Search bioRxiv⌕ Search

bioRxiv · 10.64898/2026.06.03.729887

Aerial imagery and deep learning accurately estimate maize foliar disease severity

Abstract

Southern leaf blight (SLB) is a foliar disease of maize (Zea mays L.) caused by the necrotrophic fungal pathogen Cochliobolus heterostrophus. Genetic resistance is the most effective control method for SLB. Developing disease resistant maize lines requires field trials during which disease phenotypes must be visually assessed. Remote sensing using drones is an emerging technology that can be leveraged for high-throughput phenotyping of disease severity that is otherwise labor-intensive and subjective. This project used a deep learning approach to estimate SLB disease severity of single-row maize plots from drone imagery. Over 26,000 plot-level images produced from flights conducted across three growing seasons were labeled with in-field visual scores taken contemporaneously by expert raters. Variation in environmental conditions contributed to a labeled image dataset that reflects the complexity of agronomic field experiments. We assessed the ability of nine deep learning models from three architectural families to estimate disease severity. The best-performing model, EVA-02-B, achieved strong cross year generalization (R2 = 0.697). Error analysis found that performance was more strongly associated with seasonal disease progression and flight-score time offset than with image-level noise. UAV-based deep learning estimated SLB severity with comparable precision to expert raters. This study lays the groundwork for integrating automated phenotypes into genetic studies of disease resistance. PLAIN LANGUAGE SUMMARYSouthern leaf blight (SLB) of maize is a disease that causes yield loss worldwide and developing resistant varieties offers the best hope for controlling the disease. Studying SLB resistance requires plant pathologists to visually score severity in the field, a labor-intensive method that requires expertise. To address these challenges, we asked whether SLB severity scoring could be automated using drone images and artificial intelligence (AI). We trained AI models using three years of image and score data then compared the results to visual scores taken by five plant pathologists. The best performing AI model showed a similar level of consistency to the experts and proved capable of scoring severity despite unpredictable and uncontrollable conditions that affect field imaging experiments such as weeds or shadows. These findings provide a validated method that improves the efficiency of maize disease research, a critical area of study for agricultural sustainability and productivity.

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Hammett, C. H., Rumley, K., Balint-Kurti, P., Gage, J. L.. 2026-06-06. Aerial imagery and deep learning accurately estimate maize foliar disease severity. https://doi.org/10.64898/2026.06.03.729887

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

Combined heat and drought stress alters chromatin accessibility and primes potato abscisic acid biosynthesis

Due to climate change, abiotic stresses get increasingly more frequent, in a combined and recurrent manner in the same growing season. Chromatin accessibility enables efficient responses to combined stress and priming for reoccurring stresses. To study the regulatory basis of priming, we profiled chromatin accessibility and gene expression in leaves of two genetically distinct potato cultivars after prolonged heat, drought, waterlogging, and combined heat and drought. We show that most accessibility changes are stress-specific, however, drought stress elicits a distinct transcriptional response as compared to combined heat and drought stress, with strong chaperone induction and dampened abscisic acid signalling, despite water deficit. A second cycle of combined stress reveals transcriptional memory of abscisic acid biosynthesis gene StNCED3 and its transcriptional activator StWRKY33b, providing a new mechanistic insight of abiotic stress memory in a staple crop important for global food security.

plant biology↗

High-throughput microarray analysis provides new insight into optimising Rubisco yield from diverse plants

Interest in plant-based proteins is increasing due to environmental, ethical, and health considerations. Ribulose-1,5-bisphosphate carboxylase/oxygenase (Rubisco), the most abundant protein on Earth, is present in all green leafy biomass and possesses excellent nutritional and functional properties. Despite its potential, Rubisco remains underutilised because extraction methods are often costly, inefficient, and influenced by species-specific differences. Moreover, the impact on Rubisco yield of cell wall-protein interactions remains poorly understood. We applied Microarray Polymer Profiling (MAPP), a high-throughput platform for simultaneous polysaccharide and protein mapping, to characterise diverse leafy biomass sources. This approach revealed interspecies variation and glycan-protein interactions that influence protein extractability and these insights inform biomass selection and optimisation of extraction protocols to improve Rubisco yield. MAPP was also used to evaluate the effects of carbohydrate-active enzymes on Rubisco recovery through targeted cell wall modification.

plant biology↗

Leaf ionomic stability shapes drought adaptation in pearl millet

Pearl millet is a staple cereal of semi-arid West Africa, where early-season water deficit constrains vegetative establishment and yield. While the genetic architecture of the pearl millet foliar ionome has been characterised under well-watered conditions, how this ionome reorganises under drought, and whether this reorganisation has a distinct genetic basis, remains unknown. We profiled the drought-response of 17 foliar elements in 175 diverse pearl millet inbred lines over two seasons in Senegal. The foliar concentration of two co-regulated groups of elements changed reproducibly under early water stress across both years. Leaf ion stability, rather than plasticity, was associated with the maintenance of flowering time and plant biomass, suggesting that drought adaptation in pearl millet relies more on ionomic stability than on adaptive shifts in elemental composition. Among the 17 elements, only potassium showed a significant genotype-by-treatment interaction suggesting that genetic variation contributes to differences in potassium response to drought. Genome-wide association mapping on potassium plasticity in response to drought identified a locus, designated qKP-6, that limits potassium depletion under stress without penalising constitutive potassium levels. This locus represents a candidate region for the genetic control of potassium plasticity under drought. This work provides new insights into the genetic control of mineral nutrition under water deficit in pearl millet, and highlights leaf potassium concentration as a genetically controlled component of drought-responsive ionomic variation with potential implications for drought tolerance.

plant biology↗