Using Hyperspectral Imagery to Detect an Invasive Fungal Pathogen and Symptom Severity in Pinus strobiformis Seedlings of Different Genotypes

Making the Genotypic Variation Visible: Hyperspectral Phenotyping in Scots Pine Seedlings

Hyperspectral reflectance contains valuable information about leaf functional traits, which can indicate a plant's physiological status. Therefore, using hyperspectral reflectance for high-throughput phenotyping of foliar traits could be a powerful tool for tree breeders and nursery practitioners to distinguish and select seedlings with desired adaptation potential to local environments. We evaluated the use of 2 nondestructive methods (i.e., leaf and proximal/canopy) measuring hyperspectral reflectance in the 350- to 2,500-nm range for phenotyping on 1,788 individual Scots pine seedlings belonging to lowland and upland ecotypes of 3 different local populations from the Czech Republic. Leaf-level measurements were collected using a spectroradiometer and a contact probe with an internal light source to measure the biconical reflectance factor of a sample of needles placed on a black background in the contact probe field of view. The proximal canopy measurements were collected under natural solar light, using the same spectroradiometer with fiber optical cable to collect data on individual seedlings' hemispherical conical reflectance factor. The latter method was highly susceptible to changes in incoming radiation. Both spectral datasets showed statistically significant differences among Scots pine populations in the whole spectral range. Moreover, using random forest and support vector machine learning algorithms, the proximal data obtained from the top of the seedlings offered up to 83% accuracy in predicting 3 different Scots pine populations. We conclude that both approaches are viable for hyperspectral phenotyping to disentangle the phenotypic and the underlying genetic variation within Scots pine seedlings.

Comparative Association Mapping Reveals Conservation of Major Gene Resistance to White Pine Blister Rust in Southwestern White Pine (Pinus strobiformis) and Limber Pine (P. flexilis)

All native North American white pines are highly susceptible to white pine blister rust (WPBR) caused by Cronartium ribicola. Understanding genomic diversity and molecular mechanisms underlying genetic resistance to WPBR remains one of the great challenges in improvement of white pines. To compare major gene resistance (MGR) present in two species, southwestern white pine (Pinus strobiformis) Cr3 and limber pine (P. flexilis) Cr4, we performed association analyses of Cr3-controlled resistant traits using single nucleotide polymorphism (SNP) assays designed with Cr4-linked polymorphic genes. We found that ∼70% of P. flexilis SNPs were transferable to P. strobiformis. Furthermore, several Cr4-linked SNPs were significantly associated with the Cr3-controlled traits in P. strobiformis families. The most significantly associated SNP (M326511_1126R) almost colocalized with Cr4 on the Pinus consensus linkage group 8, suggesting that Cr3 and Cr4 might be the same R locus, or have localizations very close to each other in the syntenic region of the P. strobiformis and P. flexilis genomes. M326511_1126R was identified as a nonsynonymous SNP, causing amino acid change (Val₃₇₆Ile) in a putative pectin acetylesterase, with coding sequences identical between the two species. Moreover, top Cr3-associated SNPs were further developed as TaqMan genotyping assays, suggesting their usefulness as marker-assisted selection (MAS) tools to distinguish genotypes between quantitative resistance and MGR. This work demonstrates the successful transferability of SNP markers between two closely related white pine species in the hybrid zone, and the possibility for deployment of MAS tools to facilitate long-term WPBR management in P. strobiformis breeding and conservation.

Plant Disease Sensing: Studying Plant-Pathogen Interactions at Scale

Plant disease threatens the environmental and financial sustainability of crop production, causing $220 billion in annual losses. The dire threat disease poses to modern agriculture demands tools for better detection and monitoring to prevent crop loss and input waste. The nascent discipline of plant disease sensing, or the science of using proximal and/or remote sensing to detect and diagnose disease, offers great promise to extend monitoring to previously unachievable resolutions, a basis to construct multiscale surveillance networks for early warning, alert, and response at low latency, an opportunity to mitigate loss while optimizing protection, and a dynamic new dimension to agricultural systems biology. Despite its revolutionary potential, plant disease sensing remains an underdeveloped discipline, with challenges facing both fundamental study and field application. This article offers a perspective on the current state and future of plant disease sensing, highlights remaining gaps to be filled, and presents a bold vision for the future of global agriculture.

Hyperspectral Imaging Combined with Machine Learning for the Detection of Fusiform Rust Disease Incidence in Loblolly Pine Seedlings

Loblolly pine is an economically important timber species in the United States, with almost 1 billion seedlings produced annually. The most significant disease affecting this species is fusiform rust, caused by Cronartium quercuum f. sp. fusiforme. Testing for disease resistance in the greenhouse involves artificial inoculation of seedlings followed by visual inspection for disease incidence. An automated, high-throughput phenotyping method could improve both the efficiency and accuracy of the disease screening process. This study investigates the use of hyperspectral imaging for the detection of diseased seedlings. A nursery trial comprising families with known in-field rust resistance data was conducted, and the seedlings were artificially inoculated with fungal spores. Hyperspectral images in the visible and near-infrared region (400–1000 nm) were collected six months after inoculation. The disease incidence was scored with traditional methods based on the presence or absence of visible stem galls. The seedlings were segmented from the background by thresholding normalized difference vegetation index (NDVI) images, and the delineation of individual seedlings was achieved through object detection using the Faster RCNN model. Plant parts were subsequently segmented using the DeepLabv3+ model. The trained DeepLabv3+ model for semantic segmentation achieved a pixel accuracy of 0.76 and a mean Intersection over Union (mIoU) of 0.62. Crown pixels were segmented using geometric features. Support vector machine discrimination models were built for classifying the plants into diseased and non-diseased classes based on spectral data, and balanced accuracy values were calculated for the comparison of model performance. Averaged spectra from the whole plant (balanced accuracy = 61%), the crown (61%), the top half of the stem (77%), and the bottom half of the stem (62%) were used. A classification model built using the spectral data from the top half of the stem was found to be the most accurate, and resulted in an area under the receiver operating characteristic curve (AUC) of 0.83.