Evaluating UAV-based remote sensing for hay yield estimation

Authors: LEE, KYUHO - University Of Missouri; Sudduth, Kenneth - Ken; ZHOU, JIANFENG - University Of Missouri

Submitted to: Sensors
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 8/14/2024
Publication Date: 8/17/2024
Citation: Lee, K., Sudduth, K.A., Zhou, J. 2024. Evaluating UAV-based remote sensing for hay yield estimation. Sensors. 24(16). Article 5326. https://doi.org/10.3390/s24165326
DOI: https://doi.org/10.3390/s24165326

Interpretive Summary: Yield monitoring systems are widely used commercially in grain crops to map yields at a scale of a few meters. However, such high-resolution yield monitoring and mapping for hay and forage crops is not yet available to farmers, as commercial hay yield monitoring systems only obtain the weight of individual bales. This makes it difficult to map and understand the spatial variability in hay yield, as needed by farmers interested in applying precision agriculture principles to hay production. This study investigated the feasibility of using remote sensing from an Uncrewed Aerial Vehicle (UAV) for estimation of hay yield at a higher resolution. Images were obtained from plots and a field containing a mixture of red clover and timothy hay, and several image variables were extracted. Models relating the image data to hay yield represented from 30 to 70% of the hay yield variability. Problems with image clarity and resolution were found to affect accuracy and will need to be addressed in future research. If these can be overcome, UAV-based yield estimation may provide accurate, high-resolution hay yield maps that can advance precision agriculture management for this important crop.

Technical Abstract: Yield monitoring systems are widely used in grain crops but are less advanced for hay and forage. Current commercial systems are generally limited to weighing individual bales, limiting the spatial resolution of hay yield variability mapping. This study evaluated an Uncrewed Aerial Vehicle (UAV)-based imaging system to estimate hay yield at a higher resolution. Data were collected from three 0.4-ha plots and a 35-ha hay field of red clover and timothy grass in September 2020. A multispectral camera on the UAV captured images at 30 m (20 mm/pixel) and 50 m (35 mm/pixel) heights. Eleven Vegetation Indices (VIs) and five texture features were calculated from the images to estimate biomass yield. Multivariate regression models (VIs & texture features vs. biomass) were evaluated. Model R2 values ranged from 0.31 to 0.68. Despite strong correlations between standard VIs and biomass, challenges such as variable image resolution and clarity affected accuracy. Further research is needed before UAV-based yield estimation can provide accurate, high-resolution hay yield maps.