Image-based plant wilting estimation

Abstract

Background Environmental stress due to climate or pathogens is a major threat to modern agriculture. Plant genetic resistance to these stresses is one way to develop more resilient crops, but accurately quantifying plant phenotypic responses can be challenging. Here we develop and test a set of metrics to quantify plant wilting, which can occur in response to abiotic stress such as heat or drought, or in response to biotic stress caused by pathogenic microbes. These metrics can be useful in genomic studies to identify genes and genomic regions underlying plant resistance to a given stress. Results We use two datasets: one of tomatoes inoculated with Ralstonia solanacearum, a soilborne pathogen that causes bacterial wilt disease, and another of soybeans exposed to water stress. For both tomato and soybean, the metrics predict the visual wilting score provided by human experts. Specific to the tomato dataset, we demonstrate that our metrics can capture the genetic difference of bacterium wilt resistance among resistant and susceptible tomato genotypes. In soybean, we show that our metrics can capture the effect of water stress. Conclusion Our proposed RGB image-based wilting metrics can be useful for identifying plant wilting caused by diverse stresses in different plant species.

Image‐based assessment of plant disease progression identifies new genetic loci for resistance to Ralstonia solanacearum in tomato

“…From the plant images, 10 traits were acquired for QTL analysis. A detailed description of the acquisition process was given previously (Yang et al., 2020, 2021). All traits were extracted based on plant size and shape.…”

“…The thresholds used were the same as described in Yang et al. (2021). The resulting segmentation mask was improved with image morphological operations to fill holes and remove noise generated by the thresholding.…”

“…To train the neural networks, stem segmentation ground truth data were generated using Adobe Photoshop and LabelMe (a Python‐based annotation tool) to mark the location of the image pixels belonging to the stem of the plant. More detail about this procedure is provided in (Yang et al., 2020, 2021).…”

Integrated web portal for non-destructive salt sensitivity detection of Camelina sativa seeds using fluorescent and visible light images coupled with machine learning algorithms

“…The performance and effectiveness of the prediction status of seeds and plates is measured using five metrics commonly used in benchmarks of machine learning algorithms: accuracy ( Equation 1 ), sensitivity Equation 2 , specificity Equation 3 , precision Equation 4 and F1 score Equation 5 ( Xu et al., 2022 ; Yang et al., 2023 ).…”

“…For inside sets, three tests for each camera (FLUO: fluorescent, VISFRONT: visible top light, VISBACK: visible back light), attribute (all, only morpho, only color), set (1-6) and salt concentration (50 mM, 100 mM, 150 mM, 200 mM, and 250 mM) were performed (Supplementary Table 1). For between sets, the k-fold cross-validation method with k=10 (Sakeef et al, 2023) was used on 200 mM only since this concentration is present in all sets. The k-fold cross-validation prevents underfitting or overfitting of the model, aligning with the sample size and the split between testing and training in the various tests (Saharan et al, 2021;Charilaou and Battat, 2022;Prusty et al, 2022).…”