Recent research on the application of remote sensing and deep learning-based analysis in precision agriculture demonstrated a potential for improved crop management and reduced environmental impacts of agricultural production. Despite the promising results, the practical relevance of these technologies for field deployment requires novel algorithms that are customized for analysis of agricultural images and robust to implementation on natural field imagery. The paper presents an approach for analyzing aerial images of a potato (Solanum tuberosum L.) crop using deep neural networks. The main objective is to demonstrate automated spatial recognition of healthy vs. stressed crop at a plant level. Specifically, we examine premature plant senescence resulting in drought stress on 'Russet Burbank' potato plants. We propose a novel deep learning (DL) model for detecting crop stress, named Retina-UNet-Ag. The proposed architecture is a variant of Retina-UNet and includes connections from low-level semantic representation maps to the feature pyramid network. The paper also introduces a dataset of aerial field images acquired with a Parrot Sequoia camera. The dataset includes manually annotated bounding boxes of healthy and stressed plant regions. Experimental validation demonstrated the ability for distinguishing healthy and stressed plants in field images, achieving an average dice score coefficient (DSC) of 0.74. A comparison to related state-of-the-art DL models for object detection revealed that the presented approach is effective for this task. The proposed method is conducive toward the assessment and recognition of potato crop stress in aerial field images collected under natural conditions.

No abstract

No abstract

Background Spot form net blotch (SFNB) caused by the necrotrophic fungal pathogen Pyrenophora teres f. maculata (Ptm) is an economically important disease of barley that also infects wheat. Using genetic analysis to characterize loci in Ptm genomes associated with virulence or avirulence is an important step to identify pathogen effectors that determine compatible (virulent) or incompatible (avirulent) interactions with cereal hosts. Association mapping (AM) is a powerful tool for detecting virulence loci utilizing phenotyping and genotyping data generated for natural populations of plant pathogenic fungi. Results Restriction-site associated DNA genotyping-by-sequencing (RAD-GBS) was used to generate 4,836 single nucleotide polymorphism (SNP) markers for a natural population of 103 Ptm isolates collected from Idaho, Montana and North Dakota. Association mapping analyses were performed utilizing the genotyping and infection type data generated for each isolate when challenged on barley seedlings of thirty SFNB differential barley lines. A total of 39 marker trait associations (MTAs) were detected across the 20 barley lines corresponding to 30 quantitative trait loci (QTL); 26 novel QTL and four that were previously mapped in Ptm biparental populations. These results using diverse US isolates and barley lines showed numerous barley-Ptm genetic interactions with seven of the 30 Ptm virulence/avirulence loci falling on chromosome 3, suggesting that it is a reservoir of diverse virulence effectors. One of the loci exhibited reciprocal virulence/avirulence with one haplotype predominantly present in isolates collected from Idaho increasing virulence on barley line MXB468 and the alternative haplotype predominantly present in isolates collected from North Dakota and Montana increasing virulence on barley line CI9819. Conclusions Association mapping provided novel insight into the host pathogen genetic interactions occurring in the barley-Ptm pathosystem. The analysis suggests that chromosome 3 of Ptm serves as an effector reservoir in concordance with previous reports for Pyrenophora teres f. teres, the causal agent of the closely related disease net form net blotch. Additionally, these analyses identified the first reported case of a reciprocal pathogen virulence locus. However, further investigation of the pathosystem is required to determine if multiple genes or alleles of the same gene are responsible for this genetic phenomenon.