Carrot yield maps are an essential tool in supporting decision makers in improving their agricultural practices, but they are unconventional and not easy to obtain. The objective was to develop a method to generate a carrot yield map applying a random forest (RF) regression algorithm on a database composed of satellite spectral data and carrot ground-truth yield sampling. Georeferenced carrot yield sampling was carried out and satellite imagery was obtained during crop development. The entire dataset was split into training and test sets. The Gini index was used to find the five most important predictor variables of the model. Statistical parameters used to evaluate model performance were the root mean squared error (RMSE), coefficient of determination (R²) and mean absolute error (MAE). The five most important predictor variables were the near-infrared spectral band at 92 and 79 days after sowing (DAS), green spectral band at 50 DAS and blue spectral band at 92 and 81 DAS. The RF algorithm applied to the entire dataset presented R², RMSE and MAE values of 0.82, 2.64 Mg ha⁻¹ and 1.74 Mg ha⁻¹, respectively. The method based on RF regression applied to a database composed of spectral bands proved to be accurate and suitable to predict carrot yield.

Yield maps provide essential information to guide precision agriculture (PA) practices. Yet, on-board yield monitoring for sugarcane can be challenging. At the same time, orbital images have been widely used for indirect crop yield estimation for many crops like wheat, corn, and rice, but not for sugarcane. Due to this, the objective of this study is to explore the potential of multi-temporal imagery data as an alternative for sugarcane yield mapping. The study was based on developing predictive sugarcane yield models integrating time-series orbital imaging and a machine learning technique. A commercial sugarcane site was selected, and Sentinel-2 images were acquired from the beginning of the ratoon sprouting until harvesting of two consecutive cropping seasons. The predictive yield models RF (Random forest) and MLR (Multiple Linear Regression) were developed using orbital images and yield maps generated by a commercial sensor-system on harvesting. Original yield data were filtered and interpolated with the same spatial resolution of the orbital images. The entire dataset was divided into training and testing datasets. Spectral bands, especially the near-infrared at tillering crop stage showed greater contribution to predicting sugarcane yield than the use of derived spectral vegetation indices. The Root Mean Squared Error (RMSE) obtained for the RF regression based on multiple spectral bands was 4.63 Mg ha⁻¹ with an R² of 0.70 for the testing dataset. Overall, the RF regression had better performance than the MLR to predict sugarcane yield.

Soybean yield estimation is either based on yield monitors or agro-meteorological and satellite imagery data, but they present several limiting factors regarding on-farm decision level. Aware that machine learning approaches have been largely applied to estimate soybean yield and the availability of data regarding soybean yield and its components (number of grains (NG) and thousand grains weight (TGW)), there is an opportunity to study their relationships. The objective was to explore the relationships between soybean yield and its components, generate equations to estimate yield and evaluate its prediction accuracy. The training dataset was composed of soybean yield and its components’ data from 2010 to 2019. Linear regression models based on NG, TGW and yield were fitted on the training dataset and applied to a validation dataset composed of 58 on-field collected samples. It was found that globally TGW and NG presented weak (r = 0.50) and strong (r = 0.92) linear relationships with yield, respectively. In addition to that, applying the fitted models to the validation dataset, model based on NG presented the highest accuracy, coefficient of determination (R²) of 0.70, mean absolute error (MAE) of 639.99 kg ha⁻¹ and root mean squared error (RMSE) of 726.67 kg ha⁻¹.

Rapid, cost-effective, and environmentally friendly analysis of key soil fertility attributes requires an ideal combination of sensors. The individual and combined performance of visible and near infrared (VNIR) diffuse reflectance spectroscopy, X-ray fluorescence spectroscopy (XRF), and laser-induced breakdown spectroscopy (LIBS) was assessed for predicting clay, organic matter (OM), cation exchange capacity (CEC), pH, base saturation (V), and extractable (ex-) nutrients in tropical soils. A set of 102 samples, collected from two agricultural fields, with broad ranges of fertility attributes were selected. Two contrasting data fusion approaches have been applied for modeling: (i) merging spectral data of different sensors followed by partial least squares regression (PLS), known as fusion before prediction; and (ii) applying the Granger and Ramanathan (GR) averaging approach, known as fusion after prediction. Results showed VNIR as individual technique to be the best for the prediction of clay and OM content (2.61 ≤ residual prediction deviation (RPD) ≤ 3.37), while the chemical attributes CEC, V, ex-P, ex-K, ex-Ca, and ex-Mg were better predicted (1.82 ≤ RPD ≤ 4.82) by elemental analysis techniques (i.e., XRF and LIBS). Only pH cannot be predicted regardless the technique. The attributes OM, V, and ex-P were best predicted using single-sensor approaches, while the attributes clay, CEC, pH, ex-K, ex-Ca, and ex-Mg were overall best predicted using multi-sensor approaches. Regarding the performance of the multi-sensor approaches, ex-K, ex-Ca, and ex-Mg, were best predicted (RPD of 4.98, 5.30, and 4.11 for ex-K, ex-Ca and ex-Mg, respectively) using two-sensor fusion approach (VNIR + XRF for ex-K and XRF + LIBS for ex-Ca and ex-Mg), while clay, CEC and pH were best predicted (RPD of 4.02, 2.63, and 1.32 for clay, CEC, and pH, respectively) with the three-sensor fusion approach (VNIR + XRF + LIBS). Therefore, the best combination of sensors for predicting key fertility attributes proved to be attribute-specific, which is a drawback of the data fusion approach. The present work is pioneering in highlighting benefits and limitations of the in tandem application of VNIR, XRF, and LIBS spectroscopies for fertility analysis in tropical soils.

Coffee has high relevance in the Brazilian agricultural scenario, as Brazil is the largest producer and exporter of coffee in the world. Strategies to advance the production of coffee grains involve better understanding its spatial variability along fields. The objectives of this study were to adjust yield-prediction models based on a time series of satellite images and high-density yield data, and to indicate the best phenological stage of coffee crop to obtain satellite images for this purpose. The study was conducted during three seasons (2019, 2020 and 2021) in a commercial area (10.24 ha), located in the state of Minas Gerais, Brazil. Data were obtained using a harvester equipped with a yield monitor that measures the volume of coffee harvested with 3.0 m of spatial resolution. Satellite images from the PlanetScope (PS) platform were used. Random forest (RF) regression and multiple linear regression (MLR) models were fitted to different datasets composed of coffee yield and time series of satellite-image data ((1) Spectral bands—red, green, blue and near-infrared; (2) Normalized difference vegetation index (NDVI); or (3) Green normalized difference vegetation index (GNDVI)). Whether using RF or MLR, the spectral bands, NDVI and GNDVI reproduced the spatial variability of yield maps one year before harvest. This information can be of critical importance for management decisions across the season. For yield quantification, the RF model using spectral bands showed the best results, reaching R² of 0.93 for the validation set, and the lowest errors of prediction. The most appropriate phenological stage for satellite-image data acquisition was the dormancy phase, observed during the dry season months of July and August. These findings can help to monitor the spatial and temporal variability of the fields and guide management practices based on the premises of precision agriculture.