Evaluation of multiple spring wheat cultivars in diverse intercropping systems

Paul, Madhuri R.; Demie, Dereje T.; Seidel, Sabine J.; Döring, Thomas F.

doi:10.1016/j.eja.2023.127024

Cited by 4 publications

(1 citation statement)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both models can quantify differences between mixtures and monocultures of the same growth stage but are hardly sensitive to differences between the mixture treatments. They only achieve the prediction of a correct mean value, which can be explained by the fact that many cultivar differences occur randomly and are not significant [ 43 ]. In general, a machine learning model (growth estimation from images) can hardly be better than the training data (process-based output), which accounts for the similar pattern in the left and middle scatter plots.…”

Section: Resultsmentioning

confidence: 99%

Data-driven crop growth simulation on time-varying generated images using multi-conditional generative adversarial networks

Drees,

Demie,

Paul

et al. 2024

Plant Methods

Self Cite

View full text Add to dashboard Cite

Background Image-based crop growth modeling can substantially contribute to precision agriculture by revealing spatial crop development over time, which allows an early and location-specific estimation of relevant future plant traits, such as leaf area or biomass. A prerequisite for realistic and sharp crop image generation is the integration of multiple growth-influencing conditions in a model, such as an image of an initial growth stage, the associated growth time, and further information about the field treatment. While image-based models provide more flexibility for crop growth modeling than process-based models, there is still a significant research gap in the comprehensive integration of various growth-influencing conditions. Further exploration and investigation are needed to address this gap. Methods We present a two-stage framework consisting first of an image generation model and second of a growth estimation model, independently trained. The image generation model is a conditional Wasserstein generative adversarial network (CWGAN). In the generator of this model, conditional batch normalization (CBN) is used to integrate conditions of different types along with the input image. This allows the model to generate time-varying artificial images dependent on multiple influencing factors. These images are used by the second part of the framework for plant phenotyping by deriving plant-specific traits and comparing them with those of non-artificial (real) reference images. In addition, image quality is evaluated using multi-scale structural similarity (MS-SSIM), learned perceptual image patch similarity (LPIPS), and Fréchet inception distance (FID). During inference, the framework allows image generation for any combination of conditions used in training; we call this generation data-driven crop growth simulation. Results Experiments are performed on three datasets of different complexity. These datasets include the laboratory plant Arabidopsis thaliana (Arabidopsis) and crops grown under real field conditions, namely cauliflower (GrowliFlower) and crop mixtures consisting of faba bean and spring wheat (MixedCrop). In all cases, the framework allows realistic, sharp image generations with a slight loss of quality from short-term to long-term predictions. For MixedCrop grown under varying treatments (different cultivars, sowing densities), the results show that adding these treatment information increases the generation quality and phenotyping accuracy measured by the estimated biomass. Simulations of varying growth-influencing conditions performed with the trained framework provide valuable insights into how such factors relate to crop appearances, which is particularly useful in complex, less explored crop mixture systems. Further results show that adding process-based simulated biomass as a condition increases the accuracy of the derived phenotypic traits from the predicted images. This demonstrates the potential of our framework to serve as an interface between a data-driven and a process-based crop growth model. Conclusion The realistic generation and simulation of future plant appearances is adequately feasible by multi-conditional CWGAN. The presented framework complements process-based models and overcomes their limitations, such as the reliance on assumptions and the low exact field-localization specificity, by realistic visualizations of the spatial crop development that directly lead to a high explainability of the model predictions.

show abstract

Section: Resultsmentioning

confidence: 99%

Data-driven crop growth simulation on time-varying generated images using multi-conditional generative adversarial networks

Drees,

Demie,

Paul

et al. 2024

Plant Methods

Self Cite

View full text Add to dashboard Cite

show abstract

Root growth and belowground interactions in spring wheat /faba bean intercrops

Hadir,

Döring,

Justes

et al. 2024

Plant Soil

View full text Add to dashboard Cite

Background and aims Intercrops offer multiple advantages over sole crops. The aim of our study was to characterize root growth and interactions in spring wheat/faba bean intercrops to better understand belowground interactions that govern resource capture. Materials and methods A field experiment was conducted with one faba bean cultivar and two spring wheat cultivars sown at three sowing densities, defining three intercropping designs. Destructive root coring was conducted (0–100 cm) in the intercrops and sole crops at two development stages. FTIR spectroscopy was used to discriminate the species’ root masses. The plant-plant interaction index was calculated to represent the belowground interactions. Results A negative impact of intercropping on total root mass was observed in the treatment with high sowing density in both stages. For the fully and partial replacement design treatments, plant-plant facilitation was more pronounced than competition in all layers. Competition dominated root growth in the treatment with high sowing density in both stages. Lower sowing densities encouraged deep root growth of wheat (both cultivars) in intercropping. The early root growth in depth and in density of one spring wheat cultivar impacted negatively faba bean root growth. Intercropping resulted in a grain yield advantage in both fully and only one partial replacement design treatment. Conclusion In the intercrops, total root mass and plant-plant interactions were affected more by sowing density than by the spring wheat cultivar. Understanding the effect of sowing density on root growth in intercropping can help to support the design of sustainable intercropping systems.

show abstract