Abstract
The utility of unmanned aerial vehicles (UAV) imagery in retrieving phenotypic data to support plant breeding research has been a topic of increasing interest in recent years. The advantages of image-based phenotyping are related to the high spatial and temporal resolution of the retrieved data and the non-destructive and rapid method of data acquisition. This study trains parametric and nonparametric regression models to retrieve leaf area index (LAI), fraction of absorbed photosynthetically active radiation (fAPAR), fractional vegetation cover (fCover), leaf chlorophyll content (LCC), canopy chlorophyll content (CCC), and grain yield (GY) of winter durum wheat breeding experiment from four-bands UAV images. A ground dataset, collected during two field campaigns and complemented with data from a previous study, is used for model development. The dataset is split at random into two parts, one for training and one for testing the models. The tested parametric models use the vegetation index formula and parametric functions. The tested nonparametric models are partial least square regression (PLSR), random forest regression (RFR), support vector regression (SVR), kernel ridge regression (KRR), and Gaussian processes regression (GPR). The retrieved biophysical variables along with traditional phenotypic traits (plant height, yield, and tillering) are analysed for detection of genetic diversity, proximity, and similarity in the studied genotypes. Analysis of variance (ANOVA), Duncan’s multiple range test, correlation analysis, and principal component analysis (PCA) are performed with the phenotypic traits. The parametric and nonparametric models show close results for GY retrieval, with parametric models indicating slightly higher accuracy (R2 = 0.49; RMSE = 0.58 kg/plot; rRMSE = 6.1%). However, the nonparametric model, GPR, computes per pixel uncertainty estimation, making it more appealing for operational use. Furthermore, our results demonstrate that grain filling was better than flowering phenological stage to predict GY. The nonparametric models show better results for biophysical variables retrieval, with GPR presenting the highest prediction performance. Nonetheless, robust models are found only for LAI (R2 = 0.48; RMSE = 0.64; rRMSE = 13.5%) and LCC (R2 = 0.49; RMSE = 31.57 mg m−2; rRMSE = 6.4%) and therefore these are the only remotely sensed phenotypic traits included in the statistical analysis for preliminary assessment of wheat productivity. The results from ANOVA and PCA illustrate that the retrieved remotely sensed phenotypic traits are a valuable addition to the traditional phenotypic traits for plant breeding studies. We believe that these preliminary results could speed up crop improvement programs; however, stronger interdisciplinary research is still needed, as well as uncertainty estimation of the remotely sensed phenotypic traits.
Highlights
Yield is a major quantitative trait formed in a complex manner by all other traits related to productivity
Among the retrieved biophysical variables with Gaussian processes regression (GPR) models, only leaf area index (LAI) and leaf chlorophyll content (LCC) demonstrate average to high agreement with observations when validated to test dataset—R2 = 0.48, relative RMSE (rRMSE) = 13.51% and R2 = 0.62, rRMSE = 6.42%, respectively
We will consider them as remotely sensed phenotypic traits, even if LAI and LCC tend to saturate for high values (Figure 5)
Summary
Yield is a major quantitative trait formed in a complex manner by all other traits related to productivity. It is a leading feature in breeding programs and its improvement is a major task that requires high-throughput phenotyping platforms. From the point of view of plant breeding, yield per unit area is of considerable importance [1,2] and the primary goal is to expand genetic diversity and develop new cultivars that perform better than those grown in the target population of environments. Durum) parents to derive superior progeny from crossing and selection [1]. To meet this goal, high-throughput fieldphenotyping tools are needed [3]. Whilst challenging to manage, such large datasets offer opportunities for applying new modelling techniques, such as machine learning [7] and increasing selection intensity, improving selection accuracy, and improving the decision support system
Sign-in/Register to view highlights & summary 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.
