Assessing Spatial Variability of Barley Whole Crop Biomass Yield and Leaf Area Index in Silvoarable Agroforestry Systems Using UAV-Borne Remote Sensing

Abstract

Agroforestry systems (AFS) can provide positive ecosystem services while at the same time stabilizing yields under increasingly common drought conditions. The effect of distance to trees in alley cropping AFS on yield-related crop parameters has predominantly been studied using point data from transects. Unmanned aerial vehicles (UAVs) offer a novel possibility to map plant traits with high spatial resolution and coverage. In the present study, UAV-borne red, green, blue (RGB) and multispectral imagery was utilized for the prediction of whole crop dry biomass yield (DM) and leaf area index (LAI) of barley at three different conventionally managed silvoarable alley cropping agroforestry sites located in Germany. DM and LAI were modelled using random forest regression models with good accuracies (DM: R² 0.62, nRMSEp 14.9%, LAI: R² 0.92, nRMSEp 7.1%). Important variables for prediction included normalized reflectance, vegetation indices, texture and plant height. Maps were produced from model predictions for spatial analysis, showing significant effects of distance to trees on DM and LAI. Spatial patterns differed greatly between the sampled sites and suggested management and soil effects overriding tree effects across large portions of 96 m wide crop alleys, thus questioning alleged impacts of AFS tree rows on yield distribution in intensively managed barley populations. Models based on UAV-borne imagery proved to be a valuable novel tool for prediction of DM and LAI at high accuracies, revealing spatial variability in AFS with high spatial resolution and coverage.

Utilizing Spectral, Structural and Textural Features for Estimating Oat Above-Ground Biomass Using UAV-Based Multispectral Data and Machine Learning

“…It has gained considerable attention in terms of crop biomass modelling as it offers the advantage of faster training time, improved accuracy, higher stability, and robustness. Our results are consistent with many other studies that have demonstrated the superiority of RFR in modelling biomass and yield-related variables [ 26 , 41 , 84 , 91 ].…”

“…Several studies have also combined canopy spectral and textural features to improve estimation accuracy for crop biomass estimation. Wengert et al [ 84 ] found that GLCM-based textural features improved the estimation of barley dry biomass and leaf area index. Similar results were also documented in above-ground biomass estimation of legume grass mixtures [ 41 ], rice [ 48 ], and winter wheat [ 52 ].…”

Remotely Sensed Phenotypic Traits for Heritability Estimates and Grain Yield Prediction of Barley Using Multispectral Imaging from UAVs

“…Moreover, the reported accuracy was in the validation dataset and was not included in the training, whereas in other studies [79], the reported accuracy was only in the cross-validation dataset. Furthermore, the accuracy could be improved by adding canopy surface height [80,81] and texture variables [80] as predictors.…”

Efecto del espaciamiento en la estimación indirecta del índice de área foliar en plantaciones dendroenergéticas de Eucalipto

“…Por su parte, Tenorio et al (2019) identificaron los espaciamientos óptimos para dos clones de Gmelina arborea, maximizando la producción anual de biomasa con el mínimo IAF posible. Finalmente, Wengert et al (2021) determinaron el espaciamiento óptimo para el establecimiento de sistemas agroforestales que optimicen la relación IAF-crecimiento en especies arbóreas tropicales.…”