Computational Science Hub (CSH)

Permanent URI for this collectionhttps://hohpublica.uni-hohenheim.de/handle/123456789/16924

Browse

Browsing Computational Science Hub (CSH) by Sustainable Development Goals "15"

Type the first few letters and click on the Browse button
Now showing 1 - 2 of 2
  • Thumbnail Image
    Publication
    DeepCob: precise and high-throughput analysis of maize cob geometry using deep learning with an application in genebank phenomics
    (2021) Kienbaum, Lydia; Correa Abondano, Miguel; Blas, Raul; Schmid, Karl
    Background: Maize cobs are an important component of crop yield that exhibit a high diversity in size, shape and color in native landraces and modern varieties. Various phenotyping approaches were developed to measure maize cob parameters in a high throughput fashion. More recently, deep learning methods like convolutional neural networks (CNNs) became available and were shown to be highly useful for high-throughput plant phenotyping. We aimed at comparing classical image segmentation with deep learning methods for maize cob image segmentation and phenotyping using a large image dataset of native maize landrace diversity from Peru. Results: Comparison of three image analysis methods showed that a Mask R-CNN trained on a diverse set of maize cob images was highly superior to classical image analysis using the Felzenszwalb-Huttenlocher algorithm and a Window-based CNN due to its robustness to image quality and object segmentation accuracy (r = 0.99). We integrated Mask R-CNN into a high-throughput pipeline to segment both maize cobs and rulers in images and perform an automated quantitative analysis of eight phenotypic traits, including diameter, length, ellipticity, asymmetry, aspect ratio and average values of red, green and blue color channels for cob color. Statistical analysis identified key training parameters for efficient iterative model updating. We also show that a small number of 10–20 images is sufficient to update the initial Mask R-CNN model to process new types of cob images. To demonstrate an application of the pipeline we analyzed phenotypic variation in 19,867 maize cobs extracted from 3449 images of 2484 accessions from the maize genebank of Peru to identify phenotypically homogeneous and heterogeneous genebank accessions using multivariate clustering. Conclusions: Single Mask R-CNN model and associated analysis pipeline are widely applicable tools for maize cob phenotyping in contexts like genebank phenomics or plant breeding.
  • Thumbnail Image
    Publication
    Seasonal variation in the activity pattern of red squirrels and their mammalian predators
    (2024) Kalb, Nadine; Schlindwein, Xenia; Gottschalk, Thomas K.; Dvorak, Jan; Randler, Christoph
    Camera traps are a powerful tool to monitor the activity pattern of species over long time periods. Camera data can be used to analyze activity patterns of or temporal niche partitioning among species. Temporal niche partitioning plays an important role for species coexistence and is under constant evolutionary pressure from predator-prey relationships. Our study aimed to investigate temporal shifts in activity patterns of red squirrels and two mammalian predators, red fox and marten ( Martes spec .). Previous studies yielded different activity patterns for these species depending on location, season, predator-prey interactions, and food- availability. We used camera traps to monitor the activity of squirrels, red fox and martens throughout a whole year in a mountainous forest in southwestern Germany. We also investigated a possible difference in activity among different color morphs as coloration in mammals is often associated with concealment, for squirrels, however, such an effect could not be demonstrated so far. We found a diurnal activity for squirrels in all seasons with a bimodal activity pattern during spring, trimodal in summer and unimodal in fall and winter. Activity patterns did not differ between black and red color morphs. The activity of the squirrels showed only low to moderate overlaps with fox and marten, but there was still slight variation among seasons. Activity overlaps were higher in spring and summer, which coincides with breeding season. Our results suggest that predators might adjust their activity during squirrel breeding season to increase the chance of preying on their offspring. Squirrels in turn could benefit by minimizing the activity overlap during wintertime when they are highly visible to predators as trees are leaf-free or even snow might enhance the contrast between them and their background. Lastly, our results indicate that temporal niche portioning among red squirrel, red fox and martens might be rather fine scaled.