EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Phenomic Prediction Can Be Improved by Optimization of NIRS Preprocessing

Vincent Braun, Xintian Zhu, Carina Meyenberg, Volker Hahn, Hans Peter Maurer, Tobias Würschum, Patrick Thorwarth

Plant Breeding · 2025-08 · 144 (4) · 454-469

DOI: 10.1111/pbr.13265 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Plant Breeding, online erschienen am 06.02.2025. Verfasst von Vincent Braun und 6 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 72 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Bundesministerium für Ernährung und Landwirtschaft.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, phenomic prediction has emerged as a new method in plant breeding that has been shown to have great potential. However, there are still many open questions regarding its practical application. For example, in the field of spectroscopy, it is standard practice to optimize the preprocessing of spectra, which so far has only been done to a limited extent for phenomic prediction. In this study, we therefore used three different data sets of soybean, triticale and maize to identify the best combinations of Savitzky–Golay filter parameters for preprocessing near‐infrared spectra for phenomic prediction. We tested 677 combinations of polynomial order, derivative and window size and evaluated them with Monte Carlo cross‐validation. Our results showed that the predictive ability can be improved with the right settings. However, there was no global optimum that gave the best results for all data sets. Even for different traits within the same data set, different combinations of parameters were necessary to achieve the highest predictive ability. Nevertheless, we show that some combinations generally result in a very low predictive ability and should not be used for preprocessing. In addition, we used the normalized discounted cumulative gain to assess whether preprocessing affected the ranking of individuals, which revealed no major changes in the top 1%, 10% or 20% of predicted individuals. Taken together, our results show the potential of preprocessing near‐infrared spectroscopy data to improve the phenomic predictive ability, but there appears to be no global optimum of parameter settings across data sets and traits.

Förderung

  • Bundesministerium für Ernährung und Landwirtschaft

Zitieren

APA

Braun, V., Zhu, X., Meyenberg, C., Hahn, V., Maurer, H. P., Würschum, T., & Thorwarth, P. (2025). Phenomic Prediction Can Be Improved by Optimization of NIRS Preprocessing. Plant Breeding, 144(4), 454-469. https://doi.org/10.1111/pbr.13265

Vancouver

Braun V, Zhu X, Meyenberg C, Hahn V, Maurer HP, Würschum T, et al. Phenomic Prediction Can Be Improved by Optimization of NIRS Preprocessing. Plant Breeding. 2025;144(4):454-469. doi:10.1111/pbr.13265

BibTeX
@article{Braun2025,
  author = {Braun, Vincent and Zhu, Xintian and Meyenberg, Carina and Hahn, Volker and Maurer, Hans Peter and Würschum, Tobias and Thorwarth, Patrick},
  title = {Phenomic Prediction Can Be Improved by Optimization of NIRS Preprocessing},
  journal = {Plant Breeding},
  year = {2025},
  volume = {144},
  number = {4},
  pages = {454--469},
  doi = {10.1111/pbr.13265}
}
Kostenlos starten →