Ebersbach, JanaKhan, Nazifa AzamMcQuillan, IanHiggins, ErinHorner, KylaBandi, VenkatGutwin, CarlVail, Sally LynneRobinson, Steve J.Parkin, Isobel2023-09-092023-09-092022Ebersbach J, Khan NA, McQuillan I, Higgins EE, Horner K, Bandi V, Gutwin C, Vail SL, Robinson SJ and Parkin IAP (2022) Exploiting High-Throughput Indoor Phenotyping to Characterize the Founders of a Structured B. napus Breeding Population. Front. Plant Sci. 12:780250. doi: 10.3389/fpls.2021.780250https://hdl.handle.net/10388/14963All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.Phenotyping is considered a significant bottleneck impeding fast and efficient crop improvement. Similar to many crops, Brassica napus, an internationally important oilseed crop, suffers from low genetic diversity, and will require exploitation of diverse genetic resources to develop locally adapted, high yielding and stress resistant cultivars. A pilot study was completed to assess the feasibility of using indoor high-throughput phenotyping (HTP), semi-automated image processing, and machine learning to capture the phenotypic diversity of agronomically important traits in a diverse B. napus breeding population, SKBnNAM, introduced here for the first time. The experiment comprised 50 spring-type B. napus lines, grown and phenotyped in six replicates under two treatment conditions (control and drought) over 38 days in a LemnaTec Scanalyzer 3D facility. Growth traits including plant height, width, projected leaf area, and estimated biovolume were extracted and derived through processing of RGB and NIR images. Anthesis was automatically and accurately scored (97% accuracy) and the number of flowers per plant and day was approximated alongside relevant canopy traits (width, angle). Further, supervised machine learning was used to predict the total number of raceme branches from flower attributes with 91% accuracy (linear regression and Huber regression algorithms) and to identify mild drought stress, a complex trait which typically has to be empirically scored (0.85 area under the receiver operating characteristic curve, random forest classifier algorithm). The study demonstrates the potential of HTP, image processing and computer vision for effective characterization of agronomic trait diversity in B. napus, although limitations of the platform did create significant variation that limited the utility of the data. However, the results underscore the value of machine learning for phenotyping studies, particularly for complex traits such as drought stress resistance.enAttribution 2.5 CanadaB. napusspring-typeNAMsemi-automated image analysismachine learningdrought resistanceArticle10.3389/fpls.2021.780250