The total or partial removal of sugarcane (Saccharum spp. L.) straw for bioenergy production may deplete soil quality and consequently affect negatively crop yield. Plants with lower yield potential may present lower concentration of leaf-tissue nutrients, which in turn changes light reflectance of canopy in different wavelengths. Therefore, vegetation indexes, such as the normalized difference vegetation index (NDVI) associated with concentration of leaf-tissue nutrients could be a useful tool for monitoring potential sugarcane yield changes under straw management. Two sites in São Paulo state, Brazil were utilized to evaluate the potential of NDVI for monitoring sugarcane yield changes imposed by different straw removal rates. The treatments were established with 0%, 25%, 50%, and 100% straw removal. The data used for the NDVI calculation was obtained using satellite images (CBERS-4) and hyperspectral sensor (FieldSpec Spectroradiometer, Malvern Panalytical, Almelo, Netherlands). Besides sugarcane yield, the concentration of the leaf-tissue nutrients (N, P, K, Ca, and S) were also determined. The NDVI efficiently predicted sugarcane yield under different rates of straw removal, with the highest performance achieved with NDVI derived from satellite images than hyperspectral sensor. In addition, leaf-tissue N and P concentrations were also important parameters to compose the prediction models of sugarcane yield. A prediction model approach based on data of NDVI and leaf-tissue nutrient concentrations may help the Brazilian sugarcane sector to monitor crop yield changes in areas intensively managed for bioenergy production.

Nitrogen is one of the essential nutrients for the production of agricultural crops, participating in a complex interaction among soil, plant and the atmosphere. Therefore, its monitoring is important both economically and environmentally. The aim of this work was to estimate the leaf nitrogen contents in sugarcane from hyperspectral reflectance data during different vegetative stages of the plant. The assessments were performed from an experiment designed in completely randomized blocks, with increasing nitrogen doses (0, 60, 120 and 180 kg ha⁻¹). The acquisition of the spectral data occurred at different stages of crop development (67, 99, 144, 164, 200, 228, 255 and 313 days after cutting; DAC). In the laboratory, the hyperspectral responses of the leaves and the Leaf Nitrogen Contents (LNC) were obtained. The hyperspectral data and the LNC values were used to generate spectral models employing the technique of Partial Least Squares Regression (PLSR) Analysis, also with the calculation of the spectral bands of greatest relevance, by the Variable Importance in Projection (VIP). In general, the increase in LNC promoted a smaller reflectance in all wavelengths in the visible (400–680 nm). Acceptable models were obtained (R² > 0.70 and RMSE 0.81 and RMSE <1.24 g kg⁻¹. An independent validation, leave-one-date-out cross validation (LOOCV), was performed using data from other collections, which confirmed the robustness and the possibility of LNC prediction in new data sets, derived, for instance, from samplings subsequent to the period of study.

Nitrogen (N) is the main nutrient element that maintains productivity in forages; it is inextricably linked to dry matter increase and plant support capacity. In recent years, high spectral and spatial resolution remote sensors, e.g., the European Space Agency (ESA)’s Sentinel satellite missions, have become freely available for agricultural science, and have proven to be powerful monitoring tools. The use of vegetation indices has been essential for crop monitoring and biomass estimation models. The objective of this work is to test and demonstrate the applicability of different vegetation indices to estimate the biomass productivity, the foliar nitrogen content (FNC), the plant height and the leaf area index (LAI) of several tropical grasslands species submitted to different nitrogen (N) rates in an experimental area of São Paulo, Brazil. Field reflectance data of Panicum maximum and Urochloa brizantha species’ cultivars were taken and convoluted to the Sentinel-2 satellite bands. Subsequently, different vegetation indices (Normalized Difference Vegetation Index (NDI), Three Band Index (TBI), Difference light Height (DLH), Three Band Dall’Olmo (DO), and Normalized Area Over reflectance Curve (NAOC)) were tested for the experimental grassland areas, and composed of Urochloa decumbens and Urochloa brizantha grass species, which were sampled and destructively analyzed. Our results show the use of different relevant Sentinel-2 bands in the visible (VIS)–near infrared (NIR) regions for the estimation of the different biophysical parameters. The FNC obtained the best correlation for the TBI index combining blue, green and red bands with a determination coefficient (R²) of 0.38 and Root Mean Square Error (RMSE) of 3.4 g kg⁻¹. The estimation of grassland productivity based on red-edge and NIR bands showed a R² = 0.54 and a RMSE = 1800 kg ha⁻¹. For the LAI, the best index was the NAOC (R² = 0.57 and RMSE = 1.4 m² m⁻²). High values of FNC, productivity and LAI based on different sets of Sentinel-2 bands were consistently obtained for areas under N fertilization.

The difference in the matrix present in soil samples from different areas limits the performance of nutrient analysis via XRF sensors, and only a few strategies to mitigate this effect to ensure an accurate analysis have been proposed so far. In this context, this research aimed to compare the performance of different predictive models, including a simple linear regression (RS), multiple linear regression (MLR), partial least-squares regression (PLS), and random forest (RF) models for the prediction of Ca and K in agricultural soils. RS models were evaluated on XRF data without (RS1) and with (RS2) Compton normalization. In addition, it was assessed whether using soil texture information and/or vis–NIR spectra as auxiliary variables would optimize the predictive performance of the models. The results showed that all strategies allowed the mitigation of the matrix effect to some degree, enabling the determination of their Ca and K contents with excellent predictive performance (R² ≥ 0.84). The best performance was obtained using RS2 for the Ca prediction (R² = 0.92, RSME = 48.25 mg kg⁻¹ and relative improvement (RI) of 52.3% compared to RS1) and using an RF for the K prediction (R² = 0.84, RSME = 17.43 mg kg⁻¹ and RI of 24.3% compared to RS1). The results indicated that sophisticated models did not always perform better than linear models. Furthermore, using texture data and vis–NIR spectra as auxiliary data was promising only for the K prediction, which showed an error reduction in the order of 10%, contrasting with the Ca prediction, which did not reduce the prediction error by more than 1%. The best modeling approach in our study proved to be attribute-specific. These results give further insight into the development of intelligence modeling strategies for sensor-based soil analysis.