Abstract
Soybean maturity is a trait of critical importance for the development of new soybean cultivars, nevertheless, its characterization based on visual ratings has many challenges. Unmanned aerial vehicles (UAVs) imagery-based high-throughput phenotyping methodologies have been proposed as an alternative to the traditional visual ratings of pod senescence. However, the lack of scalable and accurate methods to extract the desired information from the images remains a significant bottleneck in breeding programs. The objective of this study was to develop an image-based high-throughput phenotyping system for evaluating soybean maturity in breeding programs. Images were acquired twice a week, starting when the earlier lines began maturation until the latest ones were mature. Two complementary convolutional neural networks (CNN) were developed to predict the maturity date. The first using a single date and the second using the five best image dates identified by the first model. The proposed CNN architecture was validated using more than 15,000 ground truth observations from five trials, including data from three growing seasons and two countries. The trained model showed good generalization capability with a root mean squared error lower than two days in four out of five trials. Four methods of estimating prediction uncertainty showed potential at identifying different sources of errors in the maturity date predictions. The architecture developed solves limitations of previous research and can be used at scale in commercial breeding programs.
Highlights
As the most important source of plant protein in the world, soybean (Glycine max L.) is widely grown and heavily traded and plays a significant role in global food security [1]
The value of the ground truth difference (GTDiff) was set to −6, meaning that from all the available image dates, the one that predicted maturity would occur about 6 days after the acquisition was used as the center image
The relatively low importance of image resolution, which is an indicator of the importance of using convolutional neural networks (CNN) as feature extractors, shows that this was not the main reason to explain the good performance of the model
Summary
As the most important source of plant protein in the world, soybean (Glycine max L.) is widely grown and heavily traded and plays a significant role in global food security [1]. In this context, crop breeding aims to increase the grain yield potential and improve the adaptation of new cultivars to environmental changes. Improving traits of interest, such as grain yield, depends on the ability to accurately assess the phenotype of a large number of experimental lines developed annually from breeding populations [2,3]. Maturity is especially important because besides defining the crop cycle length, many management decisions are associated with it. This information is used to take into account the effects that earlier maturing lines may have on the neighboring plots [6]
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.
