Semantic Segmentation of Sorghum Using Hyperspectral Data Identifies Genetic Associations

Miao, Chenyong; Pages, Alejandro; Xu, Zheng; Rodene, Eric; Yang, Jinliang; Schnable, James C.

doi:10.34133/2020/4216373

Cited by 41 publications

(49 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The phenotypically constrained subset of 292 SAP lines were imaged at the University of Nebraska's Greenhouse Innovation Center (UNGIC). Imaging lasted approximately one month centered on reproductive development and each plant was imaged using a set of five cameras including top views and side views from multiple angles and hyperspectral imaging from a single side view perspective 26,34,35 . Two methods were employed to extract plant height at individual time points.…”

Section: Genetic Associations With Sorghum Height At Different Time Pmentioning

confidence: 99%

“…The first was whole plant segmentation, an approach widely used in plant image analysis 36 : segmentation of an image into plant pixels and not plant pixels, and measuring height by the difference between the minimum and maximum y-axis values for plant pixels [ Figure 2A]. The second approach was a recently described method 26 to semantically segment "plant pixels" of sorghum plants into separate stalk, leaf, and panicle classes [ Figure S1, 2B]. There are many different ways to measure the plant height 26,37 .…”

Section: Genetic Associations With Sorghum Height At Different Time Pmentioning

confidence: 99%

“…The second approach was a recently described method 26 to semantically segment "plant pixels" of sorghum plants into separate stalk, leaf, and panicle classes [ Figure S1, 2B]. There are many different ways to measure the plant height 26,37 . Generally, researchers in the field have preferred to benchmark on the height of stalk, height to the uppermost leaf collar, or the height to the tip of the inflorescence rather than the height to the highest leaf tip.…”

Section: Genetic Associations With Sorghum Height At Different Time Pmentioning

confidence: 99%

“…Generally, researchers in the field have preferred to benchmark on the height of stalk, height to the uppermost leaf collar, or the height to the tip of the inflorescence rather than the height to the highest leaf tip. An advantage of the latter method -semantic segmentation -is that it can be used to measure a version of plant height which more closely approximates how height is measured in the field 26 . Sorghum plant height measured by whole plant segmentation tended to oscillate over time as new leaves emerged, while sorghum plant height measured via the semantic segmentation method tended to be monotonically increasing [ Figure 2C].…”

Section: Genetic Associations With Sorghum Height At Different Time Pmentioning

confidence: 99%

“…This population was grown and imaged through vegetative and reproductive development in a high throughput phenotyping facility. Organ level semantic segmentation from hyperspectral images was employed to extract phenotypic values 26 . Three cloned sorghum genes controlling height -dwarf1, dwarf2, and dwarf3 -are segregating in the Sorghum Association Panel.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Functional principal component based time-series genome-wide association in sorghum

Miao

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

The phenotypes of plants develop over time and change in response to the environment. New engineering and computer vision technologies track phenotypic change over time. Identifying genetic loci regulating differences in the pattern of phenotypic change remains challenging. In this study we used functional principal component analysis (FPCA) to achieve this aim. Time-series phenotype data was collected from a sorghum diversity panel using a number of technologies including RGB and hyperspectral imaging. Imaging lasted for thirty-seven days centered on reproductive transition. A new higher density SNP set was generated for the same population. Several genes known to controlling trait variation in sorghum have been cloned and characterized. These genes were not confidently identified in genome-wide association analyses at single time points. However, FPCA successfully identified the same known and characterized genes. FPCA analyses partitioned the role these genes play in controlling phenotype. Partitioning was consistent with the known molecular function of the individual cloned genes. FPCA-based genome-wide association studies can enable robust time-series mapping analyses in a wide range of contexts. Time-series analysis can increase the accuracy and power of quantitative genetic analyses. 2/173/17 7/17

show abstract

Section: Genetic Associations With Sorghum Height At Different Time Pmentioning

confidence: 99%

Section: Genetic Associations With Sorghum Height At Different Time Pmentioning

confidence: 99%

Section: Genetic Associations With Sorghum Height At Different Time Pmentioning

confidence: 99%

Section: Genetic Associations With Sorghum Height At Different Time Pmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Functional principal component based time-series genome-wide association in sorghum

Miao

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Leveraging deep learning for dollar spot detection and quantification in turfgrass

Kitchin,

Sneed,

McCall

2024

Crop Science

View full text Add to dashboard Cite

This study evaluates the effectiveness of fine‐tuning a semantic segmentation model to identify and quantify dollar spot in turfgrasses, the most extensively managed and researched disease of turfgrasses worldwide. Using the DeepLabV3+ model, recognized for its capability to segment complex shapes and integrate multi‐scale contextual information, the research leveraged a diverse dataset comprising various turfgrass species, disease stages, and lighting conditions to ensure robust model training. The trained model is able to identify and segment disease instances accurately and precisely, and the results indicate the potential for model‐based assessment to outperform traditional visual assessment methods in speed, accuracy, and consistency. The development of deep learning models on extensive datasets like ImageNet requires significant computational resources. However, by fine‐tuning a pretrained semantic segmentation model, we adapted it for disease segmentation using only a standard personal computer's graphics processing unit. This approach not only conserves resources but also highlights the practicality of deploying advanced deep learning applications in turfgrass pathology with limited computational capacity. The proposed model provides a new tool for turfgrass researchers and professionals to rapidly and accurately quantify this important disease under real‐world growing conditions. Additionally, the findings suggest the potential to apply deep learning algorithms to other turfgrass diseases to support data‐driven decisions. This could enhance disease management practices and improve decision‐making processes for fungicidal treatments, thereby improving the economic and environmental sustainability of turfgrass management.

show abstract

Leveraging soil mapping and machine learning to improve spatial adjustments in plant breeding trials

Carroll,

Riera,

Miller

et al. 2024

Crop Science

View full text Add to dashboard Cite

Spatial adjustments are used to improve the estimate of plot seed yield across crops and geographies. Moving means (MM) and P‐Spline are examples of spatial adjustment methods used in plant breeding trials to deal with field heterogeneity. Within the trial, spatial variability primarily comes from soil feature gradients, such as nutrients, but a study of the importance of various soil factors including nutrients is lacking. We analyzed plant breeding progeny row (PR) and preliminary yield trial (PYT) data of a public soybean breeding program across 3 years consisting of 43,545 plots. We compared several spatial adjustment methods: unadjusted (as a control), MM adjustment, P‐spline adjustment, and a machine learning‐based method called XGBoost. XGBoost modeled soil features at: (a) the local field scale for each generation and per year, and (b) all inclusive field scale spanning all generations and years. We report the usefulness of spatial adjustments at both PR and PYT stages of field testing and additionally provide ways to utilize interpretability insights of soil features in spatial adjustments. Our work shows that using soil features for spatial adjustments increased the relative efficiency by 81%, reduced the similarity of selection by 30%, and reduced the Moran's I from 0.13 to 0.01 on average across all experiments. These results empower breeders to further refine selection criteria to make more accurate selections and select for macro‐ and micro‐nutrients stress tolerance.

show abstract

Semantic Segmentation of Sorghum Using Hyperspectral Data Identifies Genetic Associations

Cited by 41 publications

References 40 publications

Functional principal component based time-series genome-wide association in sorghum

Functional principal component based time-series genome-wide association in sorghum

Leveraging deep learning for dollar spot detection and quantification in turfgrass

Leveraging soil mapping and machine learning to improve spatial adjustments in plant breeding trials

Contact Info

Product

Resources

About