Validation of UAV-based alfalfa biomass predictability using photogrammetry with fully automatic plot segmentation

Abstract

Alfalfa is the most widely cultivated forage legume, with approximately 30 million hectares planted worldwide. Genetic improvements in alfalfa have been highly successful in developing cultivars with exceptional winter hardiness and disease resistance traits. However, genetic improvements have been limited for complex economically important traits such as biomass. One of the major bottlenecks is the labor-intensive phenotyping burden for biomass selection. In this study, we employed two alfalfa fields to pave a path to overcome the challenge by using UAV images with fully automatic field plot segmentation for high-throughput phenotyping. The first field was used to develop the prediction model and the second field to validate the predictions. The first and second fields had 808 and 1025 plots, respectively. The first field had three harvests with biomass measured in May, July, and September of 2019. The second had one harvest with biomass measured in September of 2019. These two fields were imaged one day before harvesting with a DJI Phantom 4 pro UAV carrying an additional Sentera multispectral camera. Alfalfa plot images were extracted by GRID software to quantify vegetative area based on the Normalized Difference Vegetation Index. The prediction model developed from the first field explained 50–70% (R Square) of biomass variation in the second field by incorporating four features from UAV images: vegetative area, plant height, Normalized Green–Red Difference Index, and Normalized Difference Red Edge Index. This result suggests that UAV-based, high-throughput phenotyping could be used to improve the efficiency of the biomass selection process in alfalfa breeding programs.

Phenomics-Assisted Selection for Herbage Accumulation in Alfalfa (Medicago sativa L.)

“…All VIs provided a high correlation with HA, and HA in alfalfa was modeled with moderate accuracy ( R 2 > 0.66 in four harvests). These results follow similar trends from the previous studies evaluating the efficiency of HTP in predicting HA in small plots from alfalfa germplasm and breeding lines ( Cazenave et al, 2019 ; Tang et al, 2021 ), as well as larger alfalfa plots ( Feng et al, 2020 ).…”

“…One of the strategies to improve selection intensity is by increasing the breeding populations’ size, but this comes at the expense of more efforts and resources dedicated to phenotyping. HTP can lead to higher genetic gain by increasing the size of breeding populations and making selections more accurately ( Houle et al, 2010 ; Tang et al, 2021 ). In our study, H 2 estimates were slightly lower for NDVI than HA, but both traits showed significant genetic variation and moderate to low H 2 .…”

“…Nevertheless, HA has become a target breeding trait among alfalfa breeders more recently ( Sakiroglu and Brummer, 2017 ; Dos Santos et al, 2018 ; Adhikari et al, 2019 ; Acharya et al, 2020 ; Benabderrahim et al, 2020 ; He et al, 2020 ; Ren et al, 2021 ; Tang et al, 2021 ). However, traditional field phenotyping for HA is based on the destructive sampling of experimental units at the ground level, weighing fresh samples, drying, and weighing dried samples to estimate dry matter content.…”

“…According to Cazenave et al (2019) , HTP can detect small differences in alfalfa yield when screening diverse germplasm. More recently, HTP improved the efficiency of the selection process for biomass in small plots (1.52 m × 0.30 m) in alfalfa breeding populations ( Tang et al, 2021 ), and provided a good prediction of HA in larger plots (6 m × 4 m) ( Feng et al, 2020 ). Remote sensing can mitigate the challenge of measuring HA in large populations for breeding programs focusing on improving alfalfa HA.…”

Integrating Drone Technology into an Innovative Agrometeorological Methodology for the Precise and Real-Time Estimation of Crop Water Requirements

“…A polygon mesh was calculated from the dense 3D point, and the pixel values of each image were then projected onto the mesh to create an orthomosaic. When combined with the GPS locations, this procedure allowed for the establishment of a high-resolution orthophoto and a digital elevation model (DEM) of the crop field [33,65].…”