Current endeavors to enhance the accuracy of in situ above-ground biomass (AGB) prediction for croplands rely on close-range monitoring surveys that use unstaffed aerial vehicles (UAVs) and mounted sensors. In precision agriculture, light detection and ranging (LiDAR) technologies are currently used to monitor crop growth, plant phenotyping, and biomass dynamics at the ecosystem scale. In this study, we utilized a UAV–LiDAR sensor to monitor two crop fields and a set of machine learning (ML) methods to predict real-time AGB over two consecutive years in the region of Mid-Jutland, Denmark. During each crop growing period, UAV surveys were conducted in parallel with AGB destructive sampling every 7–15 days, the AGB samples from which were used as the ground truth data. We evaluated the ability of the ML models to estimate the real-time values of AGB at a sub-meter resolution (0.17–0.52 m2). An extremely randomized trees (ERT) regressor was selected for the regression analysis, based on its predictive performance for the first year’s growing season. The model was retrained using previously identified hyperparameters to predict the AGB of the crops in the second year. The ERT performed AGB estimation using height and reflectance metrics from LiDAR-derived point cloud data and achieved a prediction performance of R2 = 0.48 at a spatial resolution of 0.35 m2. The prediction performance could be improved significantly by aggregating adjacent predictions (R2 = 0.71 and R2 = 0.93 at spatial resolutions of 1 m2 and 2 m2, respectively) as they ultimately converged to the reference biomass values because any individual errors averaged out. The AGB prediction results were examined as function of predictor type, training set size, sampling resolution, phenology, and canopy density. The results demonstrated that when combined with ML regression methods, the UAV–LiDAR method could be used to provide accurate real-time AGB prediction for crop fields at a high resolution, thereby providing a way to map their biochemical constituents.
This project received funding support from the Talent Program Horizon 2020/Marie Skłodowska-Curie Actions; a Villum Experiment grant from the Velux Foundations, the Drone-Borne LiDAR and Artificial Intelligence for Assessing Carbon Storage (MapCland) project (grant number: 00028314); the Deep Learning for Accurate Quantification of Carbon Stocks in Cropland and Forest Areas (DeepCrop) project (UCPH Strategic plan 2023 Data + Pool); as well as a UAS ability infrastructure grant from the Danish Agency for Science, Technology, and Innovation. The authors also acknowledge the financial support from the Independent Research Fund, Denmark, through the Monitoring Changes in Big Satellite Data via Massively-Parallel Artificial Intelligence project (grant number: 9131-00110B) and the Villum Fonden through the Deep Learning and Remote Sensing for Unlocking Global Ecosystem Resource Dynamics (DeReEco) project (grant number: 34306).
© 2022 by the authors.