Automated detection and quantification of plant diseases would enable more rapid gains in plant breeding and faster scouting of farmers’ fields. However, it is difficult for a simple algorithm to distinguish between the target disease and other sources of dead plant tissue in a typical field, especially given the many variations in lighting and orientation. Training a machine learning algorithm to accurately detect a given disease from images taken in the field requires a massive amount of human-generated training data. This data set contains images of maize (Zea mays L.) leaves taken in three ways: by a hand-held camera, with a camera mounted on a boom, and with a camera mounted on a small unmanned aircraft system (sUAS, commonly known as a drone). Lesions of northern leaf blight (NLB), a common foliar disease of maize, were annotated in each image by one of two human experts. The three data sets together contain 18,222 images annotated with 105,705 NLB lesions, making this the largest publicly available image set annotated for a single plant disease.

Plant disease poses a serious threat to global food security. Accurate, high-throughput methods of quantifying disease are needed by breeders to better develop resistant plant varieties and by researchers to better understand the mechanisms of plant resistance and pathogen virulence. Northern leaf blight (NLB) is a serious disease affecting maize and is responsible for significant yield losses. A Mask R-CNN model was trained to segment NLB disease lesions in unmanned aerial vehicle (UAV) images. The trained model was able to accurately detect and segment individual lesions in a hold-out test set. The mean intersect over union (IOU) between the ground truth and predicted lesions was 0.73, with an average precision of 0.96 at an IOU threshold of 0.50. Over a range of IOU thresholds (0.50 to 0.95), the average precision was 0.61. This work demonstrates the potential for combining UAV technology with a deep learning-based approach for instance segmentation to provide accurate, high-throughput quantitative measures of plant disease.

Key message: Heritable variation in phenotypes extracted from multi-spectral images (MSIs) and strong genetic correlations with end-of-season traits indicates the value of MSIs for crop improvement and modeling of plant growth curve. Vegetation indices (VIs) derived from multi-spectral imaging (MSI) platforms can be used to study properties of crop canopy, providing non-destructive phenotypes that could be used to better understand growth curves throughout the growing season. To investigate the amount of variation present in several VIs and their relationship with important end-of-season traits, genetic and residual (co)variances for VIs, grain yield and moisture were estimated using data collected from maize hybrid trials. The VIs considered were Normalized Difference Vegetation Index (NDVI), Green NDVI, Red Edge NDVI, Soil-Adjusted Vegetation Index, Enhanced Vegetation Index and simple Ratio of Near Infrared to Red (Red) reflectance. Genetic correlations of VIs with grain yield and moisture were used to fit multi-trait models for prediction of end-of-season traits and evaluated using within site/year cross-validation. To explore alternatives to fitting multiple phenotypes from MSI, random regression models with linear splines were fit using data collected in 2016 and 2017. Heritability estimates ranging from (0.10 to 0.82) were observed, indicating that there exists considerable amount of genetic variation in these VIs. Furthermore, strong genetic and residual correlations of the VIs, NDVI and NDRE, with grain yield and moisture were found. Considerable increases in prediction accuracy were observed from the multi-trait model when using NDVI and NDRE as a secondary trait. Finally, random regression with a linear spline function shows potential to be used as an alternative to mixed models to fit VIs from multiple time points.

Hemp (Cannabis sativa) is a multi-use crop garnering newfound attention from researchers and consumers. While interest has emerged, a lack of substantiated research still exists regarding effects of adverse weather events on physiological health and secondary metabolite production of hemp. The aim of this experiment was to assess cold tolerance of hemp using the cultivars ‘FINOLA’ and ‘AutoCBD’. Effects of cultivar, plant age, cold acclimation, frequency of cold treatments, and intensity of cold treatments were all considered in regard to their influence on physiological stress, biomass, and cannabinoid profile. Few effects of sequential cold treatments were noted, and they were not moderated by cold acclimation, which tended to have negative effects across many responses. This detrimental effect of cold acclimation conditions was further observed in decreased total CBD % and total THC % compared to non-acclimated plants. These findings bear consideration when assessing the unpredictability of a changing climate’s effects on the heath and cannabinoid profile of hemp.

Proper crop management requires rapid detection methods for abiotic and biotic stresses to ensure plant health and yield. Hemp (Cannabis sativa L.) is an emerging economically and environmentally sustainable crop capable of yielding high biomass. Nitrogen deficiency significantly reduces hemp plant growth, affecting photosynthetic capacity and ultimately decreasing yield. When symptoms of nitrogen deficiency are visible to humans, there is often already lost yield. A real-time, non-destructive detection method, such as Raman spectroscopy, is therefore critical to identify nitrogen deficiency in living hemp plant tissue for fast, precise crop remediation. A two-part experiment was conducted to investigate portable Raman spectroscopy as a viable hemp nitrogen deficiency detection method and to compare the technique’s predictive ability against a handheld SPAD (chlorophyll index) meter. Raman spectra and SPAD readings were used to train separate nitrogen deficiency discrimination models. Raman scans displayed characteristic spectral markers indicative of nitrogen deficiency corresponding to vibrational modes of carotenoids, essential pigments for photosynthesis. The Raman-based model consistently predicted nitrogen deficiency in hemp prior to the onset of visible stress symptoms across both experiments, while SPAD only differentiated nitrogen deficiency in the second experiment when the stress was more pronounced. Our findings add to the repertoire of plant stresses that hand-held Raman spectroscopy can detect by demonstrating the ability to provide assessments of nitrogen deficiency. This method can be implemented at the point of cultivation, allowing for timely interventions and efficient resource use.

The cuticle, a hydrophobic layer of cutin and waxes synthesized by plant epidermal cells, is the major barrier to water loss when stomata are closed at night and under water-limited conditions. Elucidating the genetic architecture of natural variation for leaf cuticular conductance ( g _c ) is important for identifying genes relevant to improving crop productivity in drought-prone environments. To this end, we conducted a genome-wide association study of g _c of adult leaves in a maize inbred association panel that was evaluated in four environments (Maricopa, AZ, and San Diego, CA in 2016 and 2017). Five genomic regions significantly associated with g _c were resolved to seven plausible candidate genes (ISTL1, two SEC14 homologs, cyclase-associated protein, a CER7 homolog, GDSL lipase, and β-D-XYLOSIDASE 4). These candidates are potentially involved in cuticle biosynthesis, trafficking and deposition of cuticle lipids, cutin polymerization, and cell wall modification. Laser microdissection RNA sequencing revealed that all these candidate genes, with the exception of the CER7 homolog, were expressed in the zone of the expanding adult maize leaf where cuticle maturation occurs. With direct application to genetic improvement, moderately high average predictive abilities were observed for whole-genome prediction of g _c in locations (0.46 and 0.45) and across all environments (0.52). The findings of this study provide novel insights into the genetic control of g _c and have the potential to help breeders more effectively develop drought-tolerant maize for target environments. Article summary: The cuticle serves as the major barrier to water loss when stomata are closed at night and under water-limited conditions and potentially relevant to drought tolerance in crops. We performed a genome-wide association study to elucidate the genetic architecture of natural variation for maize leaf cuticular conductance. We identified epidermally expressed candidate genes that are potentially involved in cuticle biosynthesis, trafficking and deposition, cutin polymerization, and cell wall modification. Finally, we observed moderately high predictive abilities for whole-genome prediction of leaf cuticular conductance. Collectively, these findings may help breeders more effectively develop drought-tolerant maize.