Browsing by Person "Meyenberg, Carina"

Now showing 1 - 3 of 3

Feature engineering and parameter tuning: improving phenomic prediction ability in multi-environmental durum wheat breeding trials
(2024) Meyenberg, Carina; Braun, Vincent; Longin, Carl Friedrich Horst; Thorwarth, Patrick
The success of plant breeding programs depends on efficient selection decisions. Phenomic selection has been proposed as a tool to predict phenotype performance based on near-infrared spectra (NIRS) to support selection decisions. In this study, we test the performance of phenomic selection in multi-environmental trials from our durum wheat breeding program for three breeding scenarios and use feature engineering as well as parameter tuning to improve the phenomic prediction ability. In addition, we investigate the influence of genotype and environment on the phenomic prediction ability for agronomic and quality traits. Preprocessing, based on a grid search over the Savitzky–Golay filter parameters based on 756,000 genotype best linear unbiased estimate (BLUE) computations, improved the phenomic prediction ability by up to 1500% (0.02–0.3). Furthermore, we show that preprocessing should be optimized depending on the dataset, trait, and model used for prediction. The phenomic prediction scenarios in our durum breeding program resulted in low-to-moderate prediction abilities with the highest and most stable prediction results when predicting new genotypes in the same environment as used for model training. This is consistent with the finding that NIRS capture both the genotype and genotype-by-environment (G×E)interaction variance.
Insights into a genomics‐based pre‐breeding program in wheat
(2025) Meyenberg, Carina; Thorwarth, Patrick; Spiller, Monika; Kollers, Sonja; Reif, Jochen Christoph; Longin, Carl Friedrich Horst
Continuous intercrossing of the best‐performing wheat ( Triticum aestivum L.) elite lines has resulted in genetic gains for a wide range of traits. However, this approach can also reduce genetic diversity, which potentially limits the long‐term genetic improvement. The use of plant genetic resources (PGRs) is therefore considered as crucial to maintain, or even increase, genetic variability in breeding to address future challenges in agriculture in a sustainable manner. Pre‐breeding programs aim to incorporate untapped genetic diversity into an elite germplasm background. Since there is limited knowledge exchange and few publications on how to run pre‐breeding programs efficiently, we report here our latest pre‐breeding scheme and key lessons learned from a decade of wheat pre‐breeding. Our study is based on genotypic and phenotypic data from 390 pre‐breeding lines coming from multiple locations and 4 years of yield trials. We used the genotypic data to estimate the genetically estimated parental contribution (GEPC) of PGRs in pre‐breeding lines. Considerable variation in GEPC between pre‐breeding lines were found even within the same cross. Combining both genotypic and phenotypic data, we compared different scenarios for genome‐wide predictions. Predicting new lines based on calibrations developed across previous years, we determined prediction abilities ranging between 0.34 and 0.69 for grain yield and 0.53 and 0.71 for sedimentation volume, depending on the predicted dataset. Finally, we showed that targeted pre‐breeding yields a small number of promising pre‐breeding lines that perform at the level of the most important commercial varieties.
Phenomic prediction can be improved by optimization of NIRS preprocessing
(2025) Braun, Vincent; Zhu, Xintian; Meyenberg, Carina; Hahn, Volker; Maurer, Hans Peter; Würschum, Tobias; Thorwarth, Patrick
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.