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.

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.

Summary: We conducted a comprehensive analysis of virulence in the fungal wheat pathogen Zymoseptoria tritici using quantitative trait locus (QTL) mapping. High‐throughput phenotyping based on automated image analysis allowed the measurement of pathogen virulence on a scale and with a precision that was not previously possible. Across two mapping populations encompassing more than 520 progeny, 540 710 pycnidia were counted and their sizes and grey values were measured. A significant correlation was found between pycnidia size and both spore size and number. Precise measurements of percentage leaf area covered by lesions provided a quantitative measure of host damage. Combining these large and accurate phenotypic datasets with a dense panel of restriction site‐associated DNA sequencing (RADseq) genetic markers enabled us to genetically dissect pathogen virulence into components related to host damage and those related to pathogen reproduction. We showed that different components of virulence can be under separate genetic control. Large‐ and small‐effect QTLs were identified for all traits, with some QTLs specific to mapping populations, cultivars and traits and other QTLs shared among traits within the same mapping population. We associated the presence of four accessory chromosomes with small, but significant, increases in several virulence traits, providing the first evidence for a meaningful function associated with accessory chromosomes in this organism. A large‐effect QTL involved in host specialization was identified on chromosome 7, leading to the identification of candidate genes having a large effect on virulence.