Search

Aim of study: To use artificial neural networks (ANN) to predict the values and spatial distribution of soil chemical attributes from apparent soil electrical conductivity (ECa) and soil clay contents.Area of study: The study was carried out in an area of 1.2-ha cultivated with cocoa, located in the state of Bahia, Brazil.Material and methods: Data collections were performed on a sampling grid containing 120 points. Soil samples were collected to determine the attributes: clay, silt, sand, P, K+, Ca2+, Mg2+, S, pH, H+Al, SB, CTC, V, OM and P-rem. ECa was measured using the electrical resistivity method in three different periods related to soil sampling: 60 days before (60ECa), 30 days before (30ECa) and when collecting soil samples (0ECa). For the prediction of chemical and physical-chemical attributes of the soil, models based on ANN were used. As input variables, the ECa and the clay contents were used. The quality of ANN predictions was determined using different statistical indicators. Thematic maps were constructed for the attributes determined in the laboratory and those predicted by the ANNs and the values were grouped using the fuzzy k-means algorithm. The agreement between classes was performed using the kappa coefficient.Main results: Only P and K+ attributes correlated with all ANN input variables. ECa and clay contents in the soil proved to be good variables for predicting soil attributes.Research highlights: The best results in the prediction process of the P and K+ attributes were obtained with the combination of ECa and the clay content.

Aim of study: To use artificial neural networks (ANN) to predict the values and spatial distribution of soil chemical attributes from apparent soil electrical conductivity (ECa) and soil clay contents.Area of study: The study was carried out in an area of 1.2-ha cultivated with cocoa, located in the state of Bahia, Brazil.Material and methods: Data collections were performed on a sampling grid containing 120 points. Soil samples were collected to determine the attributes: clay, silt, sand, P, K+, Ca2+, Mg2+, S, pH, H+Al, SB, CTC, V, OM and P-rem. ECa was measured using the electrical resistivity method in three different periods related to soil sampling: 60 days before (60ECa), 30 days before (30ECa) and when collecting soil samples (0ECa). For the prediction of chemical and physical-chemical attributes of the soil, models based on ANN were used. As input variables, the ECa and the clay contents were used. The quality of ANN predictions was determined using different statistical indicators. Thematic maps were constructed for the attributes determined in the laboratory and those predicted by the ANNs and the values were grouped using the fuzzy k-means algorithm. The agreement between classes was performed using the kappa coefficient.Main results: Only P and K+ attributes correlated with all ANN input variables. ECa and clay contents in the soil proved to be good variables for predicting soil attributes.Research highlights: The best results in the prediction process of the P and K+ attributes were obtained with the combination of ECa and the clay content.

Precision agriculture has been used as an important technique for localized management of soil fertility. Therefore, it is essential to characterize the spatial variability of chemical and physical attributes of the soil by sampling can represent such variations. This study aimed to analyze the correlation between the apparent electrical conductivity with the chemical and physical attributes of an Rhodic Hapludox. The work was performed on a property located in the Brazilian Cerrado. In an area of 90 hectare were collected 181 georeferenced soil samples at depths from 0.00 to 0.20 meters. The same sites and removal of samples were made apparent electrical conductivity of the soil. The samples were sent to the laboratory to perform the physical and chemical analysis. Were selected randomly sampling 30 points and calculated the Pearson correlation coefficient between the variable physical, chemical and apparent soil electrical conductivity. There was no significant correlation between the apparent electrical conductivity with the soil physical attributes. There was a significant positive correlation of apparent electrical conductivity of the soil at a depth of 0.20 m with the chemical attributes match, remaining phosphorus and zinc., A agricultura de precisão vem sendo utilizada como importante técnica de manejo localizado da fertilidade do solo.Para tanto, é indispensável à caracterização da variabilidade espacial dos atributos químicos e físicos do solo através de amostragem capaz de representar tais variações. O presente estudo teve por objetivo analisar a correlação entre a condutividade elétrica aparente com os atributos químicos e físicos de um Latossolo Vermelho distroférrico. O trabalho foi realizado em uma propriedade localizada no cerrado brasileiro. Em uma área de 90 hectares foram coletados 181 amostras de solo georeferenciadas, na profundidade de 0,00 – 0,20 metros. Nos mesmos locais de retirada de amostras foram efetuadas leituras de condutividade elétrica aparente do solo. As amostras foram encaminhadas ao laboratório para realização das análises física e química. Selecionou-se, aleatoriamente, 30 pontos amostrais e calculou-se o coeficiente de correlação de Pearson entre as variáveis físicas, químicas e a condutividade elétrica aparente do solo. Não foi observado correlação significativa entre a condutividade elétrica aparente com os atributos físicos do solo. Observou-se correlação positiva e significativa da condutividade elétrica aparente do solo na profundidade de 0,20 m com os atributos químicos fósforo, fósforo remanescente e zinco.

Precision agriculture has been used as an important technique for localized management of soil fertility. Therefore, it is essential to characterize the spatial variability of chemical and physical attributes of the soil by sampling can represent such variations. This study aimed to analyze the correlation between the apparent electrical conductivity with the chemical and physical attributes of an Rhodic Hapludox. The work was performed on a property located in the Brazilian Cerrado. In an area of 90 hectare were collected 181 georeferenced soil samples at depths from 0.00 to 0.20 meters. The same sites and removal of samples were made apparent electrical conductivity of the soil. The samples were sent to the laboratory to perform the physical and chemical analysis. Were selected randomly sampling 30 points and calculated the Pearson correlation coefficient between the variable physical, chemical and apparent soil electrical conductivity. There was no significant correlation between the apparent electrical conductivity with the soil physical attributes. There was a significant positive correlation of apparent electrical conductivity of the soil at a depth of 0.20 m with the chemical attributes match, remaining phosphorus and zinc., A agricultura de precisão vem sendo utilizada como importante técnica de manejo localizado da fertilidade do solo.Para tanto, é indispensável à caracterização da variabilidade espacial dos atributos químicos e físicos do solo através de amostragem capaz de representar tais variações. O presente estudo teve por objetivo analisar a correlação entre a condutividade elétrica aparente com os atributos químicos e físicos de um Latossolo Vermelho distroférrico. O trabalho foi realizado em uma propriedade localizada no cerrado brasileiro. Em uma área de 90 hectares foram coletados 181 amostras de solo georeferenciadas, na profundidade de 0,00 – 0,20 metros. Nos mesmos locais de retirada de amostras foram efetuadas leituras de condutividade elétrica aparente do solo. As amostras foram encaminhadas ao laboratório para realização das análises física e química. Selecionou-se, aleatoriamente, 30 pontos amostrais e calculou-se o coeficiente de correlação de Pearson entre as variáveis físicas, químicas e a condutividade elétrica aparente do solo. Não foi observado correlação significativa entre a condutividade elétrica aparente com os atributos físicos do solo. Observou-se correlação positiva e significativa da condutividade elétrica aparente do solo na profundidade de 0,20 m com os atributos químicos fósforo, fósforo remanescente e zinco.

Na colheita do café a etapa de derriça é a mais onerosa e que demanda maior tempo, por isso sua mecanização torna-se tão importante. Objetivou-se com este trabalho projetar, construir e avaliar a dinâmica de um dispositivo de derriça laboratorial para café. O protótipo consta de um dispositivo de derriça com hastes montadas em uma placa metálica e um chassi. O programa computacional CAD gerou uma malha sólida tetraédrica de segunda ordem por meio de análises de elementos finitos. Foi possível simular e mostrar erros ou falhas dos dispositivos e, também gerar dados, tais como a deformação da peça, tensão de Von Mises e esforços equivalentes. Para descrever a cinemática do dispositivo de derriça, foram desenvolvidas algumas equações baseadas na teoria de Denavit-Hartenberg, que foram comparadas ao projeto desenvolvido em programa computacional. A análise dos croquis apresentou o sistema tipo alavanca como a melhor configuração para o desenvolvimento do dispositivo, por ser de simples construção e que permita facilmente equilibrar as massas das peças do projeto. O fator de segurança alcançado foi superior à 28. O ajuste da amplitude de vibração das hastes foi possível com o eixo excêntrico de acionamento da biela. O estudo da biela e a previsão dos pontos de falha foi possível pela análise em elementos finitos., En la cosecha del café la etapa de desprendimiento es la más costosa y la que demanda mayor tiempo, por eso su mecanización se vuelve tan importante. Se pretendió con este trabajo proyectar, construir y avalar la dinámica de un dispositivo de desprendimiento laboratorial para café. El prototipo consta de un dispositivo de desprendimiento con vástagos montados sobre una placa de metal y un chasis. El programa computacional CAD genero una mallado solida tetraédrica de segunda orden por medio de análisis de elementos finitos. Fue posible simular y mostrar errores o fallas de los dispositivos y, también generar dados, tal como la deformación de la pieza, tensión de Von Mises y esfuerzo equivalentes. Para describir la cinematica del desprendimiento, fueron desarrolladas algunas ecuaciones basadas en la teoría de Denavit-Hartenberg, que fueron comparadas a lo proyecto desarrollado en programa computacional. El análisis de los dibujos presentó el sistema tipo palanca como la mejor configuración para el desarrollo del dispositivo, por ser de simple construcción y que permita fácilmente equilibrar las masas de las piezas del proyecto. El factor de seguridad alcanzado fue superior a la 28. El ajuste de la amplitud de vibración de los vástagos fue posible con el eje excéntrico de accionamiento de la biela. El estudio de la biela y la previsión de los puntos de falla fueron posibles por medio de análisis en elementos finitos., Dragging is the most costly and time-consuming stage of the coffee harvest. Therefore, its mechanization is important. The objectives of this study were to design, build, and evaluate the dynamics of a coffee-dragging device in a laboratory setting. The prototype consists of a dragging device with rods mounted on a metal plate and a chassis. Computer-aided design (CAD) software was used to generate a solid second-order tetrahedral mesh for use in finite element analyses of the device and its parts. It was possible to simulate and display the device’s errors and failures and generate data on part deformities, Von Mises tension, and equivalent efforts. Equations based on the Denavit–Hartenberg theory were developed to describe the dragging device kinematics, and the results obtained with these equations were compared to those for the design developed using the software program. A preliminary drawing analysis identified a lever-type system as the best configuration for the device, based on its simple construction and its ability to balance the weight of the project parts. The safety factor achieved was greater than 28. Adjustment of the vibration amplitude of the rods is possible using the eccentric shaft of the connecting rod drive. Finite element analyses was used to analyze the connecting rod and predict the likely failure points.

This study aimed to analyze the influence of different sampling grids in determining the spatial variability of physical attributes of a Oxisol. It was used to study an area of approximately 90 hectares, where soil was sampled at depth from 0 to 0.20 meters, using a grid of 2 points per hectare (G1). Each soil sample was composed of four subsamples and obtained using a soil sampler Dutch type. The samples were sent to the laboratory to granulometric analysis. From the initial grid, the area was divided into sampling cells of 2.9 (G2) and 4.7 hectares (G3), and assigned a coordinate value representative of the center of each cell. Classical statistical and geostatistical methods were used to characterize the data and to model the spatial dependence. Spatial dependence was detected for all physical variables of the soil, regardless of the sampling grid used. The utilization of sampling grid of 1 point for each 2.9 hectares, and the sampling cell characterized by 12 subsamples, showed itself capable of detecting the spatial variability of the physical attributes of the soil, guaranteeing reliability in the estimates, even reducing the quantity of points when compared to the densest grid.

This study aimed to analyze the influence of different sampling grids in determining the spatial variability of physical attributes of a Oxisol. It was used to study an area of approximately 90 hectares, where soil was sampled at depth from 0 to 0.20 meters, using a grid of 2 points per hectare (G1). Each soil sample was composed of four subsamples and obtained using a soil sampler Dutch type. The samples were sent to the laboratory to granulometric analysis. From the initial grid, the area was divided into sampling cells of 2.9 (G2) and 4.7 hectares (G3), and assigned a coordinate value representative of the center of each cell. Classical statistical and geostatistical methods were used to characterize the data and to model the spatial dependence. Spatial dependence was detected for all physical variables of the soil, regardless of the sampling grid used. The utilization of sampling grid of 1 point for each 2.9 hectares, and the sampling cell characterized by 12 subsamples, showed itself capable of detecting the spatial variability of the physical attributes of the soil, guaranteeing reliability in the estimates, even reducing the quantity of points when compared to the densest grid.