Progeny Differentiation in Faba Bean Using Hyperspectral Images and Machine Learning
4 affiliations
- 1Department of Plant Breeding Justus‐Liebig University Giessen Giessen Germany
- 2Julius Kuehn Institute (JKI), Federal Research Centre for Cultivated Plants Institute for Resistance Research and Stress Tolerance Quedlinburg Germany
- 3NPZ Innovation GmbH Holtsee Germany
- 4Norddeutsche Pflanzenzucht, Hans‐Georg Lembke KG Holtsee Germany
Abstract
Though currently a minor crop, faba bean is a promising source of plant‐based protein as global diets shift towards more plant‐based nutrition. To realize this potential, advances in breeding and cultivation are crucial. To exploit heterosis, faba bean breeding frequently utilizes synthetic cultivars, produced by open pollination of inbred lines, resulting in a mixture of F1 hybrid seeds and self‐pollinated offspring. Pure F1 hybrid cultivars are currently unavailable due to unstable cytoplasmic male sterility (CMS) systems. An ability to distinguish F1 seeds from their parental inbreds based on characteristics associated with the xenia effect could change this. The xenia effect refers to the influence of paternal pollen on seed traits, for example, seed weight and cotyledon cells in faba bean. In this study, we exploited the xenia effect captured in hyperspectral imaging data to develop machine learning scenarios for discriminating between parental and F1 seeds of open‐pollinated synthetic combinations (Syn‐1). The hyperspectral data were preprocessed using Savitzky–Golay filtering to reduce noise and smooth the spectra. Various machine learning algorithms were applied, incorporating Bayesian hyperparameter optimization. The scenarios achieved up to 98.9% accuracy in separating parental components of Syn‐1. When including all seeds, the model achieved an F1 score of 40.7%, indicating moderate detection and classification performance. As the harmonic mean of precision and recall, the F1 score reflects both the correctness of F1 seed identifications and the completeness with which F1 seeds were identified. While this approach does not yet enable the development of full hybrid cultivars, it paves the way for hybrid‐enriched cultivars. These could help to streamline breeding for synthetic cultivars and potentially increase yields, for example, by increasing the proportion of F1 hybrid seeds in synthetic cultivars. This study extends knowledge of the xenia effect in faba bean and provides a basis for further research aimed at enhancing breeding methods and productivity.
Related
- Truncated automatic sparse differentiation for machine learning interatomic potentials
- Corrosion Prediction of AZ31 Mg Alloy Using Machine Learning and Digital Smartphone Images
- Decoding Crystallographic Surface Chirality from Real Space and Momentum Space Images by Machine Learning
- Differentiation of Bacterial Isolates Using Mass Spectrometry and Machine Learning Analysis of Volatile Organic Compounds.
- Deep spectral–spatial learning for robust bruise detection and internal damage estimation in apples using visible/near-infrared hyperspectral imaging
BibTeX
@article{schlichtermann2026progeny,
title = {{Progeny Differentiation in Faba Bean Using Hyperspectral Images and Machine Learning}},
author = {Rica‐Hanna Schlichtermann and Sebastian Warnemünde and Hanna Tietgen and Gregor Welna and Andreas Stahl and Benjamin Wittkop and Rod J. Snowdon},
journal = {Plant Direct},
year = {2026},
month = oct,
doi = {10.1002/pld3.70193},
url = {https://doi.org/10.1002/pld3.70193},
note = {CC BY},
}
RIS
TY - JOUR
TI - Progeny Differentiation in Faba Bean Using Hyperspectral Images and Machine Learning
AU - Rica‐Hanna Schlichtermann
AU - Sebastian Warnemünde
AU - Hanna Tietgen
AU - Gregor Welna
AU - Andreas Stahl
AU - Benjamin Wittkop
AU - Rod J. Snowdon
PY - 2026
DA - 2026/10/29
JO - Plant Direct
DO - 10.1002/pld3.70193
UR - https://doi.org/10.1002/pld3.70193
AB - Though currently a minor crop, faba bean is a promising source of plant‐based protein as global diets shift towards more plant‐based nutrition. To realize this potential, advances in breeding and cultivation are crucial. To exploit heterosis, faba bean breeding frequently utilizes synthetic cultivars, produced by open pollination of inbred lines, resulting in a mixture of F1 hybrid seeds and self‐pollinated offspring. Pure F1 hybrid cultivars are currently unavailable due to unstable cytoplasmic male sterility (CMS) systems. An ability to distinguish F1 seeds from their parental inbreds based on characteristics associated with the xenia effect could change this. The xenia effect refers to the influence of paternal pollen on seed traits, for example, seed weight and cotyledon cells in faba bean. In this study, we exploited the xenia effect captured in hyperspectral imaging data to develop machine learning scenarios for discriminating between parental and F1 seeds of open‐pollinated synthetic combinations (Syn‐1). The hyperspectral data were preprocessed using Savitzky–Golay filtering to reduce noise and smooth the spectra. Various machine learning algorithms were applied, incorporating Bayesian hyperparameter optimization. The scenarios achieved up to 98.9% accuracy in separating parental components of Syn‐1. When including all seeds, the model achieved an F1 score of 40.7%, indicating moderate detection and classification performance. As the harmonic mean of precision and recall, the F1 score reflects both the correctness of F1 seed identifications and the completeness with which F1 seeds were identified. While this approach does not yet enable the development of full hybrid cultivars, it paves the way for hybrid‐enriched cultivars. These could help to streamline breeding for synthetic cultivars and potentially increase yields, for example, by increasing the proportion of F1 hybrid seeds in synthetic cultivars. This study extends knowledge of the xenia effect in faba bean and provides a basis for further research aimed at enhancing breeding methods and productivity.
SN - 2475-4455
ER -