Abstract
Yield evaluation of breeding lines is the key to successful release of cultivars, which is becoming a serious issue due to soil heterogeneity in enlarged field tests. This study aimed at establishing plot-yield prediction models using unmanned aerial vehicle (UAV)-based hyperspectral remote sensing for yield-selection in large-scale soybean breeding programs. Three sets of soybean breeding lines (1103 in total) were tested in blocks-in-replication experiments for plot yield and canopy spectral reflectance on 454~950 nm bands at different growth stages using a UAV-based hyperspectral spectrometer (Cubert UHD185 Firefly). The four elements for plot-yield prediction model construction were studied respectively and concluded as: the suitable reflectance-sampling unit-size in a plot was its 20%–80% central part; normalized difference vegetation index (NDVI) and ration vegetation index (RVI) were the best combination of vegetation indices; the initial seed-filling stage (R5) was the best for a single stage prediction, while another was the best combination for a two growth-stage prediction; and multi-variate linear regression was suitable for plot-yield prediction. In model establishment for each material-set, a random half was used for modelling and another half for verification. Twenty-one two growth-stage two vegetation-index prediction models were established and compared for their modelling coefficient of determination (RM2) and root mean square error of the model (RMSEM), verification RV2 and RMSEV, and their sum RS2 and RMSES. Integrated with the coincidence rate between the model predicted and the practical yield-selection results, the models, MA1-2, MA4-2 and MA6-2, with coincidence rates of 56.8%, 58.5% and 52.4%, respectively, were chosen for yield-prediction in yield-test nurseries. The established model construction elements and methods can be used as local models for pre-harvest yield-selection and post-harvest integrated yield-selection in advanced breeding nurseries as well as yield potential prediction in plant-derived-line nurseries. Furthermore, multiple models can be used jointly for plot-yield prediction in soybean breeding programs.
Abstract from the paper’s OpenAlex record; open copy licensed cc-by. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 9
Claim · model-written summary
Sampling the central 20%–80% of a plot was suitable for reflectance measurement.
- Taxon
- Soybean
Glycine maxt0 - Outcome
- suitable reflectance-sampling unit-sizee0
- Value
- 20%–80%e0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“the suitable reflectance-sampling unit-size in a plot was its 20%–80% central part”
t0“Soybean”
Claim · model-written summary
NDVI and RVI were the best combination of indices for yield prediction.
- Taxon
- SoybeanGlycine maxt0
- Outcome
- best combination of vegetation indicese0
- Comparator
- vegetation indicese0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“normalized difference vegetation index (NDVI) and ration vegetation index (RVI) were the best combination of vegetation indices”
t0“Soybean”
Claim · model-written summary
The initial seed-filling stage R5 was best for single-stage prediction.
- Taxon
- SoybeanGlycine maxt0
- Organ / stage
- initial seed-filling stagee0
- Outcome
- best for a single stage predictione0
- Value
- R5e0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“the initial seed-filling stage (R5) was the best for a single stage prediction”
t0“Soybean”
Claim · model-written summary
Multivariate linear regression was suitable for plot yield prediction.
- Taxon
- SoybeanGlycine maxt0
- Outcome
- suitable for plot-yield predictione0
- Comparator
- multi-variate linear regressione0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“multi-variate linear regression was suitable for plot-yield prediction”
t0“Soybean”
Claim · model-written summary
Model MA1-2 had 56.8% coincidence with practical yield selection.
- Taxon
- SoybeanGlycine maxt0
- Material
- MA1-2e0
- Outcome
- coincidence ratese0
- Value
- 56.8%e0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“models, MA1-2, MA4-2 and MA6-2, with coincidence rates of 56.8%, 58.5% and 52.4%, respectively”
t0“Soybean”
Claim · model-written summary
Model MA4-2 had 58.5% coincidence with practical yield selection.
- Taxon
- SoybeanGlycine maxt0
- Material
- MA4-2e0
- Outcome
- coincidence ratese0
- Value
- 58.5%e0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“models, MA1-2, MA4-2 and MA6-2, with coincidence rates of 56.8%, 58.5% and 52.4%, respectively”
t0“Soybean”
Claim · model-written summary
Model MA6-2 had 52.4% coincidence with practical yield selection.
- Taxon
- SoybeanGlycine maxt0
- Material
- MA6-2e0
- Outcome
- coincidence ratese0
- Value
- 52.4%e0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“models, MA1-2, MA4-2 and MA6-2, with coincidence rates of 56.8%, 58.5% and 52.4%, respectively”
t0“Soybean”
Claim · model-written summary
The authors propose the model methods for yield selection in breeding nurseries.
- Taxon
- SoybeanGlycine maxt0
- Outcome
- can be used as local models for pre-harvest yield-selection and post-harvest integrated yield-selectione0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“The established model construction elements and methods can be used as local models for pre-harvest yield-selection and post-harvest integrated yield-selection in advanced breeding nurseries as well as yield potential prediction in plant-derived-line nurseries”
t0“Soybean”
Claim · model-written summary
The authors propose using multiple models jointly for soybean plot yield prediction.
- Taxon
- soybeanGlycine maxe0
- Outcome
- multiple models can be used jointly for plot-yield predictione0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“multiple models can be used jointly for plot-yield prediction in soybean breeding programs”