Validation of functional polymorphisms affecting maize plant height by unoccupied aerial systems discovers novel temporal phenotypes

Adak, Alper; Conrad, Clarissa; Chen, Yuanyuan; Wilde, Scott; Murray, Seth C.; Anderson, Steven L.; Subramanian, Nithya

doi:10.1093/g3journal/jkab075

Cited by 23 publications

(29 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is also important to note that higher temporal and image resolution were provided in this study by lower flight altitude (25 m) and higher number of flights (13 and 17 time points) to generate the high throughput phenomic data that have been disregarded so far by most of the current literatures. Higher temporal and image resolutions were proposed to be important in predicting complex traits with higher accuracies, followed by the number of wavelengths and sensors 57 , 58 . Moreover, temporal resolution in high throughput phenomic data is required to dissect the growth stages in greater detail, particularly when the determination of critical time points as selection criteria are a goal in plant breeding programs.…”

Section: Discussionmentioning

confidence: 99%

Phenomic data-facilitated rust and senescence prediction in maize using machine learning algorithms

DeSalvio

Adak

Murray

et al. 2022

Sci Rep

Self Cite

View full text Add to dashboard Cite

Current methods in measuring maize (Zea mays L.) southern rust (Puccinia polyspora Underw.) and subsequent crop senescence require expert observation and are resource-intensive and prone to subjectivity. In this study, unoccupied aerial system (UAS) field-based high-throughput phenotyping (HTP) was employed to collect high-resolution aerial imagery of elite maize hybrids planted in the 2020 and 2021 growing seasons, with 13 UAS flights obtained from 2020 and 17 from 2021. In total, 36 vegetation indices (VIs) were extracted from mosaicked aerial images that served as temporal phenomic predictors for southern rust scored in the field and senescence as scored using UAS-acquired mosaic images. Temporal best linear unbiased predictors (TBLUPs) were calculated using a nested model that treated hybrid performance as nested within flights in terms of rust and senescence. All eight machine learning regressions tested (ridge, lasso, elastic net, random forest, support vector machine with radial and linear kernels, partial least squares, and k-nearest neighbors) outperformed a general linear model with both higher prediction accuracies (92–98%) and lower root mean squared error (RMSE) for rust and senescence scores (linear model RMSE ranged from 65.8 to 2396.5 across all traits, machine learning regressions RMSE ranged from 0.3 to 17.0). UAS-acquired VIs enabled the discovery of novel early quantitative phenotypic indicators of maize senescence and southern rust before being detectable by expert annotation and revealed positive correlations between grain filling time and yield (0.22 and 0.44 in 2020 and 2021), with practical implications for precision agricultural practices.

show abstract

Section: Discussionmentioning

confidence: 99%

Phenomic data-facilitated rust and senescence prediction in maize using machine learning algorithms

DeSalvio

Adak

Murray

et al. 2022

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…The increased density of phenotypic data produced by high throughput phenotyping enables researchers to dynamically measure changes in plant growth, evaluating the impact of genomic variation at different developmental stages. For example, a study using images collected weekly by an unmanned aerial vehicle observed that two SNPs related to maize height had a larger effect during early growth (10–25 cm), with their contribution to this phenotype decreasing towards the end of the season ( Adak et al, 2021 ). In rice, high throughput imagery was used to calculate six vegetation indexes that were used as input traits for the identification of eight quantitative trait loci (QTLs), one of which was corroborated by another analysis using ground-truth agronomic data ( Naito et al, 2017 ).…”

Section: Integrating High Throughput Phenotyping Into Genotype To Phe...mentioning

confidence: 99%

Plant Genotype to Phenotype Prediction Using Machine Learning

et al. 2022

View full text Add to dashboard Cite

Genomic prediction tools support crop breeding based on statistical methods, such as the genomic best linear unbiased prediction (GBLUP). However, these tools are not designed to capture non-linear relationships within multi-dimensional datasets, or deal with high dimension datasets such as imagery collected by unmanned aerial vehicles. Machine learning (ML) algorithms have the potential to surpass the prediction accuracy of current tools used for genotype to phenotype prediction, due to their capacity to autonomously extract data features and represent their relationships at multiple levels of abstraction. This review addresses the challenges of applying statistical and machine learning methods for predicting phenotypic traits based on genetic markers, environment data, and imagery for crop breeding. We present the advantages and disadvantages of explainable model structures, discuss the potential of machine learning models for genotype to phenotype prediction in crop breeding, and the challenges, including the scarcity of high-quality datasets, inconsistent metadata annotation and the requirements of ML models.

show abstract

“…It is also important to note that higher temporal and image resolution were provided in this study by lower ight altitude (25 meters) and higher number of ights (13 and 17 time points) to generate the high throughput phenomic data that have been disregarded so far by most of the current literatures. Higher temporal and image resolutions were proposed to be important in predicting complex traits with higher accuracies, followed by the number of wavelengths and sensors 50,51 . Moreover, temporal resolution in high throughput phenomic data is required to dissect the growth stages in greater detail, particularly when the determination of critical time points as selection criteria are a goal in plant breeding programs.…”

Section: High Throughput Phenotyping: Implications For Plant Breeders and Geneticistsmentioning

confidence: 99%

Phenomic Data-Facilitated Rust and Senescence Prediction in Maize Using Machine Learning Algorithms

DeSalvio

Adak

Murray

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Current methods in measuring maize (Zea mays L.) southern rust (Puccinia polyspora Underw.) and subsequent crop senescence require expert observation which are resource-intensive and prone to subjectivity. In this study, unoccupied aerial system (UAS) field-based high-throughput phenotyping (HTP) was employed to collect high-resolution aerial imagery of elite maize hybrids planted in the 2020 and 2021 growing seasons, with 13 UAS flights obtained from 2020 and 17 from 2021. Vegetation indices (VIs) were extracted from mosaicked aerial images that served as temporal phenomic predictors for southern rust scored in the field and senescence as scored using UAS-acquired mosaic images. Temporal best linear unbiased predictors (TBLUPs) were calculated using a nested model that treated the pedigree performances as nested within flights in terms of rust and senescence. All eight machine learning regressions tested (ridge, lasso, elastic net, random forest, support vector machine with radial and linear kernels, partial least squares, and k-nearest neighbors) outperformed a general linear model with both higher prediction accuracies (92-98%) and lower root mean squared error (RMSE) for rust and senescence scores. UAS-acquired VIs enabled the discovery of novel early quantitative phenotypic indicators of maize senescence and southern rust before being detectable by expert annotation and revealed positive correlations between grain filling time and yield (0.22 and 0.44 in 2020 and 2021), with practical implications for precision agricultural practices.

show abstract

Validation of functional polymorphisms affecting maize plant height by unoccupied aerial systems discovers novel temporal phenotypes

Cited by 23 publications

References 55 publications

Phenomic data-facilitated rust and senescence prediction in maize using machine learning algorithms

Phenomic data-facilitated rust and senescence prediction in maize using machine learning algorithms

Plant Genotype to Phenotype Prediction Using Machine Learning

Phenomic Data-Facilitated Rust and Senescence Prediction in Maize Using Machine Learning Algorithms

Contact Info

Product

Resources

About