Forage biomass estimation using UAV-based remote sensing and machine learning: A tool for assessing management practices

Authors: ZHAO, BIQUAN - University Of Nebraska; HILLER, JEREMY - University Of Nebraska; AWADA, TALA - University Of Nebraska; WARDLOW, BRIAN - University Of Nebraska; ERICKSON, GALEN - University Of Nebraska; SHI, YEYIN - University Of Nebraska

Submitted to: Ecological Informatics
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 7/27/2025
Publication Date: 7/28/2025
Citation: Zhao, B., Hiller, J., Awada, T., Wardlow, B., Erickson, G., Shi, Y. 2025. Forage biomass estimation using UAV-based remote sensing and machine learning: A tool for assessing management practices. Ecological Informatics. 90(2025). Article 103361. https://doi.org/10.1016/j.ecoinf.2025.103361.
DOI: https://doi.org/10.1016/j.ecoinf.2025.103361

Interpretive Summary: Unmanned aerial vehicles (UAVs), or drones, are being used increasingly to evaluate crop and pasture productivity. This study demonstrated the practical use of UAVs to assess pasture management. Estimated forage dry matter from UAV imagery reflected 76% of measured data over two years with treatments. Significant differences in forage dry matter were found among fertilizer treatments. To improve the accuracy of UAV-measured pasture productivity, we propose an enhanced ground sampling strategy to help capture landscape variations that affect pasture growth.

Technical Abstract: Forage biomass exhibits temporal and spatial variability driven by microenvironmental conditions and diverse management practices in pastures. Common forage sampling strategies, such as random or transect-based sampling, often overlook this variability, potentially resulting in unrepresentative samples and inaccurate estimates. This study investigated the potential of a forage biomass estimation tool based on unmanned aerial vehicles (UAV) remote sensing for assessing spatial and temporal effects of various pasture management practices. Using UAV-derived forage dry matter (DM) maps collected over two years from for managed Bromus inermis dominated pastures in eastern Nebraska, we evaluated the impacts of grazing and fertilization management practices on biomass. Forage DM model was developed using vegetation indices derived from UAV multispectral data, cumulative precipitation and growing degree days, ground-sampled biomass data, and Random Forest machine learning (ML) algorithm. Result showed that total DM was estimated with R2 of 0.76 and RMSE of 1068 kg'ha-1 (rRMSE = 33.1 %). Significant DM differences were observed for three management treatments—control, feed supplement with Dry Distillers Grains Solubles (DDGS), and pasture nitrogen fertilization—with and without grazing across 2021 and 2022 growing seasons using the UAV estimated DMs (p < 0.001). In addition, we also suggest conducting the UAV flight and data processing prior to ground sampling to guide the sampling locations, if both ground biomass samples and UAV remote sensing data are intended to be collected, to better capture spatial variability across the pasture.