One of the problems of optical remote sensing of crop above-ground biomass (AGB) is that vegetation indices (VIs) often saturate from the middle to late growth stages. This study focuses on combining VIs acquired by a consumer-grade multiple-spectral UAV and machine learning regression techniques to (i) determine the optimal time window for AGB estimation of winter wheat and to (ii) determine the optimal combination of multi-spectral VIs and regression algorithms. Monitoring AGB prior to flowering was found to be more effective than post-flowering. Moreover, this study demonstrates that it is feasible to estimate AGB for multiple growth stages of winter wheat by combining the optimal VIs and PLSR and RF models, which overcomes the saturation problem of using individual VI-based linear regression models.
Nitrogen (N) remobilization is a critical process that provides substantial N to winter wheat grains for improving yield productivity. However, our understanding on the N remobilization efficiency (NRE) is still limited due to the lack of efficient, repeatable approaches for evaluating the NRE. In this study, we provided a proof of concept for estimating N concentration and assessing N remobilization using hyperspectral data of individual organs, which offers a non-chemical and low-cost approach to screen germplasms for an optimal NRE in drought-resistance breeding.
Predicting micronutrients in wheat kernel and flour using hyperspectral imaging. The prediction of micronutrients was superior based on the kernel spectra compared to the use of flour spectra. The Ca, Mg, Mo and Zn nutrients in wheat kernel/flour were predicted with a high credibility.
The QTL *qhir8* affecting in vivo haploid induction in maize was mapped to a 789 kb region, embryo abortion rate and segregation ratios were analyzed, linkage markers for MAS were developed.