The monitoring and determination of peanut maturity are fundamental to reducing losses during digging operation. However, the methods currently used are laborious and subjective. To solve this problem, we developed models to access peanut maturity using images from unmanned aerial vehicles (UAV) and satellites. We evaluated an area of approximately 8 hectares in which a regular grid of 30 points was determined with weekly evaluations starting at 90 days after sowing. Two Artificial Neural Networking (ANN) were used with Radial Basis Function (RBF) and Multilayer Perceptron (MLP) to predict the Peanut Maturity Index (PMI) with the spectral bands available from each sensor. Several vegetation indices were used as input to the ANN, with the data being split 80/20 for training and validation, respectively. The vegetation index, Normalized Difference Red Edge Index (NDRE), was the most precise coefficient of determination (R² = 0.88) and accurate mean absolute error (MAE = 0.06) for estimating PMI, regardless of the type of ANN used. The satellite with Normalized Difference Vegetation Index (NDVI) could also determine PMI with better accuracy (MAE = 0.05) than the NDRE. The performance evaluation indicates that the RBF and MLP networks are similar in predicting peanut maturity. We concluded that satellite and UAV images can predict the maturity index with good accuracy and precision.

The operational slowness in the execution of direct methods for estimating forage mass, an important variable for defining the animal stocking rate, gave rise to the need for methods with faster responses and greater territorial coverage. In this context, the aim of this study was to evaluate a method to estimate the mass of Urochloa brizantha cv. BRS Piatã in shaded and full sun systems, through proximal sensing applied to the Simple Algorithm for Evapotranspiration Retrieving (SAFER) model, applied with the Monteith Radiation Use Efficiency (RUE) model. The study was carried out in the experimental area of Fazenda Canchim, a research center of Embrapa Pecuária Sudeste, São Carlos, SP, Brazil (21°57′S, 47°50′W, 860 m), with collections of forage mass and reflectance in the silvopastoral systems animal production and full sun. Reflectance data, as well as meteorological data obtained by a weather station installed in the study area, were used as input for the SAFER model and, later, for the radiation use efficiency model to calculate the fresh mass of forage. The forage collected in the field was sent to the laboratory, separated, weighed and dried, generating the variables of pasture total dry mass), total leaf dry mass, leaf and stalk dry mass and leaf area index. With the variables of pasture, in situ, and fresh mass, obtained from SAFER, the training regression model, in which 80% were used for training and 20% for testing the models. The SAFER was able to promisingly express the behavior of forage variables, with a significant correlation with all of them. The variables that obtained the best estimation performance model were the dry mass of leaves and stems and the dry mass of leaves in silvopastoral and full sun systems, respectively. It was concluded that the association of the SAFER model with the proximal sensor allowed us to obtain a fast, precise and accurate forage estimation method.

A Revista Ciência Agronômica é voltada para estudos relacionados com as Ciências Rurais e Recursos Naturais

The mechanized harvesting of peanut crops results in both visible and invisible losses. Therefore, monitoring and accurately determining pod maturation are essential to minimizing such losses. The objectives of this study were to (i) identify the most relevant variables for estimating peanut pod maturation and (ii) estimate two maturation indices (brown and black classes; orange, brown, and black classes) using Remote Sensing (RS) and Artificial Neural Networks (ANN), while assessing the generalization potential of the models across different areas. The experiment was carried out in two commercial peanut fields in the state of São Paulo, Brazil, during the 2021/2022 and 2022/2023 growing seasons, using the IAC 503 cultivar. Data collection began one month before the expected harvest date, with weekly intervals. Spectral variables and vegetation indices were obtained from orbital remote sensing (PlanetScope), while climatic data were retrieved from NASA POWER. For analysis, two ANN architectures were employed: Multilayer Perceptron (MLP) and Radial Basis Function (RBF). The dataset from the Cândido Rodrigues site was split into 80% for training and 20% for testing. The model was then evaluated and generalized using data from the Guariba site. Variable selection involved filtering via Principal Component Analysis (PCA) followed by the Stepwise method. Both models demonstrated high accuracy (R² ≥ 0.90; MAE between 0.06 and 0.07). Generalization tests yielded promising results (R² between 0.59 and 0.64; MAE between 0.13 and 0.17), confirming the robustness of the approach under different conditions.

Machine harvesting is an essential step of crop production, considering a dynamic operation, and is subject to losses due to several factors that affect its quality. The objective of this study was to evaluate the quality of mechanized peanut pickers in the three soil tillage operations using Statistical Quality Control (SQC) tools. We conducted the experiments in a peanut field located at 21°20′23″ S and 47°54′06″ W of Brazilian peanut farmers. We used Statistic Control Quality (SQC) experimental design to monitor peanut losses during machine harvesting. The treatments evaluated were three soil tillage operations: conventional (CT), rotary tillers (RT), and hoe (RH). The quality indicators were collected inside the picker’s bulk tank. Statistical analyses used were descriptive statistics and SQC tools (run charts, control charts, and the Ishikawa diagram). The process was considered stable for indicators: whole pods (CT, RT, and RH), broken pods (CT, RT, and RH), and hatched pods (CT, RT, and RH), while the other indicators showed points that were out of control. With the application of SQC tools, it was possible to identify the factors that caused the increase of variability in peanut harvesting, listing the points to be improved to support decision-making, always aiming to increase this operation’s quality.