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:98-122Paper 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.
Code and data availability