Temporal covariance structure of multi-spectral phenotypes and their predictive ability for end-of-season traits in maize

Anche, Mahlet T.; Kaczmar, Nicholas; Morales, Nicolás; Clohessy, James W.; Ilut, Daniel C.; Gore, Michael A.; Robbins, Kelly R.

doi:10.1007/s00122-020-03637-6

Cited by 16 publications

(17 citation statements)

References 37 publications

(49 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, a study using 33 different VIs reported that NDVI, NDRE and GNDVI had the strongest correlation with maize yield [49]. Other studies also demonstrate NDVI correlation with grain yield and moisture, suggesting its use as a secondary trait for plant selection during trials [58,66,67]. For wheat, NDVI provided spatial separation between the high-and low-yielding regions within a plot during the anthesis, tillering, and seedling stages [68].…”

Section: Discussionmentioning

confidence: 99%

Maize Yield Prediction at an Early Developmental Stage Using Multispectral Images and Genotype Data for Preliminary Hybrid Selection

et al. 2021

View full text Add to dashboard Cite

Assessing crop production in the field often requires breeders to wait until the end of the season to collect yield-related measurements, limiting the pace of the breeding cycle. Early prediction of crop performance can reduce this constraint by allowing breeders more time to focus on the highest-performing varieties. Here, we present a multimodal deep learning model for predicting the performance of maize (Zea mays) at an early developmental stage, offering the potential to accelerate crop breeding. We employed multispectral images and eight vegetation indices, collected by an uncrewed aerial vehicle approximately 60 days after sowing, over three consecutive growing cycles (2017, 2018 and 2019). The multimodal deep learning approach was used to integrate field management and genotype information with the multispectral data, providing context to the conditions that the plants experienced during the trial. Model performance was assessed using holdout data, in which the model accurately predicted the yield (RMSE 1.07 t/ha, a relative RMSE of 7.60% of 16 t/ha, and R2 score 0.73) and identified the majority of high-yielding varieties, outperforming previously published models for early yield prediction. The inclusion of vegetation indices was important for model performance, with a normalized difference vegetation index and green with normalized difference vegetation index contributing the most to model performance. The model provides a decision support tool, identifying promising lines early in the field trial.

show abstract

Section: Discussionmentioning

confidence: 99%

Maize Yield Prediction at an Early Developmental Stage Using Multispectral Images and Genotype Data for Preliminary Hybrid Selection

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The time‐dependent structure of a covariance matrix is included in the model by explaining growth curves with base expansions using arbitrary functions (Kirkpatrick & Heckman, 1989). Several reports have shown that random regression was an effective method when applied to longitudinal remote sensing data (Anche et al., 2020; Sun et al., 2017) or growth data measured by a high‐throughput phenotyping platform (Campbell et al., 2018). Random regression can be understood as a dimension reduction of growth curves using functions such as Legendre polynomials or spline functions.…”

Section: Discussionmentioning

confidence: 99%

Genomic prediction modeling of soybean biomass using UAV‐based remote sensing and longitudinal model parameters

et al. 2021

View full text Add to dashboard Cite

The application of remote sensing in plant breeding can provide rich information about the growth processes of plants, which leads to better understanding concerning crop yield. It has been shown that traits measured by remote sensing were also beneficial for genomic prediction (GP) because the inclusion of remote sensing data in multitrait models improved prediction accuracies of target traits. However, the present multitrait GP model cannot incorporate high‐dimensional remote sensing data due to the difficulty in the estimation of a covariance matrix among the traits, which leads to failure in improving its prediction accuracy. In this study, we focused on growth models to express growth patterns using remote sensing data with a few parameters and investigated whether a multitrait GP model using these parameters could derive better prediction accuracy of soybean [Glycine max (L.) Merr.] biomass. A total of 198 genotypes of soybean germplasm were cultivated in experimental fields, and longitudinal changes of their canopy height and area were measured continuously via remote sensing with an unmanned aerial vehicle. Growth parameters were estimated by applying simple growth models and incorporated into the GP of biomass. By evaluating heritability and correlation, we showed that the estimated growth parameters appropriately represented the observed growth curves. Also, the use of these growth parameters in the multitrait GP model contributed to successful biomass prediction. We conclude that the growth models could describe the genetic variation of soybean growth curves based on several growth parameters. These dimension‐reduction growth models will be indispensable for extracting useful information from remote sensing data and using this data in GP and plant breeding.

show abstract

“…These high resolution NDVI, NDRE, BNDVI, GNDVI, OSAVI, and TGI images are suitable for the ground-based analysis of green biomass, vegetative coverage, chlorophyll content, vegetation water content, and vegetation growth in grassland. VIs derived from multi-spectral imaging (MSI) tools can be used to provide nondestructive phenotypes that could be used to better understand growth curves throughout the growing season [45,46]. This study used the ASQ-Discover to collect the multispectral images of each quadrat and generate vegetation index images in which each pixel value is a vegetation index (NDVI, NDRE, BNDVI, GNDVI, OSAVI, TGI).…”

Section: A Set Of Spectral Traits Of Vegetation 231 Selecting Vegetation Indicesmentioning

confidence: 99%

A Handheld Grassland Vegetation Monitoring System Based on Multispectral Imaging

Zhang

et al. 2021

Agriculture

View full text Add to dashboard Cite

Monitoring grassland vegetation growth is of vital importance to scientific grazing and grassland management. People expect to be able to use a portable device, like a mobile phone, to monitor grassland vegetation growth at any time. In this paper, we propose a handheld grassland vegetation monitoring system to achieve the goal of monitoring grassland vegetation growth. The system includes two parts: the hardware unit is a hand-held multispectral imaging tool named ASQ-Discover based on a smartphone, which has six bands (wavelengths)—including three visible bands (450 nm, 550 nm, 650 nm), a red-edge band (750 nm), and two near-infrared bands (850 nm, 960 nm). The imagery data of each band has a size of 5120 × 3840 pixels with 8-bit depth. The software unit improves image quality through vignetting removal, radiometric calibration, and misalignment correction and estimates and analyzes spectral traits of grassland vegetation (Fresh Grass Ratio (FGR), NDVI, NDRE, BNDVI, GNDVI, OSAVI and TGI) that are indicators of vegetation growth in grassland. We introduce the hardware and software unit in detail, and we also experiment in five pastures located in Haiyan County, Qinghai Province. Our experimental results show that the handheld grassland vegetation growth monitoring system has the potential to revolutionize the grassland monitoring that operators can conduct when using a hand-held tool to achieve the tasks of grassland vegetation growth monitoring.

show abstract

Temporal covariance structure of multi-spectral phenotypes and their predictive ability for end-of-season traits in maize

Cited by 16 publications

References 37 publications

Maize Yield Prediction at an Early Developmental Stage Using Multispectral Images and Genotype Data for Preliminary Hybrid Selection

Maize Yield Prediction at an Early Developmental Stage Using Multispectral Images and Genotype Data for Preliminary Hybrid Selection

Genomic prediction modeling of soybean biomass using UAV‐based remote sensing and longitudinal model parameters

A Handheld Grassland Vegetation Monitoring System Based on Multispectral Imaging

Contact Info

Product

Resources

About