English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Image-based crop growth modeling can substantially contribute to precisionagriculture by revealing spatial crop development over time, which allows anearly and location-specific estimation of relevant future plant traits, such asleaf area or biomass. A prerequisite for realistic and sharp crop imagegeneration is the integration of multiple growth-influencing conditions in amodel, such as an image of an initial growth stage, the associated growth time,and further information about the field treatment. We present a two-stageframework consisting first of an image prediction model and second of a growthestimation model, which both are independently trained. The image predictionmodel is a conditional Wasserstein generative adversarial network (CWGAN). Inthe generator of this model, conditional batch normalization (CBN) is used tointegrate different conditions along with the input image. This allows themodel to generate time-varying artificial images dependent on multipleinfluencing factors of different kinds. These images are used by the secondpart of the framework for plant phenotyping by deriving plant-specific traitsand comparing them with those of non-artificial (real) reference images. Forvarious crop datasets, the framework allows realistic, sharp image predictionswith a slight loss of quality from short-term to long-term predictions.Simulations of varying growth-influencing conditions performed with the trainedframework provide valuable insights into how such factors relate to cropappearances, which is particularly useful in complex, less explored cropmixture systems. Further results show that adding process-based simulatedbiomass as a condition increases the accuracy of the derived phenotypic traitsfrom the predicted images. This demonstrates the potential of our framework toserve as an interface between an image- and process-based crop growth model.

Data-driven Crop Growth Simulation on Time-varying Generated Images using Multi-conditional Generative Adversarial Networks