Rodene, E. | Search bioRxiv

bioRxiv2021

A UAV-based high-throughput phenotyping approach to assess time-series nitrogen responses and identify traits associated genetic components in maize

Advancements in the use of genome-wide markers have provided new opportunities for dissecting the genetic components that control phenotypic trait variation. However, cost-effectively characterizing agronomically important phenotypic traits on a large scale remains a bottleneck. Unmanned aerial vehicle (UAV)-based high-throughput phenotyping has recently become a prominent method, as it allows large numbers of plants to be analyzed in a time-series manner. In this experiment, 233 inbred lines from the maize diversity panel were grown in a replicated incomplete block under both nitrogen-limited conditions and following conventional agronomic practices. UAV images were collected during different plant developmental stages throughout the growing season. A pipeline for extracting plot-level images, filtering images to remove non-foliage elements, and calculating canopy coverage and greenness ratings based on vegetation indices (VIs) was developed. After applying the pipeline, about half a million plot-level image clips were obtained for 12 different time points. High correlations were detected between VIs and ground truth physiological and yield-related traits collected from the same plots, i.e., Vegetative Index (VEG) vs. leaf nitrogen levels (Pearson correlation coefficient, R = 0.73), Woebbecke index vs. leaf area (R = -0.52), and Visible Atmospherically Resistant Index (VARI) vs. 20 kernel weight - a yield component trait (R = 0.40). The genome-wide association study was performed using canopy coverage and each of the VIs at each date, resulting in N = 29 unique genomic regions associated with image extracted traits from three or more of the 12 total time points. A candidate gene Zm00001d031997, a maize homolog of the Arabidopsis HCF244 (high chlorophyll fluorescence 244), located underneath the leading SNPs of the canopy coverage associated signals that were repeatedly detected under both nitrogen conditions. The plot-level time-series phenotypic data and the trait-associated genes provide great opportunities to advance plant science and to facilitate plant breeding.

plant biology↗

bioRxiv2019

Simulated Plant Images Improve Maize Leaf Counting Accuracy

Automatically scoring plant traits using a combination of imaging and deep learning holds promise to accelerate data collection, scientific inquiry, and breeding progress. However, applications of this approach are currently held back by the availability of large and suitably annotated training datasets. Early training datasets targeted arabidopsis or tobacco. The morphology of these plants quite different from that of grass species like maize. Two sets of maize training data, one real-world and one synthetic were generated and annotated for late vegetative stage maize plants using leaf count as a model trait. Convolutional neural networks (CNNs) trained on entirely synthetic data provided predictive power for scoring leaf number in real-world images. This power was less than CNNs trained with equal numbers of real-world images, however, in some cases CNNs trained with larger numbers of synthetic images outperformed CNNs trained with smaller numbers of real-world images. When real-world training images were scarce, augmenting real-world training data with synthetic data provided improved prediction accuracy. Quantifying leaf number over time can provide insight into plant growth rates and stress responses, and can help to parameterize crop growth models. The approaches and annotated training data described here may help future efforts to develop accurate leaf counting algorithms for maize.

plant biology↗