Tays Silva Batista

Edaphic attributes strongly influence sugarcane yield, yet production environments are commonly classified based on average productivity, which may not fully capture environmental variability. This study evaluated how physicochemical soil attributes and soil classes influence sugarcane productivity and whether integrating nonlinear modeling and multivariate analyses improves the characterization of production environments. Edaphic data obtained from SoilGrids and mean Tons of Stalks per Hectare (TSH) per genotype, environment, and harvest cycle collected between 2018 and 2021 were used. Generalized additive models (GAMs) were fitted to assess the effects of soil classes and continuous soil attributes on productivity, while principal component analysis (PCA) and hierarchical clustering were used to identify edaphic gradients and group environments according to soil similarity. The GAM explained 67% of the variance in TSH and revealed significant nonlinear effects of bulk density, cation exchange capacity (CEC), silt, nitrogen, and organic carbon across soil depths. Soil class also significantly affected productivity, with LATOSSOLO VERMELHO Distrófico (LVd) associated with the highest TSH values. PCA identified two major edaphic gradients related to texture/fertility and surface fertility, and clustering grouped environments into four distinct edaphic profiles. Comparison with the traditional productivity-based classification showed that environments with similar TSH can exhibit markedly different soil characteristics, indicating that average yield alone is insufficient to describe environmental variability. Integrating nonlinear modeling and multivariate soil characterization provides a more informative framework for environmental stratification, supporting genotype recommendation and agronomic management in sugarcane production systems.

Maize is the main cereal grown in Brazil and is used mainly for animal feed and food consumption of its derivates. Under favorable environmental conditions, toxigenic fungi such as Fusarium, Aspergillus, and Penicillium spp. could produce mycotoxins in maize grain during plant growth or storage. This study aimed to evaluate the incidence of toxigenic fungi and its relationship with the grain weight of maize varieties grown under high and low topdressing nitrogen. The first factor consisted of 11 open-pollinated varieties, and the second factor of two topdressing nitrogen rates (60 and 180 kg ha-1). After harvesting the experimental units, the following variables were evaluated: 100-grain weight (HGW) and incidence of A. flavus, Penicillium spp., and Fusarium spp. There were differences (p<0.05) among maize varieties for all evaluated variables. There was a significant interaction between varieties and nitrogen for the percentage of seeds infected by A. flavus, Fusarium spp., and HGW. The incidence of fungi and HGW of maize depends on the variety and the topdressing nitrogen used.

Wood volume is the variable that best represents the yield of planted forests, and several regression models are used in its estimation. Artificial neural networks (ANNs) are recognised for their a...

Machine learning techniques (ML) have gained attention in precision agriculture practices since they efficiently address multiple applications, like estimating the growth and yield of trees in forest plantations. The combination between ML algorithms and spectral vegetation indices (VIs) from high-spatial-resolution line measurement, segment: 0.079024 m multispectral imagery, could optimize the prediction of these biometric variables. In this paper, we investigate the performance of ML techniques and VIs acquired with an unnamed aerial vehicle (UAV) to predict the diameter at breast height (DBH) and total height (Ht) of eucalyptus trees. An experimental site with six eucalyptus species was selected, and the Parrot Sequoia sensor was used. Several ML techniques were evaluated, like random forest (RF), REPTree (DT), alternating model tree (AT,) k-nearest neighbor (KNN), support vector machine (SVM), artificial neural network (ANN), linear regression (LR), and radial basis function (RBF). Each algorithm performance was verified using the correlation coefficient (r) and the mean absolute error (MAE). We used, as input, 34 VIs as numeric variables to predict DHB and Ht. We also added to the model a categorical variable as input identifying the different eucalyptus trees species. The RF technique obtained an overall superior estimation for all the tested configurations. Still, the RBF also showed a higher performance for predicting DHB, numerically surpassing the RF both in r and MAE, in some cases. For Ht variable, the technique that obtained the smallest MAE was SVM, though in a particular test. In this regard, we conclude that a combination of ML and VIs extracted from UAV-based imagery is suitable to estimate DBH and Ht in eucalyptus species. The approach presented constitutes an interesting contribution to the inventory and management of planted forests.