No abstract

Spatial interpolation methods are frequently used to characterize soil attributes' spatial variability. However, inconclusive results, about the comparative performance of these methods, have been reported in the literature. Therefore, the present study aimed to analyze the efficiency of ordinary kriging (OK) and inverse distance weighting (IDW) methods in estimating the soil penetration resistance (SPR), soil bulk density (SBD), and soil moisture content (SM) using two distinct sampling grids. The soil sampling was performed on a 5.7 ha area in Southeast Brazil. For data collection, a regular grid with 145 points (20 x 20 m) was created. Soil samples were taken at a 0.20 m layer depth. In order to compare the accuracy of OK and IDW, another grid was created from the initial grid (A), by eliminating one interspersed line, which resulted in a grid with 41 sampled points (40 x 40 m). Results showed that sampling grid A presented less errors than B, proving that the more sampling points, the lower the errors that are associated with both methods will be. Overall, the OK was less biased than IDW only for SBD (A) and SM (B) maps, whereas IDW outperformed OK for the other attributes for both sampling grids.

The challenge of recovering degraded soils due to salinity excess leads to the search for more effective strategies that can overcome this problem. Among these, one of the approaches is the use of resistant plant varieties in affected areas. This study aimed to evaluate the influence of different doses of salts on seed germination and seedling formation of two lettuce cultivars (Hanson and H121) and to verify the existence of tolerance among the cultivars. A completely randomized design was used in a 2x5x4 factorial scheme, where the cultivars were evaluated under five distinct salt doses (0, 25, 50, 75 and 100 mol.m-3, conductivities of 0.0, 2.8, 5.4, ​​8.0 and 10.6 dS.m-1, respectively), with four replicates. In this sense, the following variables were evaluated: germination rate (GR), germination speed index (GSI), seedling height (SH), root length (RL) and percentage of dry matter in relation to fresh matter (DM%). As a result, the Hanson cultivar presented better performance than the H121, under all the different salt doses, in all the studied variables. Also, the EC of 2.8 dS.m-1 did not affect any of the studied variables, including both cultivars. However, EC above 2.8 dS.m-1had, significantly, reduced the development of the cultivars. The Hanson cultivar was influenced only in the variables SH, RL and DM%, where and DM% were influenced by EC values above 8.0 and 10.6 dS.m-1, respectively. The cultivar H121 was significantly influenced by all evaluate dvariables, which demonstrates its greater susceptibility to salinity.

The increasing market interest in coffee beverage, lead coffee growers around the world to adopt more efficient methods to select the best-quality coffee beans. Currently, coffee beans selection is carried out either manually, which is a costly and unreliable process, or using electronic sorting machines, which are often inefficient because some coffee beans defects, such as sour and immature beans, have similar spectral response patterns. In this sense, the present work aimed to analyze the importance of shape and color features for different machine learning techniques, such as Support Vector Machine (SVM), Deep Neural Network (DNN) and Random Forest (RF), to assess coffee beans' defects. For this purpose, an algorithm written in Python language was used to extract shape and color features from coffee beans images. The dataset obtained was then used as input to the machine learning algorithms, developed using Python and R programing languages. The data reported in this study pointed to the importance of color descriptors for classifying coffee beans defects. Among the variables used, the components G mean from RGB (Red, Green and Blue) color space and V mean from HSV (Hue, Saturation and Value) color space were some of the most relevant features for the classification models. The results reported in this study indicate that all the classifier models presented similar performance. In addition, computer vision along with machine learning algorithms can be used to classify coffee beans with a very high accuracy (> 88%).

This study aimed to modify a webcam by replacing its near-infrared (NIR) blocking filter to a low-cost red, green and blue (RGB) filter for obtaining NIR images and to evaluate its performance in two agricultural applications. First, the sensitivity of the webcam to differentiate normalized difference vegetation index (NDVI) levels through five nitrogen (N) doses applied to the Batatais grass (Paspalum notatum Flugge) was verified. Second, images from maize crops were processed using different vegetation indices, and thresholding methods with the aim of determining the best method for segmenting crop canopy from the soil. Results showed that the webcam sensor was capable of detecting the effect of N doses through different NDVI values at 7 and 21 days after N application. In the second application, the use of thresholding methods, such as Otsu, Manual, and Bayes when previously processed by vegetation indices showed satisfactory accuracy (up to 73.3%) in separating the crop canopy from the soil.