Abstract
Traditional evaluation of crop biotic and abiotic stresses are time-consuming and labor-intensive limiting the ability to dissect the genetic basis of quantitative traits. A machine learning (ML)-enabled image-phenotyping pipeline for the genetic studies of abiotic stress iron deficiency chlorosis (IDC) of soybean is reported. IDC classification and severity for an association panel of 461 diverse plant-introduction accessions was evaluated using an end-to-end phenotyping workflow. The workflow consisted of a multi-stage procedure including: (1) optimized protocols for consistent image capture across plant canopies, (2) canopy identification and registration from cluttered backgrounds, (3) extraction of domain expert informed features from the processed images to accurately represent IDC expression, and (4) supervised ML-based classifiers that linked the automatically extracted features with expert-rating equivalent IDC scores. ML-generated phenotypic data were subsequently utilized for the genome-wide association study and genomic prediction. The results illustrate the reliability and advantage of ML-enabled image-phenotyping pipeline by identifying previously reported locus and a novel locus harboring a gene homolog involved in iron acquisition. This study demonstrates a promising path for integrating the phenotyping pipeline into genomic prediction, and provides a systematic framework enabling robust and quicker phenotyping through ground-based systems.
Highlights
One major challenge of population genetics is the efficient and precise phenotyping of a large population with replicated tests
A total of 5,916 red-greenblue (RGB) images of individual soybean plots was taken at the same time as field visual rating (FVR) by flowing a standard digital imaging protocol to obtain consistent images of individual plant canopies (Box 1)
A multi-class Support Vector Machine (SVM) model proved adept at categorizing the observations into three groups; an individual SVM was deployed on each susceptibility group to identify the corresponding IDC classes
Summary
One major challenge of population genetics is the efficient and precise phenotyping of a large population with replicated tests. Current soybean IDC phenotyping is heavily based on visual assessment and SPAD measurement of chlorophyll concentration. SPAD measurements are limited to a small fraction of the leaf, and are usually not statistically representative of the disease severity over the complete canopy. These barriers in phenotyping have driven intense efforts by agricultural researchers and engineers to adapt newer technologies in field phenotyping. The current state-of-art in sensor platforms, computing hardware and automation, as well as recent advances in machine learning principles make the phenotyping workflow that seamlessly integrates image phenotyping and ML-based features extraction a promising and potentially transformative approach to accelerate genetic gain. Modeling the major genetic variant and/or a surrogate trait as fixed effects is demonstrated to enhance GP when compared to models with all factors as random
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
