Soil analysis is used to estimate nutrient availability, but nutrient concentrations are not always related to yield in most fruit plants, including grapevines. Thus, additional multivariate mathematical models, such as the compositional nutrient diagnosis (CND), which takes into account leaves nutrient concentration, and yield, can contribute to estimating critical levels or sufficiency bands of elements, as well as to detect deficiency and/or excess of nutrients. The aim of the present study was to establish CND standards, and the critical level and sufficiency band of nutrients, in the grapevine Vitis vinifera L., grown in a subtropical climate region. Leaves were collected in 81 vineyards in the Campanha Gaúcha do Rio Grande do Sul region, Southern Brazil, and analyzed for macro- and micro-nutrient concentration. The yield of each vineyard was assessed. Grapevine nutritional status was calculated through the CND method. CND-r² indices were effective in establishing the nutritional status of grapevines for macro- and micro-nutrients as sub-optimal, excessive, or balanced. The CND methodology established the critical level and sufficiency bands of nutrients more accurately than the current recommendations for grapevines. Multi-nutrient associations were more effective than the single nutrient determination in defining the threshold of a given nutrient that can reduce grapevine yield.

Regional nutrient ranges are commonly used to diagnose plant nutrient status. In contrast, local diagnosis confronts unhealthy to healthy compositional entities in comparable surroundings. Robust local diagnosis requires well-documented data sets processed by machine learning and compositional methods. Our objective was to customize nutrient diagnosis of peach (Prunus persica) trees at local scale. We collected 472 observations from commercial orchards and fertilizer trials across eleven cultivars of Prunus persica and six rootstocks in the state of Rio Grande do Sul (RS), Brazil. The random forest classification model returned an area under curve exceeding 0.80 and classification accuracy of 80% about yield cutoff of 16 Mg ha⁻¹. Centered log ratios (clr) of foliar defective compositions have appropriate geometry to compute Euclidean distances from closest successful compositions in “enchanting islands”. Successful specimens closest to defective specimens as shown by Euclidean distance allowed reaching trustful fruit yields using site-specific corrective measures. Comparing tissue composition of low-yielding orchards to that of the closest successful neighbors in two major Brazilian peach-producing regions, regional diagnosis differed from local diagnosis, indicating that regional standards may fail to fit local conditions. Local diagnosis requires well-documented Humboldtian data sets that can be acquired through ethical collaboration between researchers and stakeholders.

Adequate nutritional management of any plant species requires quantifying the nutrients accumulated in the plant and knowing their allocation in the different organs. The objective of this study was to evaluate the partitioning, accumulation, export of macronutrients and the nutritional efficiency of fertigated Prata banana plants. A historical survey of annual fruit productivity was conducted in 66 plots of Prata banana, selecting four that met the annual productivity classes (< 30.0; 30.0 = 37.5; 37.5 = 45.0 and > 45.0 t ha-1). The dry matter weights of the different organs of parent plant and follower, as well as the respective contents of macronutrients, were used to estimate the accumulation, partitioning, export, sequence of accumulation of macronutrients and nutritional efficiency using the coefficient of biological utilization (CBU). The partitioning of macronutrient accumulation varied with productivity class and plant organ. The average distribution of nutrients in the parent plant and in the follower ranged from 67.5 to 82.8 % and from 17.2 to 32.5 %, respectively. Macronutrient exports per ton of bunch were 4.334, 1.660, 0.361, 0.224, 0.148 and 0.119 kg t-1 for K, N, P, Mg, S and Ca, respectively. Banana mats have a nutrient partitioning pattern for different yields, that is, this work provides evidence that there is an “ideal compartmentalization” that promotes higher productivity; however, more research is needed to support this statement. The most exported nutrients per ton of bunch were K and N. The descending order of accumulation was: K > N > Ca > Mg > P > S. It was observed that the CBUs of N and P were less sensitive to productivity variations, while those of Ca and Mg were the most sensitive.

Fertigation management of banana plantations at a plot scale is expanding rapidly in Brazil. To guide nutrient management at such a small scale, genetic, environmental and managerial features should be well understood. Machine learning and compositional data analysis (CoDa) methods can measure the effects of feature combinations on banana yield and rank nutrients in the order of their limitation. Our objectives are to review ML and CoDa models for application at regional and local scales, and to customize nutrient diagnoses of fertigated banana at the plot scale. We documented 940 “Prata” and “Cavendish” plot units for tissue and soil tests, environmental and managerial features, and fruit yield. A Neural Network informed by soil tests, tissue tests and other features was the most proficient learner (AUC up to 0.827). Tissue nutrients were shown to have the greatest impact on model accuracy. Regional nutrient standards were elaborated as centered log ratio means and standard deviations of high-yield and nutritionally balanced specimens. Plot-scale diagnosis was customized using the closest successful factor-specific tissue compositions identified by the smallest Euclidean distance from the diagnosed composition using centered or isometric log ratios. Nutrient imbalance differed between regional and plot-scale diagnoses, indicating the profound influence of local factors on plant nutrition. However, plot-scale diagnoses require large, reliable datasets to customize nutrient management using ML and CoDa models.

The importance of mineral nutrition to the various plant species has been recognized for many years. Since nutrients are directly linked to physiological and metabolic processes, they promote the growth of rootstocks and seedlings, contributing to the formation of more productive orchards. As a consequence of the lack of technical information for most fruit trees, fertilization in nurseries has still been carried out empirically, sometimes underestimating or overestimating nutritional requirements and compromising the quality of plants produced. Given the importance of mineral nutrition in the formation of high-quality seedlings and the lack of scientific information on the topic, the aim of the present review was to raise interest in further research, and contribute to produce nutritionally balanced fruit seedlings.