wth estimation model. A transferability experiment demonstrates that our framework has the potential to be transferred to crop mixtures in another field with different environmental conditions. 2 Materials and Methods This section introduces the data basis (Sec. 2.1 ) and the framework 1 1 1 Source code is publicly available at https://github.com/luked12/crop-growth-cgan , where a 2-step approach is followed. First, an image is predicted (Sec. 2.2 ), and second, the growth is estimated using plant phenotyping (Sec. 2.3 ). While existing state-of-the-art models are used for growth estimation, which is fine-tuned on our data, the methodological focus of this work is on the first part, image pr
Open resource ↗luked12/crop-growth-cgan · lines:128-235Unverified paper record
Data-driven Crop Growth Simulation on Time-varying Generated Images using Multi-conditional Generative Adversarial Networks
arXiv (Cornell University) · 6 Dec 2023 · 10.48550/arxiv.2312.03443
Abstract
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. We present a two-stage framework consisting first of an image prediction model and second of a growth estimation model, which both are independently trained. The image prediction model is a conditional Wasserstein generative adversarial network (CWGAN). In the generator of this model, conditional batch normalization (CBN) is used to integrate different conditions along with the input image. This allows the model to generate time-varying artificial images dependent on multiple influencing factors of different kinds. 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. For various crop datasets, the framework allows realistic, sharp image predictions with a slight loss of quality from short-term to long-term predictions. 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 an image- and process-based crop growth model.
Plant phenotyping relevance
画像生成と成長推定を統合したフレームワークを開発し、生成画像から植物個体の形質を抽出・比較することが中心であるため、植物フェノタイピング手法として含める。
abstractWe present a two-stage framework consisting first of an image prediction model and second of a growth estimation model, which both are independently trained.
abstractThese 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.
abstractFurther results show that adding process-based simulated biomass as a condition increases the accuracy of the derived phenotypic traits from the predicted images.
Code and data availability
The paper explicitly states that its source code (the multi-conditional CWGAN crop growth simulation framework) is publicly available on GitHub. The SIMPLACE documentation URL is a generic external resource, not a paper-specific asset.
This is an automatically classified, unverified record. Curator approval is required before any resource enters the Catalog.