Development and Validation of a Model to Combine NDVI and Plant Height for High-Throughput Phenotyping of Herbage Yield in a Perennial Ryegrass Breeding Program

Gebremedhin, Alem; Badenhorst, Pieter; Wang, Junping; Giri, Khageswor; Spangenberg, Germán; Smith, K. F.

doi:10.3390/rs11212494

Cited by 25 publications

(41 citation statements)

References 56 publications

(111 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As for the image itself, the major limitation of a UAV image data collection is the low capacity to compensate and analyze larger areas. However, this type of aerial remote sensing is important when considering the spatial resolution and highly detailed information obtained on the vegetation cover, permitting an analysis at a plant or crop-plot level [68][69][70][71]. Additionally, by evaluating crop at an aerial view, it is easier to ascertain the relationship between spectral data and biophysical variables, since the end-user can reduce the amount of noise introduced in the system by extracting only pixels corresponding with the canopy itself.…”

Section: Discussionmentioning

confidence: 99%

Leaf Nitrogen Concentration and Plant Height Prediction for Maize Using UAV-Based Multispectral Imagery and Machine Learning Techniques

et al. 2020

View full text Add to dashboard Cite

Under ideal conditions of nitrogen (N), maize (Zea mays L.) can grow to its full potential, reaching maximum plant height (PH). As a rapid and nondestructive approach, the analysis of unmanned aerial vehicles (UAV)-based imagery may be of assistance to estimate N and height. The main objective of this study is to present an approach to predict leaf nitrogen concentration (LNC, g kg−1) and PH (m) with machine learning techniques and UAV-based multispectral imagery in maize plants. An experiment with 11 maize cultivars under two rates of N fertilization was carried during the 2017/2018 and 2018/2019 crop seasons. The spectral vegetation indices (VI) normalized difference vegetation index (NDVI), normalized difference red-edge index (NDRE), green normalized difference vegetation (GNDVI), and the soil adjusted vegetation index (SAVI) were extracted from the images and, in a computational system, used alongside the spectral bands as input parameters for different machine learning models. A randomized 10-fold cross-validation strategy, with a total of 100 replicates, was used to evaluate the performance of 9 supervised machine learning (ML) models using the Pearson’s correlation coefficient (r), mean absolute error (MAE), coefficient of regression (R²), and root mean square error (RMSE) metrics. The results indicated that the random forest (RF) algorithm performed better, with r and RMSE, respectively, of 0.91 and 1.9 g.kg−¹ for LNC, and 0.86 and 0.17 m for PH. It was also demonstrated that VIs contributed more to the algorithm’s performances than individual spectral bands. This study concludes that the RF model is appropriate to predict both agronomic variables in maize and may help farmers to monitor their plants based upon their LNC and PH diagnosis and use this knowledge to improve their production rates in the subsequent seasons.

show abstract

Section: Discussionmentioning

confidence: 99%

Leaf Nitrogen Concentration and Plant Height Prediction for Maize Using UAV-Based Multispectral Imagery and Machine Learning Techniques

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Firstly, 480 individual plants from three breeding lines were selected and manually harvested at 5 cm above ground level in each of the seasonal harvests. The manually harvested measurements were used to develop and validate dry matter yield (DMY) estimation model from the combinations of NDVI and plant height values from sensors (Gebremedhin et al, 2019a). The models developed from these individual plants were used to estimate biomass of the 48,000 plants for the winter2018, spring2018_1, and late-spring2018_2 seasonal harvests.…”

Section: Phenotypic Data Collectionmentioning

confidence: 99%

“…In the ground-based platform, "PhenoRover, " a Polaris ranger side-by-side vehicle was used for ryegrass morphometric data collection. Details of the PhenoRover platform and data processing method was discussed in our previous paper (Gebremedhin et al, 2019a). In brief, the vehicle has six ultrasonic sonars for plant height measurement attached to a welded steel bar at 0.6 m above-ground.…”

Section: Ground-based Plant Height Data Acquisition and Processingmentioning

confidence: 99%

“…The aboveground biomass was harvested manually at 5 cm height. Destructive biomass harvest of 480 space-plants was collected following the same procedure described previously (Gebremedhin et al, 2019a). In addition, mechanical cutting of all the GS field experiment plots was conducted to measure total fresh biomass weight (kg/plot) at the row or plot level.…”

Section: Destructive Biomass Measurementsmentioning

confidence: 99%

“…Therefore, development and validation of a phenotyping computational workflow of data acquisition, processing and analysis could be applied to implement automated biomass yield estimation in large-scale ryegrass breeding program. We have recently shown that normalized difference vegetative index (NDVI) and plant height correlated with perennial ryegrass biomass yield in four seasons (Gebremedhin et al, 2019a). The results showed combining NDVI and plant height to be a robust method to enable high-throughput phenotyping of biomass yield in a ryegrass breeding program.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Development and Validation of a Phenotyping Computational Workflow to Predict the Biomass Yield of a Large Perennial Ryegrass Breeding Field Trial

et al. 2020

Self Cite

View full text Add to dashboard Cite

Increasing dry matter yield (DMY) is the most important objective in perennial ryegrass breeding programs. Current yield assessment methods like cutting are time-consuming and destructive, non-destructive measures such as scoring yield on single plants by visual inspection may be subjective. These assessments involve multiple measurements and selection procedures across seasons and years to evaluate biomass yield repeatedly. This contributes to the slow process of new cultivar development and commercialisation. This study developed and validated a computational phenotyping workflow for image acquisition, processing and analysis of spaced planted ryegrass and investigated sensor-based DMY yield estimation of individual plants through normalized difference vegetative index (NDVI) and ultrasonic plant height data extraction. The DMY of 48,000 individual plants representing 50 advanced breeding lines and commercial cultivars was accurately estimated at multiple harvests across the growing season. NDVI, plant height and predicted DMY obtained from aerial and ground-based sensors illustrated the variation within and between cultivars across different seasons. Combining NDVI and plant height of individual plants was a robust method to enable highthroughput phenotyping of biomass yield in ryegrass breeding. Similarly, the plot-level model indicated good to high-coefficients of determination (R 2) between the predicted and measured DMY across three seasons with R 2 between 0.19 and 0.81 and root mean square errors (RMSE) values ranging from 0.09 to 0.21 kg/plot. The model was further validated using a combined regression of the three seasons harvests. This study further sets a foundation for the application of sensor technologies combined with genomic studies that lead to greater rates of genetic gain in perennial ryegrass biomass yield.

show abstract

Developing an integrated genomic selection approach beyond biomass for varietal protection and nutritive traits in perennial ryegrass (Lolium perenne L.)

et al. 2023

View full text Add to dashboard Cite

Key message Breeding target traits can be broadened to include nutritive value and plant breeder’s rights traits in perennial ryegrass by using in-field regression-based spectroscopy phenotyping and genomic selection. Abstract Perennial ryegrass breeding has focused on biomass yield, but expansion into a broader set of traits is needed to benefit livestock industries whilst also providing support for intellectual property protection of cultivars. Numerous breeding objectives can be targeted simultaneously with the development of sensor-based phenomics and genomic selection (GS). Of particular interest are nutritive value (NV), which has been difficult and expensive to measure using traditional phenotyping methods, resulting in limited genetic improvement to date, and traits required to obtain varietal protection, known as plant breeder’s rights (PBR) traits. In order to assess phenotyping requirements for NV improvement and potential for genetic improvement, in-field reflectance-based spectroscopy was assessed and GS evaluated in a single population for three key NV traits, captured across four timepoints. Using three prediction approaches, the possibility of targeting PBR traits using GS was evaluated for five traits recorded across three years of a breeding program. Prediction accuracy was generally low to moderate for NV traits and moderate to high for PBR traits, with heritability highly correlated with GS accuracy. NV did not show significant or consistent correlation between timepoints highlighting the need to incorporate seasonal NV into selection indexes and the value of being able to regularly monitor NV across seasons. This study has demonstrated the ability to implement GS for both NV and PBR traits in perennial ryegrass, facilitating the expansion of ryegrass breeding targets to agronomically relevant traits while ensuring necessary varietal protection is achieved.

show abstract

Development and Validation of a Model to Combine NDVI and Plant Height for High-Throughput Phenotyping of Herbage Yield in a Perennial Ryegrass Breeding Program

Cited by 25 publications

References 56 publications

Leaf Nitrogen Concentration and Plant Height Prediction for Maize Using UAV-Based Multispectral Imagery and Machine Learning Techniques

Leaf Nitrogen Concentration and Plant Height Prediction for Maize Using UAV-Based Multispectral Imagery and Machine Learning Techniques

Development and Validation of a Phenotyping Computational Workflow to Predict the Biomass Yield of a Large Perennial Ryegrass Breeding Field Trial

Developing an integrated genomic selection approach beyond biomass for varietal protection and nutritive traits in perennial ryegrass (Lolium perenne L.)

Contact Info

Product

Resources

About