) and enabled accurate HSW prediction, with Ridge Regression achieving the best performance (R<sup>2</sup> = 0.88; RMSE = 3.83; MAE = 3.19). PCA explained 85.7% of the variance and revealed three phenotypic clusters. Traits such as seed length (H<sup>2</sup> = 0.88) and aspect ratio (H<sup>2</sup> = 0.87) exhibited high heritability, while roundness (H<sup>2</sup> = 0.79), perimeter (H<sup>2</sup> = 0.72), and area (H<sup>2</sup> = 0.67) were moderate. These findings demonstrate that digital phenotyping is a reliable and high-throughput method for castor bean seed characterization, supporting genotype selection and the integration of machine learning approaches into breeding programs for greater precision and efficiency.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Image-based phenotyping of castor bean seeds for morphological traits, seed weight prediction, and assessment of genetic diversity

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月16日

查看全文
  • Diego Andrade Santos,
  • Diego Fernando Marmolejo Cortes,
  • Mylena Almeida dos Santos,
  • Myriam El Adas,
  • Bismarck Ferreira de Morais,
  • Denise Barreto dos Santos,
  • Tairone da Silva de Almeida,
  • Christian Adalberto Santos de Queiroz,
  • Gabriel da Paixão Fernandes,
  • Ailan Santos de Jesus,
  • Rafaella da Silva Rodrigues,
  • Daniel Santos Alves,
  • Hellen Cristina da Paixão Moura,
  • Simone Alves Silva

摘要

Digital seed phenotyping offers an efficient and objective alternative to conventional, labor-intensive methods for morphological characterization in plant breeding programs. In castor bean, rapid and reliable tools are essential to support genetic improvement. This study evaluated the potential of digital phenotyping for seed characterization and its application in breeding. Seeds from 65 accessions (2023) and 51 accessions (2024) were photographed with an RGB camera and processed in ImageJ® for extraction of morphological traits. Agreement between digital and manual measurements was assessed by correlation and Bland–Altman analysis, while machine learning models were trained to predict hundred-seed weight (HSW). Genetic diversity was explored using principal component analysis (PCA) and clustering, and variance components and heritability were estimated with mixed linear models. Digital phenotyping showed strong agreement with manual measurements (r = 0.95–0.97) and enabled accurate HSW prediction, with Ridge Regression achieving the best performance (R2 = 0.88; RMSE = 3.83; MAE = 3.19). PCA explained 85.7% of the variance and revealed three phenotypic clusters. Traits such as seed length (H2 = 0.88) and aspect ratio (H2 = 0.87) exhibited high heritability, while roundness (H2 = 0.79), perimeter (H2 = 0.72), and area (H2 = 0.67) were moderate. These findings demonstrate that digital phenotyping is a reliable and high-throughput method for castor bean seed characterization, supporting genotype selection and the integration of machine learning approaches into breeding programs for greater precision and efficiency.