Remote Sensing · 2021 · 92 citations · 38 references
AgricultureCrop SciencesPrecision AgricultureRemote SensingYield MappingYield MonitoringInfrared Remote SensingRemote Sensing For Crop ManagementRemote Sensing ImagerySatellite Image InterpretationSatellite SensorsVegetation IndicesCrop YieldsField-scale Yield MappingRemote Sensing-based Yield EstimationSatellite Crop MonitoringSatellite-based Agronomic MonitoringWithin-field Spatial VariabilityWithin-field VariabilityYield Variability Mapping
Crop yield monitoring is an important component in agricultural assessment. Multi-spectral remote sensing instruments onboard space-borne platforms such as Advanced Very High Resolution Radiometer (AVHRR), Moderate Resolution Imaging Spectroradiometer (MODIS), and Visible Infrared Imaging Radiometer Suite (VIIRS) have shown to be useful for efficiently generating timely and synoptic information on the yield status of crops across regional levels. However, the coarse spatial resolution data inherent to these sensors provides little utility at the management level. Recent satellite imagery collection advances toward finer spatial resolution (down to 1 m) alongside increased observational cadence (near daily) implies information on crops obtainable at field and within-field scales to support farming needs is now possible. To test this premise, we focus on assessing the efficiency of multiple satellite sensors, namely WorldView-3, Planet/Dove-Classic, Sentinel-2, and Landsat 8 (through Harmonized Landsat Sentinel-2 (HLS)), and investigate their spatial, spectral (surface reflectance (SR) and vegetation indices (VIs)), and temporal characteristics to estimate corn and soybean yields at sub-field scales within study sites in the US state of Iowa. Precision yield data as referenced to combine harvesters’ GPS systems were used for validation. We show that imagery spatial resolution of 3 m is critical to explaining 100% of the within-field yield variability for corn and soybean. Our simulation results show that moving to coarser resolution data of 10 m, 20 m, and 30 m reduced the explained variability to 86%, 72%, and 59%, respectively. We show that the most important spectral bands explaining yield variability were green (0.560 μm), red-edge (0.726 μm), and near-infrared (NIR − 0.865 μm). Furthermore, the high temporal frequency of Planet and a combination of Sentinel-2/Landsat 8 (HLS) data allowed for optimal date selection for yield map generation. Overall, we observed mixed performance of satellite-derived models with the coefficient of determination (R2) varying from 0.21 to 0.88 (averaging 0.56) for the 30 m HLS and from 0.09 to 0.77 (averaging 0.30) for 3 m Planet. R2 was lower for fields with higher yields, suggesting saturation of the satellite-collected reflectance features in those cases. Therefore, other biophysical variables, such as soil moisture and evapotranspiration, at similar fine spatial resolutions are likely needed alongside the optical imagery to fully explain the yields.
38
Conditional variable importance for random forests
Carolin Strobl, Anne‐Laure Boulesteix, Thomas Kneib et al. · BMC Bioinformatics · 2008 · 3.2K citations · Full text
Good practices for estimating area and assessing accuracy of land change
Pontus Olofsson, Giles M. Foody, Martin Herold et al. · Remote Sensing of Environment · 2014 · 2.9K citations · Full text