Dataset Information

An Exploration of Deep-Learning Based Phenotypic Analysis to Detect Spike Regions in Field Conditions for UK Bread Wheat.

ABSTRACT: Wheat is one of the major crops in the world, with a global demand expected to reach 850 million tons by 2050 that is clearly outpacing current supply. The continual pressure to sustain wheat yield due to the world's growing population under fluctuating climate conditions requires breeders to increase yield and yield stability across environments. We are working to integrate deep learning into field-based phenotypic analysis to assist breeders in this endeavour. We have utilised wheat images collected by distributed CropQuant phenotyping workstations deployed for multiyear field experiments of UK bread wheat varieties. Based on these image series, we have developed a deep-learning based analysis pipeline to segment spike regions from complicated backgrounds. As a first step towards robust measurement of key yield traits in the field, we present a promising approach that employ Fully Convolutional Network (FCN) to perform semantic segmentation of images to segment wheat spike regions. We also demonstrate the benefits of transfer learning through the use of parameters obtained from other image datasets. We found that the FCN architecture had achieved a Mean classification Accuracy (MA) >82% on validation data and >76% on test data and Mean Intersection over Union value (MIoU) >73% on validation data and and >64% on test datasets. Through this phenomics research, we trust our attempt is likely to form a sound foundation for extracting key yield-related traits such as spikes per unit area and spikelet number per spike, which can be used to assist yield-focused wheat breeding objectives in near future.

SUBMITTER: Alkhudaydi T

PROVIDER: S-EPMC7706304 | biostudies-literature | 2019

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

An Exploration of Deep-Learning Based Phenotypic Analysis to Detect Spike Regions in Field Conditions for UK Bread Wheat.

Alkhudaydi Tahani T Reynolds Daniel D Griffiths Simon S Zhou Ji J de la Iglesia Beatriz B

Plant phenomics (Washington, D.C.) 20190731

Wheat is one of the major crops in the world, with a global demand expected to reach 850 million tons by 2050 that is clearly outpacing current supply. The continual pressure to sustain wheat yield due to the world's growing population under fluctuating climate conditions requires breeders to increase yield and yield stability across environments. We are working to integrate deep learning into field-based phenotypic analysis to assist breeders in this endeavour. We have utilised wheat images col ...[more]

PMID: 33313535

Similar Datasets

Project description:BackgroundUnderstanding root system morphology in bread wheat is critical for identifying root traits to breed cultivars with improved resource uptake and better adaptation to adverse environments. Variability in root morphological traits at early vegetative stages was examined among 184 bread wheat genotypes originating from 37 countries grown in a semi-hydroponic phenotyping system.ResultsAt the onset of tillering (Z2.1, 35?days after transplanting), plants had up to 42?cm in shoot height and 158?cm long in root depth. Phenotypic variation existed for both shoot and root traits, with a maximal 4.3-fold difference in total root length and 5-fold difference in root dry mass among the 184 genotypes. Of the 41 measured traits, 24 root traits and four shoot traits had larger coefficients of variation (CV???0.25). Strong positive correlations were identified for some key root traits (i.e., root mass, root length, and these parameters at different depths) and shoot traits (i.e., shoot mass and tiller number) (P???0.05). The selected 25 global traits (at whole-plant level) contributed to one of the five principal components (eigenvalues>?1) capturing 83.0% of the total variability across genotypes. Agglomerative hierarchical clustering analysis separated the 184 genotypes into four (at a rescaled distance of 15) or seven (at a rescaled distance of 10) major groups based on the same set of root traits. Strong relationships between performance traits (dry mass) with several functional traits such as specific root length, root length intensity and root tissue density suggest their linkage to plant growth and fitness strategies.ConclusionsLarge phenotypic variability in root system morphology in wheat genotypes was observed at the tillering stage using established semi-hydroponic phenotyping techniques. Phenotypic differences in and trait correlations among some interesting root traits may be considered for breeding wheat cultivars with efficient water acquisition and better adaptation to abiotic stress.

Dataset Information

An Exploration of Deep-Learning Based Phenotypic Analysis to Detect Spike Regions in Field Conditions for UK Bread Wheat.

Publications

An Exploration of Deep-Learning Based Phenotypic Analysis to Detect Spike Regions in Field Conditions for UK Bread Wheat.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets