An Optimization Method of Deep Transfer Learning for Vegetation Segmentation under Rainy and Dry Season Differences in a Dry Thermal Valley

Deep learning networks might require re-training for different datasets, consuming significant manual labeling and training time. Transfer learning uses little new data and training time to enable pre-trained network segmentation in relevant scenarios (e.g., different vegetation images in rainy and dry seasons); however, existing transfer learning methods lack systematicity and controllability. So, an MTPI method (Maximum Transfer Potential Index method) was proposed to find the optimal conditions in data and feature quantity for transfer learning (MTPI conditions) in this study. The four pre-trained deep networks (Seg-Net (Semantic Segmentation Networks), FCN (Fully Convolutional Networks), Mobile net v2, and Res-Net 50 (Residual Network)) using the rainy season dataset showed that Res-Net 50 had the best accuracy with 93.58% and an WIoU (weight Intersection over Union) of 88.14%, most worthy to transfer training in vegetation segmentation. By obtaining each layer's TPI performance (Transfer Potential Index) of the pre-trained Res-Net 50, the MTPI method results show that the 1000-TDS and 37-TP were estimated as the best training speed with the smallest dataset and a small error risk. The MTPI transfer learning results show 91.56% accuracy and 84.86% WIoU with 90% new dataset reduction and 90% iteration reduction, which is informative for deep networks in segmentation tasks between complex vegetation scenes.

Quantitative disease resistance: Multifaceted players in plant defense

In contrast to large-effect qualitative disease resistance, quantitative disease resistance (QDR) exhibits partial and generally durable resistance and has been extensively utilized in crop breeding. The molecular mechanisms underlying QDR remain largely unknown but considerable progress has been made in this area in recent years. In this review, we summarize the genes that have been associated with plant QDR and their biological functions. Many QDR genes belong to the canonical resistance gene categories with predicted functions in pathogen perception, signal transduction, phytohormone homeostasis, metabolite transport and biosynthesis, and epigenetic regulation. However, other "atypical" QDR genes are predicted to be involved in processes that are not commonly associated with disease resistance, such as vesicle trafficking, molecular chaperones, and others. This diversity of function for QDR genes contrasts with qualitative resistance, which is often based on the actions of nucleotide-binding leucine-rich repeat (NLR) resistance proteins. An understanding of the diversity of QDR mechanisms and of which mechanisms are effective against which classes of pathogens will enable the more effective deployment of QDR to produce more durably resistant, resilient crops.

Plant Root Phenotyping Using Deep Conditional GANs and Binary Semantic Segmentation

This paper develops an approach to perform binary semantic segmentation on Arabidopsis thaliana root images for plant root phenotyping using a conditional generative adversarial network (cGAN) to address pixel-wise class imbalance. Specifically, we use Pix2PixHD, an image-to-image translation cGAN, to generate realistic and high resolution images of plant roots and annotations similar to the original dataset. Furthermore, we use our trained cGAN to triple the size of our original root dataset to reduce pixel-wise class imbalance. We then feed both the original and generated datasets into SegNet to semantically segment the root pixels from the background. Furthermore, we postprocess our segmentation results to close small, apparent gaps along the main and lateral roots. Lastly, we present a comparison of our binary semantic segmentation approach with the state-of-the-art in root segmentation. Our efforts demonstrate that cGAN can produce realistic and high resolution root images, reduce pixel-wise class imbalance, and our segmentation model yields high testing accuracy (of over 99%), low cross entropy error (of less than 2%), high Dice Score (of near 0.80), and low inference time for near real-time processing.

Introduction to emerging technologies in plant science

In recent years, an array of new technologies is propelling plant science in exciting directions and facilitating the integration of data across multiple scales. These tools come at a critical time. With an expanding global population and the need to provide food in sustainable ways, we as a civilization will be asking more of plants and plant biologists than ever before. This special issue on emerging technologies in plant science brings together a set of reviews that spotlight a range of approaches that are changing how we ask questions and allow scientific inquiry from macromolecular to ecosystem scales.