Reference evapotranspiration (ET₀) is one important agrometeorological parameter for hydrological studies and climate risk zoning. ET₀ calculation by the FAO Penman–Monteith method requires several input data. However, the availability of climate data has been a problem in many places around the world, so the study of scenarios with different combinations of climate data has become essential. The aim of this study was to evaluate the performance of artificial neural network (ANN), random forest (RF), support vector machine (SVM), and multiple linear regression (MLR) approaches to estimate monthly mean ET₀ with different input data combinations and scenarios. Three scenarios were evaluated: at the state level, where all climatological stations were used (Scenario I–SI), and at the regional level, where the Minas Gerais state was divided according to the climatic classifications of Thornthwaite (Scenario II–SII) and Köppen (Scenario III–SIII). ANN and RF performed better in ET₀ estimation among the models evaluated in the SI, SII, and SIII scenarios with the following data combinations: (i) latitude, longitude, altitude, month, mean, maximum and minimum temperature, and relative humidity and (ii) latitude, longitude, altitude, month, mean temperature, and relative humidity. SVM and MLR models are recommended for all scenarios in situations with limited climatic data where only air temperature and relative humidity data are available. The results and information presented in this study are important for the agricultural chain and water resources in Minas Gerais state.

The development of approaches to determine the spatial variability of nitrogen (N) into coffee leaves is essential to increase productivity and reduce production costs and environmental impacts associated with excessive N applications. Thus, this study aimed to assess the potential of the Random Forest (RF) machine learning method applied to vegetation indices (VI) obtained from Remotely Piloted Aircraft (RPA) images to measure the N content in coffee plants. A total of 10 VI were obtained from multispectral images by a camera attached to a rotary-wing RPA. The RGB orthomosaic was used to determine sampling points at the crop area, which were ranked by N levels in the plants as deficient, critical, or sufficient. The chemical analysis of N content in the coffee leaves, as well as the VI values in sample points, were used as input parameters for the image training and its classification by the RF. The suggested model has shown global accuracy and a kappa coefficient of up to 0.91 and 0.86, respectively. The best results were achieved using the Green Normalized Difference Vegetation (GNDVI) and Green Optimized Soil Adjusted Vegetation Index (GOSAVI). In addition, the model enabled the evaluation of the spatial distribution of N in the coffee trees, as well as quantification of N deficiency in the crop for the whole area. The GNDVI and GOSAVI allowed the verification that 22% of the entire crop area had plants with N deficiency symptoms, which would result in a reduction of 78% in the amount of N applied by the producer.

Nitrogen (N) is the most extracted and exported element by the soybean crop. In high yield tropical environments with irrigation, little is known about N accumulation in different soybean plant organs as well as the N balance. The objective of this study was to characterize soybean growth, N accumulation in plant organs, N balance, and N gap in a high yield tropical environment. This study was performed in a homogeneous field, in a soil with low organic matter, with 20 kg ha^-1 of N, under furrow fertilization. Evaluations were performed ten times, temporally distributed from emergence to senescence. The soybean cultivar used was ‘RK7518 IPRO’ and was sown with row spacing of 0.45 m and a seeding rate of 300,000 plants ha^-1. Plant N partition, N from the biological N fixation (BNF), grain yield, crop harvest index (HI), N harvest index (NHI) with and without root contribution were evaluated. Also, at the grain filling stage the N gap was evaluated from the soil by difference between whole plant accumulated N and the amount of N from BNF. The average grain yield was 6,470 kg ha^-1 and leads to a negative partial balance of N of -33.4 and -42.8 kg_[N] ha^-1 with and without roots, respectively. The N gap from the soil was 231.7 kg_[N] ha^-1. It is recommended to adopt techniques that increase the efficiency of BNF and the soil N accumulation to balance these production systems in the medium to long term.

Sugarcane (Sacharum officinarum L.) monocropping has had a great socio-economic and environmental impact in Brazil, and agroforestry systems have been considered as an alternative for more sustainable production; however, there is a lack of field research under such conditions. The aim of this study was to evaluate the growth rates, radiation use efficiency and yield traits in sugarcane cultivated in the understory of Aleurites fordii, in two agroforestry arrangements and monocropping systems. A field experiment was conducted from July 2015 to June 2016 in the city of Frederico Westphalen, Rio Grande do Sul, Brazil. The radiation use efficiency, assimilate partitioning, leaf area index, absolute growth rate, net assimilation rate, number of tillers, plant height, % of intercepted solar radiation, extinction coefficient, and yield in each system was evaluated. In agroforestry systems, the dynamic interactions between multiple plant species change with the time and can result in unique microclimates. The use of agroforestry systems in 12 x 12m arrangements should be prioritized because it enables greater yields and radiation availability in the understory. This study sought to provide new sustainable alternatives for farmers in order to increase the diversification of the rural property and maintain the preservation of existing agroecosystems.

The aim of this study was to determine the effect of age and plant spacing on biomass production of four forestry tree species: Acacia mearnsii De Wild, Eucalyptus grandis W. Hill ex Maiden, Mimosa scabrella Benth, and Ateleia glazioviana Baill. The following spacings of plants at the ages of 1, 3, and 5 years after planting were considered: 2.0 × 1.0 m, 2.0 × 1.5 m, 3.0 × 1.0 m, and 3.0 × 1.5 m. The study was installed in randomized complete block design. Biomass was determined by weighing different components of the trees after harvesting. Plant spacing affected biomass production of forestry trees at different ages after planting. Dense spacings produced larger quantities of biomass than less dense spacing. The tree species differed in biomass production: Eucalyptus grandis produced the largest quantity (325.1 t ha^-1), followed by Acacia mearnsii (239.3 t ha^-1), Mimosa scabrella (53.4 t ha^-1), and Ateleia glazioviana (32.1 t ha^-1). Wood biomass represented the biomass component with the largest production over time, which showed an increasing proportion throughout the age groups, followed branch, leaf, and bark biomass.