Quality control is used to evaluate processes and products, and is a powerful tool for reducing variability. The objective of this study was to evaluate the quality of green sugarcane (Saccharum spp.) cutting for mechanized harvest, using statistical quality control tools. Cutting height and damage to ratoon stalks caused by different blade and disc combinations of the basecutter mechanism were used as indicators of quality. Cutting height showed high variability with a controlled process for some treatments. However, these treatments were incapable of producing satisfactory results. The damage index was lower in treatments that used tilted blades, but above the target for all treatments, which caused significant damage to the ratoons. In general, the process of mechanized harvest as assessed by these indicators was found incapable of achieving targeted results and staying below specification limits, and thus requires corrective actions to improve quality

Considerando que a colheita é a etapa final de um processo produtivo e que as perdas devem ser mantidas dentro de padrões aceitáveis, as regulagens das colhedoras e as características agronômicas da cultura deverão permitir menores perdas quantitativas para que possa atingir o máximo nível de qualidade e maior sustentabilidade do sistema produtivo. Este trabalho teve como objetivo determinar as perdas quantitativas, distribuição de palha e características operacionais da colhedora por meio do controle estatístico de processo, bem como verificar a qualidade da operação de colheita. O trabalho foi realizado no município de Santa Juliana (MG), com as coordenadas geográficas de referência 19º 18'Se 47º 31'O. A área amostrada constou de 40 pontos distribuídos em malha retangular, equidistantes de 50 m, definidos sequencialmente a partir do momento de início da colheita. Em cada ponto foi determinado o teor de água dos grãos, número de vagens por planta, altura de inserção de primeira vagem, altura de plantas, produtividade, distribuição de palha e características operacionais da colhedora. A perda de grãos ocasionada pela colhedora esteve fora dos limites de controle, porém dentro dos padrões aceitáveis de perdas para cultura da soja. A qualidade da operação de colheita e as regulagens da colhedora foram dependentes da velocidade de deslocamento. A distribuição de palha esteve próxima do desejável para o sistema de semeadura direta. A utilização das cartas de controle foi eficiente na identificação dos pontos fora de controle e na avaliação da qualidade do processo de colheita.

Identifying nematode damage in large soybean areas is not always achievable in a practical way. Multispectral reflectance sensors have not been thoroughly evaluated to detect nematode damage in soybeans (Glycine max L.). The main research aims of this study were to: (i) determine the bivariate relationship between individual spectral bands and vegetation indices (VIs) relative to soybean conditions (symptomatic versus asymptomatic), and (ii) to select the best model for identifying plant conditions using three algorithms (logistic regression—LR, random forest—RF, conditional inference tree—CIT) and three options for data input using bands, vegetation indices (VIs), and bands plus VIs. The trial was conducted in Brazil on three on-farm soybean fields presenting different species of nematode infestation. Multispectral imagery was obtained using a drone-mounted MicaSense RedEdge^® sensor. At each sampling, georeferenced point nematode infestation and spectral measurements of soybean plants were retrieved for the classification of symptomatic and asymptomatic areas, according to the threshold level adopted. Bivariate analysis of variance (ANOVA), LR, RF, and CIT were used to select the multispectral bands/VIs that discriminated among symptomatic and asymptomatic plants, assessing the best model via their respective parameters for accuracy, sensitivity, and specificity. The greatest classification accuracy (>0.70) was achieved when using the CIT algorithm with the spectral bands only, with green (560 ± 20 nm) and near-infrared (840 ± 40 nm) included as the main spectral input variables in the model. These results demonstrate the potential of combining remotely sensed data and machine learning to distinguish nematode-symptomatic and asymptomatic soybean plants.

Palm oil has become one of the most consumed vegetable oils in the world, and it is a key element in profitable global value chains. In Costa Rica, oil palm cultivation is one of the three crops with the largest occupied agricultural area. The objective of this study was to explain and predict yield in safe time lags for production management by using free-access satellite images. To this end, machine learning methods were performed to a 20-year data set of an oil palm plantation located in the Central Pacific Region of Costa Rica and the corresponding vegetation indices obtained from LANDSAT satellite images. Since the best correlations corresponded to a one-year time lag, the predictive models Random Forest (RF), Least Absolute Shrinkage and Selection Operator (LASSO), Extreme Gradient Boosting (XGBoost), Recursive Partitioning and Regression Trees (RPART), and Neural Network (NN) were built for a Time-lag 1. These models were applied to all genetic material and to the predominant variety (AVROS) separately. While NN showed the best performance for multispecies information (r² = 0.8139, NSE = 0.8131, RMSE = 0.3437, MAE = 0.2605), RF showed a better fit for AVROS (r² = 0.8214, NSE = 0.8020, RMSE = 0.3452, MAE = 0.2669). The most relevant vegetation indices (NDMI, MSI) are related to water in the plant. The study also determined that data distribution must be considered for the prediction and evaluation of the oil palm yield in the area under study. The estimation methods of this study provide information on the identification of important variables (NDMI) to characterize palm oil yield. Additionally, it generates a scenario with acceptable uncertainties on the yield forecast one year in advance. This information is of direct interest to the oil palm industry.

O conceito de controle de qualidade nas operações inserido na agricultura é viabilizado por incidir diretamente nos principais objetivos do processo produtivo: retorno econômico e aumento da produtividade. A colheita mecanizada normalmente é realizada sem que haja controle efetivo para que a variabilidade das perdas fique dentro de padrões aceitáveis. Esta pesquisa teve o objetivo de determinar e caracterizar as perdas e a distribuição da cobertura vegetal após a colheita mecanizada da soja, por meio de ferramenta de controle estatístico de processo (cartas de controle). A média da perda de grãos total foi próxima do limite superior aceitável para a cultura da soja, apresentando alta variabilidade entre os pontos, tornando o processo fora de controle. A distribuição de cobertura vegetal manteve-se em processo controlado, com maior variabilidade onde o relevo foi mais inclinado. A utilização das cartas de controle foi eficiente na identificação dos pontos fora de controle e na avaliação da qualidade do processo de colheita.