Chemical differences in cover crop residue quality are maintained through litter decay.

As plant litter decomposes, its mass exponentially decreases until it reaches a non-zero asymptote. However, decomposition rates vary considerably among litter types as a function of their overall quality (i.e., carbon:nitrogen (C:N) ratio and litter chemistry). We investigated the effects of hairy vetch (HV: Vicia villosa Roth):cereal rye (RYE: Secale cereale L.) biomass proportions with or without broadcasted poultry manure on overall litter quality before and during decomposition. As HV biomass proportions increased from 0 to 100%, the relative susceptibility of HV:RYE mixtures to microbial decomposition increased due to: (i) decrease in the initial C:N ratio (87:1 to 10:1 in 2012 and 67:1 to 9:1 in 2013), (ii) increase in the non-structural labile carbohydrates (33 to 61% across years), and (iii) decrease in the structural holo-cellulose (59 to 33% across years) and lignin (8 to 6% across years) fractions. Broadcasted poultry manure decreased the overall initial quality of HV-dominated litters and increased the overall initial quality of RYE-dominated litters. Across all HV:RYE biomass proportions with or without poultry manure, chemical changes during litter decay were related to proportional mass loss. Therefore, the relative decrease in carbohydrates and the concomitant increase in holo-cellulose and lignin fractions were more pronounced for fast decomposing litter types, i.e., litters dominated by HV rather than RYE. While our results suggest possible convergence of litter C:N ratios, initial differences in litter chemistry neither converged nor diverged. Therefore, we conclude that the initial chemistry of litter before decomposition exerts a strong control on its chemical composition throughout the decay continuum.

Use of synthetic images for training a deep learning model for weed detection and biomass estimation in cotton.

Site-specific treatment of weeds in agricultural landscapes has been gaining importance in recent years due to economic savings and minimal impact on the environment. Different detection methods have been developed and tested for precision weed management systems, but recent developments in neural networks have offered great prospects. However, a major limitation with the neural network models is the requirement of high volumes of data for training. The current study aims at exploring an alternative approach to the use of real images to address this issue. In this study, synthetic images were generated with various strategies using plant instances clipped from UAV-borne real images. In addition, the Generative Adversarial Networks (GAN) technique was used to generate fake plant instances which were used in generating synthetic images. These images were used to train a powerful convolutional neural network (CNN) known as "Mask R-CNN" for weed detection and segmentation in a transfer learning mode. The study was conducted on morningglories (MG) and grass weeds (Grass) infested in cotton. The biomass for individual weeds was also collected in the field for biomass modeling using detection and segmentation results derived from model inference. Results showed a comparable performance between the real plant-based synthetic image (mean average precision for mask-mAPm: 0.60; mean average precision for bounding box-mAPb: 0.64) and real image datasets (mAPm: 0.80; mAPb: 0.81). However, the mixed dataset (real image  + real plant instance-based synthetic image dataset) resulted in no performance gain for segmentation mask whereas a very small performance gain for bounding box (mAPm: 0.80; mAPb: 0.83). Around 40-50 plant instances were sufficient for generating synthetic images that resulted in optimal performance. Row orientation of cotton in the synthetic images was beneficial compared to random-orientation. Synthetic images generated with automatically-clipped plant instances performed similarly to the ones generated with manually-clipped instances. Generative Adversarial Networks-derived fake plant instances-based synthetic images did not perform as effectively as real plant instance-based synthetic images. The canopy mask area predicted weed biomass better than bounding box area with R2 values of 0.66 and 0.46 for MG and Grass, respectively. The findings of this study offer valuable insights for guiding future endeavors oriented towards using synthetic images for weed detection and segmentation, and biomass estimation in row crops.

Creating Predictive Weed Emergence Models Using Repeat Photography and Image Analysis.

Weed emergence models have the potential to be important tools for automating weed control actions; however, producing the necessary data (e.g., seedling counts) is time consuming and tedious. If similar weed emergence models could be created by deriving emergence data from images rather than physical counts, the amount of generated data could be increased to create more robust models. In this research, repeat RGB images taken throughout the emergence period of Raphanus raphanistrum L. and Senna obtusifolia (L.) Irwin and Barneby underwent pixel-based spectral classification. Relative cumulative pixels generated by the weed of interest over time were used to model emergence patterns. The models that were derived from cumulative pixel data were validated with the relative emergence of true seedling counts. The cumulative pixel model for R. raphanistrum and S. obtusifolia accounted for 92% of the variation in relative emergence of true counts. The results demonstrate that a simple image analysis approach based on time-dependent changes in weed cover can be used to generate weed emergence predictive models equivalent to those produced based on seedling counts. This process will help researchers working on weed emergence models, providing a new low-cost and technologically simple tool for data collection.

Pod Dehiscence in Hairy Vetch (Vicia villosa Roth).

Hairy vetch, Vicia villosa (Roth), is a cover crop that does not exhibit a typical domestication syndrome. Pod dehiscence reduces seed yield and creates weed problems for subsequent crops. Breeding efforts aim to reduce pod dehiscence in hairy vetch. To characterize pod dehiscence in the species, we quantified visual dehiscence and force required to cause dehiscence among 606 genotypes grown among seven environments of the United States. To identify potential secondary selection traits, we correlated pod dehiscence with various morphological pod characteristics and field measurements. Genotypes of hairy vetch exhibited wide variation in pod dehiscence, from completely indehiscent to completely dehiscent ratings. Mean force to dehiscence also varied widely, from 0.279 to 8.97 N among genotypes. No morphological traits were consistently correlated with pod dehiscence among environments where plants were grown. Results indicated that visual ratings of dehiscence would efficiently screen against genotypes with high pod dehiscence early in the breeding process. Force to dehiscence may be necessary to identify the indehiscent genotypes during advanced stages of selection.

Beneficial insect borders provide northern bobwhite brood habitat.

Strips of fallow vegetation along cropland borders are an effective strategy for providing brood habitat for declining populations of upland game birds (Order: Galliformes), including northern bobwhite (Colinus virginianus), but fallow borders lack nectar-producing vegetation needed to sustain many beneficial insect populations (e.g., crop pest predators, parasitoids, and pollinator species). Planted borders that contain mixes of prairie flowers and grasses are designed to harbor more diverse arthropod communities, but the relative value of these borders as brood habitat is unknown. We used groups of six human-imprinted northern bobwhite chicks as a bioassay for comparing four different border treatments (planted native grass and prairie flowers, planted prairie flowers only, fallow vegetation, or mowed vegetation) as northern bobwhite brood habitat from June-August 2009 and 2010. All field border treatments were established around nine organic crop fields. Groups of chicks were led through borders for 30-min foraging trials and immediately euthanized, and eaten arthropods in crops and gizzards were measured to calculate a foraging rate for each border treatment. We estimated arthropod prey availability within each border treatment using a modified blower-vac to sample arthropods at the vegetation strata where chicks foraged. Foraging rate did not differ among border treatments in 2009 or 2010. Total arthropod prey densities calculated from blower-vac samples did not differ among border treatments in 2009 or 2010. Our results showed plant communities established to attract beneficial insects should maximize the biodiversity potential of field border establishment by providing habitat for beneficial insects and young upland game birds.

Breeding cereal crops for enhanced weed suppression: optimizing allelopathy and competitive ability.

Interest in breeding grain crops with improved weed suppressive ability is growing in response to the evolution and rapid expansion of herbicide resistant populations in major weeds of economic importance, environmental concerns, and the unmet needs of organic producers and smallholder farmers without access to herbicides. This review is focused on plant breeding for weed suppression; specifically, field and laboratory screening protocols, genetic studies, and breeding efforts that have been undertaken to improve allelopathy and competition in rice, wheat, and barley. The combined effects of allelopathy and competition determine the weed suppressive potential of a given cultivar, and research groups worldwide have been working to improve both traits simultaneously to achieve maximum gains in weed suppression. Both allelopathy and competitive ability are complex, quantitatively inherited traits that are heavily influenced by environmental factors. Thus, good experimental design and sound breeding procedures are essential to achieve genetic gains. Weed suppressive rice cultivars are now commercially available in the U.S. and China that have resulted from three decades of research. Furthermore, a strong foundation has been laid during the past 10 years for the breeding of weed suppressive wheat and barley cultivars.