Northern leaf blight (NLB) can cause severe yield loss in maize; however, scouting large areas to accurately diagnose the disease is time consuming and difficult. We demonstrate a system capable of automatically identifying NLB lesions in field-acquired images of maize plants with high reliability. This approach uses a computational pipeline of convolutional neural networks (CNNs) that addresses the challenges of limited data and the myriad irregularities that appear in images of field-grown plants. Several CNNs were trained to classify small regions of images as containing NLB lesions or not; their predictions were combined into separate heat maps, then fed into a final CNN trained to classify the entire image as containing diseased plants or not. The system achieved 96.7% accuracy on test set images not used in training. We suggest that such systems mounted on aerial- or ground-based vehicles can help in automated high-throughput plant phenotyping, precision breeding for disease resistance, and reduced pesticide use through targeted application across a variety of plant and disease categories.

Quantitative resistance to plant pathogens, controlled by multiple loci of small effect, is important for food production, food security, and food safety but is poorly understood. To gain insights into the genetic architecture of quantitative resistance in maize, we evaluated a 5,000-inbred-line nested association mapping population for resistance to northern leaf blight, a maize disease of global economic importance. Twenty-nine quantitative trait loci were identified, and most had multiple alleles. The large variation in resistance phenotypes could be attributed to the accumulation of numerous loci of small additive effects. Genome-wide nested association mapping, using 1.6 million SNPs, identified multiple candidate genes related to plant defense, including receptor-like kinase genes similar to those involved in basal defense. These results are consistent with the hypothesis that quantitative disease resistance in plants is conditioned by a range of mechanisms and could have considerable mechanistic overlap with basal resistance.

Many plants, both in nature and in agriculture, are resistant to multiple diseases. Although much of the plant innate immunity system provides highly specific resistance, there is emerging evidence to support the hypothesis that some components of plant defense are relatively nonspecific, providing multiple disease resistance (MDR). Understanding MDR is of fundamental and practical interest to plant biologists, pathologists, and breeders. This review takes stock of the available evidence related to the MDR hypothesis. Questions about MDR are considered primarily through the lens of forward genetics, starting at the organismal level and proceeding to the locus level and, finally, to the gene level. At the organismal level, MDR may be controlled by clusters of R genes that evolve under diversifying selection, by dispersed, pathogen-specific genes, and/or by individual genes providing MDR. Based on the few MDR loci that are well-understood, MDR is conditioned by diverse mechanisms at the locus and gene levels.

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.

Much research has been devoted to understanding the biology of plant-pathogen interactions. The extensive genetic analysis of disease resistance in rice, coupled with the sequenced genome and genomic resources, provides the opportunity to seek convergent evidence implicating specific chromosomal segments and genes in the control of resistance. Published data on quantitative and qualitative disease resistance in rice were synthesized to evaluate the distributions of and associations among resistance loci. Quantitative trait loci (QTL) for resistance to multiple diseases and qualitative resistance loci (R genes) were clustered in the rice genome. R genes and their analogs of the nucleotide binding site–leucine-rich repeat class and genes identified on the basis of differential representation in disease-related EST libraries were significantly associated with QTL. Chromosomal segments associated with broad-spectrum quantitative disease resistance (BS-QDR) were identified. These segments contained numerous positional candidate genes identified on the basis of a range of criteria, and groups of genes belonging to two defense-associated biochemical pathways were found to underlie one BS-QDR region. Genetic dissection of disease QTL confidence intervals is needed to reduce the number of positional candidate genes for further functional analysis. This study provides a framework for future investigations of disease resistance in rice and related crop species.

Background: Studies on host-pathogen interactions in a range of pathosystems have revealed an array of mechanisms by which plants reduce the efficiency of pathogenesis. While R-gene mediated resistance confers highly effective defense responses against pathogen invasion, quantitative resistance is associated with intermediate levels of resistance that reduces disease progress. To test the hypothesis that specific loci affect distinct stages of fungal pathogenesis, a set of maize introgression lines was used for mapping and characterization of quantitative trait loci (QTL) conditioning resistance to Setosphaeria turcica, the causal agent of northern leaf blight (NLB). To better understand the nature of quantitative resistance, the identified QTL were further tested for three secondary hypotheses: (1) that disease QTL differ by host developmental stage; (2) that their performance changes across environments; and (3) that they condition broad-spectrum resistance. Results: Among a set of 82 introgression lines, seven lines were confirmed as more resistant or susceptible than B73. Two NLB QTL were validated in BC₄F₂ segregating populations and advanced introgression lines. These loci, designated qNLB1.02 and qNLB1.06, were investigated in detail by comparing the introgression lines with B73 for a series of macroscopic and microscopic disease components targeting different stages of NLB development. Repeated greenhouse and field trials revealed that qNLB1.06 _Tx303 (the Tx303 allele at bin 1.06) reduces the efficiency of fungal penetration, while qNLB1.02 _B73 (the B73 allele at bin 1.02) enhances the accumulation of callose and phenolics surrounding infection sites, reduces hyphal growth into the vascular bundle and impairs the subsequent necrotrophic colonization in the leaves. The QTL were equally effective in both juvenile and adult plants; qNLB1.06 _Tx303 showed greater effectiveness in the field than in the greenhouse. In addition to NLB resistance, qNLB1.02 _B73 was associated with resistance to Stewart's wilt and common rust, while qNLB1.06 _Tx303 conferred resistance to Stewart's wilt. The non-specific resistance may be attributed to pleiotropy or linkage. Conclusions: Our research has led to successful identification of two reliably-expressed QTL that can potentially be utilized to protect maize from S. turcica in different environments. This approach to identifying and dissecting quantitative resistance in plants will facilitate the application of quantitative resistance in crop protection.