Reliable crop predictions are essential to make well-informed agricultural decisions. Most yield prediction methods are data intensive. Therefore, the purpose of this study was to develop yield prediction models based on remote and proximal sensing, which were assessed with simple linear regression (SLR), multiple linear regression (MLR), and random forest (RF). Among the different models, RF showed a significant improvement in the accuracy of barley yield prediction.

To separate soil from an herbaceous crop, winter wheat, this work applies the multilevel OTSU algorithm to two vegetation indices derived from UAV multispectral and airborne hyperspectral images in three different phenological periods. NDVI and ChRE (Chlorophyll Red Edge) spectral indices have been used for this purpose. Linear regression has been carried out to predict crop traits such as yield, nitrogen content, and biomass. This work has shown that the application of multilevel thresholding in a spectral space represented by a vegetation index offers a suitable strategy to identify the optimal threshold to separate soil from crop. The best results have been achieved by applying a threshold obtained from a 4-level threshold procedure during the middle growing period with an NDVI calculated from airborne hyperspectral bands. In this case, 0.60, 0.69 and 0.68 R2 values were obtained, respectively, with yield, nitrogen content and biomass measurements.

The evaluation of cover crops (CCs) effects on soil N dynamics and water content (SWC) in a cropping system requires knowledge of their growth pattern. The present study aimed at evaluating the effectiveness of utilizing time series vegetation indices (VIs) acquired from the Sentinel-2 satellite to monitor CC growth, while estimating the CCs residues N release and measuring cash crop production and soil water content.Satellite imagery revealed different winter growth patterns of CCs: rye and triticale exhibited quicker growth than clover, while mustard displayed the fastest growth but suffered frost-winterkill. These findings suggest the potential utility of remote sensing tools to optimize CC utilization and improve crop management efficiency. Despite different biomass production and estimated N release among CCs species, none of them affected SWC or yield and N uptake of the cash crop.

Remote sensing offers great potential to monitor crop performance, which could help to improve water and nitrogen (N) management. The aim of this study is to assess the nutritional and water status of two wheat (Triticum aestivum L.) genotypes (Cellule and Nogal) to determine their performance by means of vegetation indices, plant traits retrieved by a radiative transfer model and thermal data. To this end, two field experiments were conducted in central Spain during 2018–2021. The results showed that the best differentiation between genotype performance was achieved by predicted chlorophyll (Chl) and leaf area index retrieved through the PROSAIL model and the canopy Chl content index (CCCI), showing that the Cellule genotype had a stronger response than Nogal to N application. Similarly, the water deficit index and canopy–air temperature difference showed that Cellule suffered lower water stress than Nogal.

This study investigates the potential of using satellite-retrieved biophysical variables to address the scarcity of agricultural management data when modeling crop productivity across heterogeneous fields with a terrestrial biosphere model (TBM). A two-season field trial was conducted in Spain, providing various combinations of nitrogen (N) fertilization and irrigation levels. The crop responses to these management levels were found to be well represented by the Leaf Area Index (LAI) retrieved from the Sentinel-2 data. The satellite-retrieved LAI was then incorporated into a terrestrial biosphere model to estimate crop biomass. This satellite-derived model produced accurate biomass estimates with an overall R2of 0.52 and RMSE of 269.7 g m-2(42.6%), with no prior knowledge of management practices nor local calibration. This study confirms the capability of satellite remote sensing to capture crop responses to management practices and highlights its potential to optimize resource use efficiency in agricultural systems.

Adjusting nitrogen (N) fertilization and accounting for the legacy of past N fertilizer application (i.e., residual N) based on remote sensing estimation of crop nutritional status may increase resource efficiency and promote sustainable management of cropping systems. Our main goal was to evaluate the potential of hyperspectral airborne imagers and ground-level sensors for identifying N fertilizer rates and the residual N effect from the previous crop fertilization in a maize/wheat rotation. A two-season field trial that provided various combinations of N rates and residual N response was established in central Spain. Ground-level sensors and aerial hyperspectral images were used to calculate vegetation indices (VIs). In addition, the solar-induced chlorophyll fluorescence (SIF760) was estimated by the Fraunhofer line-depth method using high-resolution hyperspectral imagery, and together with biophysical modeling, biochemical and biophysical constituents at canopy scales were retrieved. N uptake, N output, grain N concentration, and proximal sensors discriminated between different N fertilizer rates and identified the residual effect when it was relevant. Structural, photosynthetic pigments and short-wave infrared region (SWIR)-based VIs, together with SIF760and the chlorophyll$a + b$($C_{{\mathrm {ab}}}$), biomass, and the leaf area index (LAI), performed similarly on N rate detection. However, the residual effect of nitrification inhibitors was only detected by the structural (NDVI and OSAVI), chlorophyll (CCCI and NDRE), blue/green, NIR-SWIR ($\text{N}_{850,1510}$) indices, SIF760,$C_{{\mathrm {ab}}}$, biomass, and the LAI. This study confirmed the ability of remote sensing to identify N rates at early growth stages and highlighted its potential to detect residual N in crop rotation.

Earth Observing Systems (EOS) are a valuable tool for vegetation monitoring. Coupling information from different spaceborne sensors allows reducing the revisit time and a more accurate Earth surface processes monitoring. However, combining surface reflectance (SR) from different EOS requires compensating for atmospheric disturbances and viewing angle induced effects. The objectives of this study were i) to compare the atmospherically corrected Sentinel-2 (S2) and WorldView-3 (WV3) SR with ground-truth spectra acquired with a FieldSpec and ii) to propose and validate a signal normalization procedure for coupling S2 and WV3 imagery. The S2 imagery showed a reliable match with field spectra, however SR from WV3 was significantly different. These discrepancies likely resulted from the off-nadir acquisition angles. The signal normalization procedure, based on calibrating each WV3 band against ground-truth spectra, allowed an accurate coupling of S2 and WV3 imagery ($\text{RMSE} < 0.007$in visible bands and$\text{RMSE}=0.018$in the NIR band).

Crop residues on the soil surface provide defense against erosive forces of water and wind. Quantifying crop residue cover is crucial for monitoring extent of conservation tillage practices. Current multispectral satellite sensors either lack appropriate spectral bands to reliably distinguish crop residue from soil or cannot provide global coverage. Our objective was to estimate crop residue cover in corn and soybean fields in central Iowa by combining data from two multispectral satellites - Landsat-8 and WorldView-3. Shortly after planting in 2016, we measured crop residue cover in >45 fields using the line-point transect method. Landsat Normalized Difference Tillage Index (NDTI) required local calibrations to account for variations in soils, crops, and moisture conditions. In contrast, WorldView-3 Shortwave Infrared Normalized Difference Residue Index (SINDRI) reliably estimated crop residue cover with minimal ground truth data. Although WorldView-3 images cannot provide global coverage, they can augment and extend ground truth observations for calibrating Landsat indices.

Crop residues protect the soil against erosion, improve runoff water quality and determine C sequestration. Thus, the capability to assess crop residue cover can improve predictions of the impact of agricultural practices. Our objective was to develop a method to alleviate the adverse effect of variable moisture conditions on crop residue estimates from satellite imagery. Fields with uneven and with uniform water distribution were identified in satellite images (WorldView-3) from Maryland (USA). The results showed that moisture correction of spectral bands based on a water index reduced the root mean square error of most common residue indices, NDTI (Normalized Difference Tillage Index) and SINDRI (Shortwave Infrared Normalized Difference Residue Index). If bands are available, crop residue estimation should be based on SINDRI. If only Landsat or Sentinel-2 satellites are available, crop residues estimated combining NDTI with a water index could alleviate the adverse effect of variable moisture conditions.

Crop residues protect the soil against erosion and reduce agrochemicals in runoff water. Crop residues and soils are spectrally different in the absorption features associated with cellulose and lignin. Our objectives were to: (1) assess the effects of soil and crop residue water contents on the remotely sensed estimates of crop residue cover and (2) propose a method to mitigate these effects. Reflectance spectra of diverse crops and soils were acquired in the laboratory and the analyses was extended to agricultural fields with different crop residue covers and a wide range of moisture conditions. The slope of the linear relationship with the Cellulose Absorption Index was very sensitive to moisture conditions, whereas the slope of the Shortwave Infrared Normalized Difference Residue Index was altered in a lesser extent. Water indices that provided reliable estimates of the water content could be used to estimate crop residue cover corrected by moisture conditions.