Effect of initial inoculum on the temporal and spatial dynamics of wheat blast under field conditions in Bolivia.

Epidemiological studies to better understand wheat blast (WB) spatial and temporal patterns were conducted in three field environments in Bolivia between 2019 and 2020. The temporal dynamics of wheat leaf blast (WLB) and spike blast (WSB) were best described by the logistic model compared to the Gompertz and exponential models. The non-linear logistic infection rates (rL) were higher under defined inoculation in experiments two and three than under undefined inoculation in experiment one, and they were also higher for WSB than for WLB. The onset of WLB began with a spatial cluster pattern according to autocorrelation analysis and Moran's Index (I) values, with higher severity and earlier onset for defined than for undefined inoculation until the last sampling time. The WSB onset did not start with a spatial cluster pattern; instead, it was detected later until the last sampling date across experiments, with higher severity and earlier onset for defined than for undefined inoculation. Maximum severity (Kmax) was 1.0 for WSB, and less than 1.0 for WLB. Aggregation of WLB and WSB was higher for defined than for undefined inoculation. The directionality of hotspot development was similar for both WLB and WSB, mainly occurring concentrically for defined inoculation. Our results show no evidence of synchronized development but suggest a temporal and spatial progression of disease symptoms on wheat leaves and spikes. Thus, we recommend that monitoring and management of WB should be considered during early growth stages of wheat planted in areas of high risk.

Monitoring tar spot disease in corn at different canopy and temporal levels using aerial multispectral imaging and machine learning.

Introduction: Tar spot is a high-profile disease, causing various degrees of yield losses on corn (Zea mays L.) in several countries throughout the Americas. Disease symptoms usually appear at the lower canopy in corn fields with a history of tar spot infection, making it difficult to monitor the disease with unmanned aircraft systems (UAS) because of occlusion. Methods: UAS-based multispectral imaging and machine learning were used to monitor tar spot at different canopy and temporal levels and extract epidemiological parameters from multiple treatments. Disease severity was assessed visually at three canopy levels within micro-plots, while aerial images were gathered by UASs equipped with multispectral cameras. Both disease severity and multispectral images were collected from five to eleven time points each year for two years. Image-based features, such as single-band reflectance, vegetation indices (VIs), and their statistics, were extracted from ortho-mosaic images and used as inputs for machine learning to develop disease quantification models. Results and discussion: The developed models showed encouraging performance in estimating disease severity at different canopy levels in both years (coefficient of determination up to 0.93 and Lin's concordance correlation coefficient up to 0.97). Epidemiological parameters, including initial disease severity or y0 and area under the disease progress curve, were modeled using data derived from multispectral imaging. In addition, results illustrated that digital phenotyping technologies could be used to monitor the onset of tar spot when disease severity is relatively low (< 1%) and evaluate the efficacy of disease management tactics under micro-plot conditions. Further studies are required to apply and validate our methods to large corn fields.

Wheat Spike Blast Image Classification Using Deep Convolutional Neural Networks.

Wheat blast is a threat to global wheat production, and limited blast-resistant cultivars are available. The current estimations of wheat spike blast severity rely on human assessments, but this technique could have limitations. Reliable visual disease estimations paired with Red Green Blue (RGB) images of wheat spike blast can be used to train deep convolutional neural networks (CNN) for disease severity (DS) classification. Inter-rater agreement analysis was used to measure the reliability of who collected and classified data obtained under controlled conditions. We then trained CNN models to classify wheat spike blast severity. Inter-rater agreement analysis showed high accuracy and low bias before model training. Results showed that the CNN models trained provide a promising approach to classify images in the three wheat blast severity categories. However, the models trained on non-matured and matured spikes images showing the highest precision, recall, and F1 score when classifying the images. The high classification accuracy could serve as a basis to facilitate wheat spike blast phenotyping in the future.

Contour-Based Detection and Quantification of Tar Spot Stromata Using Red-Green-Blue (RGB) Imagery.

Quantifying symptoms of tar spot of corn has been conducted through visual-based estimations of the proportion of leaf area covered by the pathogenic structures generated by Phyllachora maydis (stromata). However, this traditional approach is costly in terms of time and labor, as well as prone to human subjectivity. An objective and accurate method, which is also time and labor-efficient, is of an urgent need for tar spot surveillance and high-throughput disease phenotyping. Here, we present the use of contour-based detection of fungal stromata to quantify disease intensity using Red-Green-Blue (RGB) images of tar spot-infected corn leaves. Image blocks (n = 1,130) generated by uniform partitioning the RGB images of leaves, were analyzed for their number of stromata by two independent, experienced human raters using ImageJ (visual estimates) and the experimental stromata contour detection algorithm (SCDA; digital measurements). Stromata count for each image block was then categorized into five classes and tested for the agreement of human raters and SCDA using Cohen's weighted kappa coefficient (κ). Adequate agreements of stromata counts were observed for each of the human raters to SCDA (κ = 0.83) and between the two human raters (κ = 0.95). Moreover, the SCDA was able to recognize "true stromata," but to a lesser extent than human raters (average median recall = 90.5%, precision = 89.7%, and Dice = 88.3%). Furthermore, we tracked tar spot development throughout six time points using SCDA and we obtained high agreement between area under the disease progress curve (AUDPC) shared by visual disease severity and SCDA. Our results indicate the potential utility of SCDA in quantifying stromata using RGB images, complementing the traditional human, visual-based disease severity estimations, and serve as a foundation in building an accurate, high-throughput pipeline for the scoring of tar spot symptoms.