Abstract
Recent substantial advances in high-throughput field phenotyping have provided plant breeders with affordable and efficient tools for evaluating a large number of genotypes for important agronomic traits at early growth stages. Nevertheless, the implementation of large datasets generated by high-throughput phenotyping tools such as hyperspectral reflectance in cultivar development programs is still challenging due to the essential need for intensive knowledge in computational and statistical analyses. In this study, the robustness of three common machine learning (ML) algorithms, multilayer perceptron (MLP), support vector machine (SVM), and random forest (RF), were evaluated for predicting soybean (Glycine max) seed yield using hyperspectral reflectance. For this aim, the hyperspectral reflectance data for the whole spectra ranged from 395 to 1005 nm, which were collected at the R4 and R5 growth stages on 250 soybean genotypes grown in four environments. The recursive feature elimination (RFE) approach was performed to reduce the dimensionality of the hyperspectral reflectance data and select variables with the largest importance values. The results indicated that R5 is more informative stage for measuring hyperspectral reflectance to predict seed yields. The 395 nm reflectance band was also identified as the high ranked band in predicting the soybean seed yield. By considering either full or selected variables as the input variables, the ML algorithms were evaluated individually and combined-version using the ensemble–stacking (E–S) method to predict the soybean yield. The RF algorithm had the highest performance with a value of 84% yield classification accuracy among all the individual tested algorithms. Therefore, by selecting RF as the metaClassifier for E–S method, the prediction accuracy increased to 0.93, using all variables, and 0.87, using selected variables showing the success of using E–S as one of the ensemble techniques. This study demonstrated that soybean breeders could implement E–S algorithm using either the full or selected spectra reflectance to select the high-yielding soybean genotypes, among a large number of genotypes, at early growth stages.
Highlights
The world population is projected to exceed nine billion individuals by 2050, which will require significant improvements in the yield of major crops that contribute to global food security (Tilman et al, 2009; Foley et al, 2011; Alexandratos and Bruinsma, 2012; Dubey et al, 2019)
Breeding approaches that are established based on secondary traits, which are strongly correlated with the primary trait, enable plant breeders to efficiently recognize promising lines at early growth stages (Ma et al, 2001; Jin et al, 2010; MontesinosLópez et al, 2017)
Out of 62 reflectance bands, 21 reflectance bands were selected to train the algorithms based on recursive feature elimination (RFE) strategy, which were considered selected variables (-VS) for further analyses
Summary
The world population is projected to exceed nine billion individuals by 2050, which will require significant improvements in the yield of major crops that contribute to global food security (Tilman et al, 2009; Foley et al, 2011; Alexandratos and Bruinsma, 2012; Dubey et al, 2019). In the area of plant breeding, measuring primary traits, such as yield, which is under influenced by a combination of quantitative and qualitative traits, in large breeding populations consisting of several thousand genotypes is time and labor-consuming (Araus and Cairns, 2014; Cai et al, 2016; Xiong et al, 2018). Breeding approaches that are established based on secondary traits (e.g., yield component traits and reflectance bands), which are strongly correlated with the primary trait, enable plant breeders to efficiently recognize promising lines at early growth stages (Ma et al, 2001; Jin et al, 2010; MontesinosLópez et al, 2017). The combination of high-throughput genotyping and phenotyping technologies have enabled plant breeders to make their early growth stage selections more accurate while it reduced the evaluation time and cost in their breeding programs (Rutkoski et al, 2016). There has been significant progress in high-throughput genotyping in recent years with a direct impact on current plant breeding challenges (Araus and Cairns, 2014; Tardieu et al, 2017; Araus et al, 2018), acquisition of high-throughput field phenotyping is still a bottleneck in most breeding programs (Furbank and Tester, 2011; Araus et al, 2018)
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.
