Wheat Yield and Protein Estimation with Handheld and Unmanned Aerial Vehicle-Mounted Sensors

Accurate sensor-based prediction of crop yield and grain quality in-season would enable growers to adjust nitrogen (N) fertilizer management for optimized production. This study assessed the feasibility (and compared the accuracy) of wheat (Triticum aestivum L.) yield, grain N uptake, and protein co...

Full description

Saved in:
Bibliographic Details
Published in:Agronomy (Basel) 2023-01, Vol.13 (1), p.207
Main Authors: Walsh, Olga S., Marshall, Juliet M., Nambi, Eva, Jackson, Chad A., Ansah, Emmanuella Owusu, Lamichhane, Ritika, McClintick-Chess, Jordan, Bautista, Francisco
Format: Article
Language:English
Subjects:
Accuracy
Agricultural production
Agriculture
Altitude
Cameras
Crop yield
Feasibility studies
Fertilizers
Grain
grain protein
grain yield
handheld sensor
Nitrogen
Normalized difference vegetative index
Nutrient content
Predictions
Proteins
Remote sensing systems
Seasons
Sensors
Spectral reflectance
Triticum aestivum
unmanned aerial vehicle
Unmanned aerial vehicles
Vegetation
Wheat
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Accurate sensor-based prediction of crop yield and grain quality in-season would enable growers to adjust nitrogen (N) fertilizer management for optimized production. This study assessed the feasibility (and compared the accuracy) of wheat (Triticum aestivum L.) yield, grain N uptake, and protein content prediction with in-season crop spectral reflectance measurements (Normalized Difference Vegetative Index, NDVI) obtained with a handheld GreenSeeker (GS) sensor and an Unmanned Aerial Vehicle (UAV)-mounted sensor. A strong positive correlation was observed between GS NDVI and UAV NDVI at Feekes 5 (R2 = 0.78) and Feekes 10 (R2 = 0.70). At Feekes 5, GS NDVI and UAV NDVI explained 42% and 43% of wheat yield, respectively. The correlation was weaker at Feekes 10 (R2 of 0.34 and 0.25 for GS NDVI and UAV NDVI, respectively). The accuracy of wheat grain N uptake prediction was comparable to that of yield: the R2 values for GS NDVI and UAV NDVI were 0.53 and 0.37 at Feekes 5 and 0.13 and 0.20 at Feekes 10. We found that neither GS NDVI nor UAV NDVI in-season data were useful in prediction of wheat grain protein content. In conclusion, wheat yield and grain N uptake can be estimated at Feekes 5 using either handheld or aerial based NDVI with comparable accuracy.
ISSN:2073-4395
2073-4395
DOI:10.3390/agronomy13010207