view of various GAN frameworks and the applications of deep learning in agriculture. Section 3 describes the proposed approach, followed by the GAN architecture developed in this work. Experiments and results are discussed in Section 4 . Section 5 concludes the paper. The code for this work is publicly available on GitHub 6 6 6 https://github.com/iPRoBe-lab/synthetic_forestry_image_using_GAN . 2 Related Work Since our goal is to design a GAN for agricultural applications, the literature review is conducted from both aspects. First, we introduce several GAN architectures proposed in the literature. Next, we summarize deep learning approaches, including GANs, that have been utilized in agricul
Open resource ↗iPRoBe-lab/synthetic_forestry_image_using_GAN · lines:98-122Unverified paper record
Synthesizing Forestry Images Conditioned on Plant Phenotype Using a Generative Adversarial Network
arXiv (Cornell University) · 7 Jul 2023 · 10.48550/arxiv.2307.03789
Abstract
Plant phenology and phenotype prediction using remote sensing data are increasingly gaining attention within the plant science community as a promising approach to enhance agricultural productivity. This work focuses on generating synthetic forestry images that satisfy certain phenotypic attributes, viz. canopy greenness. We harness a Generative Adversarial Network (GAN) to synthesize biologically plausible and phenotypically stable forestry images conditioned on the greenness of vegetation (a continuous attribute) over a specific region of interest, describing a particular vegetation type in a mixed forest. The training data is based on the automated digital camera imagery provided by the National Ecological Observatory Network (NEON) and processed by the PhenoCam Network. Our method helps render the appearance of forest sites specific to a greenness value. The synthetic images are subsequently utilized to predict another phenotypic attribute, viz., redness of plants. The quality of the synthetic images is assessed using the Structural SIMilarity (SSIM) index and Fréchet Inception Distance (FID). Further, the greenness and redness indices of the synthetic images are compared against those of the original images using Root Mean Squared Percentage Error (RMSPE) to evaluate their accuracy and integrity. The generalizability and scalability of our proposed GAN model are established by effectively transforming it to generate synthetic images for other forest sites and vegetation types. From a broader perspective, this approach could be leveraged to visualize forestry based on different phenotypic attributes in the context of various environmental parameters.
Plant phenotyping relevance
植物の表現型属性（樹冠の緑色度・植物の赤色度）に条件付けたGAN画像生成と、その精度・一般化可能性の評価が中心であり、画像ベースの表現型推定手法の開発に該当する。
abstractThis work focuses on generating synthetic forestry images that satisfy certain phenotypic attributes, viz. canopy greenness.
abstractWe harness a Generative Adversarial Network (GAN) to synthesize biologically plausible and phenotypically stable forestry images conditioned on the greenness of vegetation
Code and data availability
The paper's GAN analysis code is explicitly stated as publicly available on the authors' GitHub repository, and the training imagery (NEON PhenoCam phenology images, DP1.00033.001) is a public data product used directly for the paper's plant-phenotyping experiments.
This is an automatically classified, unverified record. Curator approval is required before any resource enters the Catalog.