From smartphone to gene: Automated image-based phenotyping captures flowering diversity of common buckwheat

Abstract

Common buckwheat (Fagopyrum esculentum Moench) exhibits an indeterminate flowering habit, resulting in the simultaneous occurrence of flowering, seed development and seed ripening. This contributes to yield losses and complicates mechanized harvesting. Therefore, the development of varieties with a desirable flowering pattern is a breeding priority in buckwheat. However, phenotyping of buckwheat flowering under field conditions remains challenging because manual assessments are time consuming and expertise dependent. Here, we show that imaging devices such as smartphones or cameras can be used for phenotyping of flowering traits in a buckwheat collection encompassing 169 accessions. Flowering traits describing flowering time (n=10), flowering intensity (n=6) and abscission (n=6) were extracted from 37,078 images captured over five growing seasons using a Mask R-CNN segmentation model combined with statistical modelling of flowering dynamics. The 22 extracted traits were highly heritable (0.5 < h2 < 0.93) and correlated well (0.84 <r< 0.94) with manually assessed flowering stages while providing additional information on flowering intensity. Genome-wide association studies revealed 171 genomic regions associated with flowering traits, including marker-trait associations for agronomically important breeding targets. Candidate genes had functional annotations including "Auxin response factor" and "Ethylene-insensitive protein", gene families involved in hormone signalling and developmental regulation, controlling flowering in other species. These results demonstrate how digital imaging combined with automated feature extraction can be leveraged to gain insight on buckwheat flowering patterns in large scale field trials across different phenotyping platforms. This paves the way to breed for desired flowering patterns using molecular tools in a targeted manner.