Feature-specific nutrient management of onion (Allium cepa) using machine learning and compositional methods.

While onion cultivars, irrigation and soil and crop management have been given much attention in Brazil to boost onion yields, nutrient management at field scale is still challenging due to large dosage uncertainty. Our objective was to develop an accurate feature-based fertilization model for onion crops. We assembled climatic, edaphic, and managerial features as well as tissue tests into a database of 1182 observations from multi-environment fertilizer trials conducted during 13 years in southern Brazil. The complexity of onion cropping systems was captured by machine learning (ML) methods. The RReliefF ranking algorithm showed that the split-N dosage and soil tests for micronutrients and S were the most relevant features to predict bulb yield. The decision-tree random forest and extreme gradient boosting models were accurate to predict bulb yield from the relevant predictors (R2 > 90%). As shown by the gain ratio, foliar nutrient standards for nutritionally balanced and high-yielding specimens producing > 50 Mg bulb ha-1 set apart by the ML classification models differed among cultivars. Cultivar × environment interactions support documenting local nutrient diagnosis. The split-N dosage was the most relevant controllable feature to run future universality tests set to assess models' ability to generalize to growers' fields.

Qualitative soil quality assessment is efficient in a grazing system with or without trees.

BACKGROUND: Soil quality (SQ) assessment is affected by methods that convert data sets into indices, and such analyses are expensive and time-consuming. Qualitative SQ assessments are faster and cheaper than quantitative methods and they can be repeated to monitor SQ in crop and pasture systems. We evaluated SQ using qualitative and quantitative SQ indicators of two grazing systems under Voisin rational grazing (VRG) with trees (WT) or without trees (NT). We took an adjacent native forest as a reference and we used principal component analysis (PCA) to compare the accuracy of the assessment methods. RESULTS: According to the set of indicators used for quantitative assessment, the WT system and the Forest had higher SQ than other systems as a result of higher values of soil physical and chemical indicators. This the reflected better performance of soil in functions related to structural support, nutrient cycling and biological productivity. According to the set of indicators used for qualitative assessment, the WT system showed better SQ than the NT areas because of the higher scores of all indicators and better performance of the soil functions, and those values were close to the Forest in the indicators. PCA applied to integrate the data of qualitative and quantitative indicators indicated that SQ in WT was similar to Forest. CONCLUSION: The qualitative evaluation was as efficient as the quantitative evaluation for SQ assessment in VRG areas with and without trees. Its use can promote farmers' autonomy and the development of skills to identify environmental factors that help to evaluate their practices. © 2023 Society of Chemical Industry.

Diversity and botanical composition of native species in the Pampa biome in vineyards cultivated on soils with high levels of copper, zinc and manganese and phytoremediation potential.

Viticulture allows the preservation of native species inside vineyards in the Pampa biome. However, phytosanitary treatments in these areas can increase the levels of Cu, Zn and Mn. The study aimed to (i) verify the influence of Cu, Zn and Mn contents in Pampa biome soils; (ii) identify variables related to Cu, Zn and Mn that most contribute to the variation in richness, diversity, and dry matter production of native vegetation, (iii) investigate the phytoremediation potential of species present in vineyards. Botanical composition, Cu, Zn, Mn available in the soil, and plant nutritional composition in two vineyards (V1 and V2) and native field (NF) were evaluated. Vineyards showed higher Cu, Zn and Mn contents in the soil, resulting in the lowest biomass, richness, and diversity of native species. Mn in tissue was the most important variable in explaining the variation in dry matter. Zn in the soil helped to explain the difference in species richness and diversity. P concentration in tissue was important in elucidating the variation in species diversity. Paspalum plicatulum and Paspalum notatum have potential for phytostabilization of metals in vineyards.

Applications and Market of Micro-Organism-Based and Plant-Based Inputs in Brazilian Agriculture.

The use of plant-based and micro-organism-based biological inputs is a sustainable agricultural practice. It promotes a suitable and better utilization of non-renewable resources in the environment. The benefits of using micro-organisms are associated with direct and indirect mechanisms, mainly related to improvements in the absorption and availability of nutrients, resulting in a consequent impact on plant growth. The main benefits of using biochemical pesticides are the promotion of sustainability and the management of resistance to pests and diseases. Although the use of micro-organisms and botanical metabolites is a promising agricultural alternative, they are still primarily concentrated in grain crops. There is a huge opportunity to expand the plant-based and micro-organism-based biological inputs used in agriculture due to the wide range of mechanisms of action of those products. At a global level, several terminologies have been adopted to characterize biological inputs, but many terms used conflict with Brazilian legislation. This review will clarify the classes of biological inputs existing in Brazil as well as present the application and evolution of the market for microbiological and plant-based inputs.

Foliar Application of Selenium Associated with a Multi-Nutrient Fertilizer in Soybean: Yield, Grain Quality, and Critical Se Threshold.

Selenium uptake and its content in soybean grains are affected by Se application methods. This study evaluated the impact of Se foliar application combined with a multi-nutrient fertilizer (MNF) on soybean, establishing a Se threshold to better understand the relationship between Se content in grains and yield of two genotypes (58I60 Lança and M5917). Two trials were conducted in a 4 × 2 factorial design: four Se rates (0, 10, 40, 80 g Se ha-1) and two methods of foliar Se application (Se combined or not with MNF). Foliar fertilizers were applied twice, at phenological stages of beginning of pod development and grain filling. Grain yield increased with the application of MNF, yet Se rates increased Se contents linearly up to 80 g Se ha-1, regardless of the use of MNF. Lança and M5917 genotypes had grain Se critical thresholds of 1.0 and 3.0 mg kg-1, respectively. The application of Se favored higher contents of K, P, and S in grains of genotype Lança and higher contents of Mn and Fe in grains of genotype M5917. Our findings highlight the importance of addressing different Se fertilization strategies as well as genotypic variations when assessing the effects of Se on soybean yield and grain quality.

Phytoremediation of Cu-contaminated vineyard soils in Brazil: A compendium of Brazilian pot studies.

Vineyard soils can be contaminated by copper (Cu) due to successive applications of fungicides and organic fertilizers. Soil remediation can be addressed by altering soil properties or selecting efficient Cu-extracting cover crops tolerant to Cu toxicity. Our objectives were to synthesize the Cu-extracting efficiency by plant species tested in Brazil, classify them according to Cu resistance to toxicity, and assess the effect of soil properties on attenuating Cu toxicity. We retrieved results from 41 species and cultivars, totaling 565 observations. Freshly added Cu varied between 50 and 600 mg Cu kg-1 of soil across studies. The partition of Cu removal between the above- and below-ground portions was scaled as a logistic variable to facilitate data synthesis. The data were analyzed using the Adaboost machine learning model. Model accuracy (predicted vs. actual values) reached R2  = 0.862 after relating species, cultivar, Cu addition, clay, SOM, pH, soil test P, and Cu as features to predict the logistic target variable. Tissue Cu concentration varied between 7 and 105 mg Cu kg-1 in the shoot and between 73 and 1340 mg Cu kg-1 in the roots. Among soil properties, organic matter and soil test Cu most influenced the accuracy of the model. Phaseolus vulgaris, Brassica juncea, Ricinus communis, Hordeum vulgare, Sorghum vulgare, Cajanus cajan, Solanum lycopersicum, and Crotolaria spectabilis were the most efficient Cu-extracting cover crops, as shown by positive values of the logistic variable (shoot removal > root removal). Those Cu-tolerant plants showed differential capacity to extract Cu in the long run.

Neutral-to-positive cadmium effects on germination and seedling vigor, with and without seed priming.

This review gathered and analyzed data about (i) the Cd-induced impacts on seed germination and seedling vigor, and (ii) the use of different priming agents to mitigate Cd-induced impacts on the early plant development. Critical evaluation of the obtained data revealed intriguing results. First, seeds of diverse species can endure exposures to Cd. Such endurance is exhibited as maintenance of or even improvement in the seed germination and vigor (up to 15% and 70%, respectively). Second, the main factors influencing seed tolerance to Cd toxicity are related to temporal variations in anatomical, physiological, and/or biochemical features. Third, Cd can trigger diverse transgenerational effects on plants by shaping seed endophytes, by modulating seed provisioning with resources and regulatory elements, and/or by altering seed (epi)genomics. Fourth, different chemical, biological and physical priming agents can mitigate Cd-induced impacts on seeds, sometimes enhancing their performance over the control (reference) values. Overall, this review shows that the impacts of Cd on seed germination and vigor encompass not only negative outcomes but also neutral and positive ones, depending upon the Cd dose, media properties, plant species and genotypes, plant developmental stage and organ, and management approaches. Increasing our understanding of plant tolerance mechanisms against the growing background Cd pollution is relevant to support breeding programs, agricultural practices, and health-environmental policies.

Subcellular distribution and physiological responses of native and exotic grasses from the Pampa biome subjected to excess manganese.

Fungicides containing manganese (Mn) applied to control plant diseases increase the concentration of Mn in soils, which may potentiate Mn toxicity in acid soils. Some species of wild grasses, such as those from the Pampa biome located in South America, or even those introduced into this biome, may possess different mechanisms of tolerance to excess Mn. The present study aimed to evaluate the subcellular distribution and physiological and biochemical responses of exotic and native grasses from the Pampa biome, cultivated in Mn excess. The experiment was conducted in nutrient solution in a greenhouse, in an entirely randomized design, bifactorial 4 × 4, consisting of four Mn concentrations (2 [control], 300, 600 and 900 µM) and four species (two exotic: Avena strigosa and Lolium multiflorum; and two native: Paspalum notatum and Paspalum plicatulum). At 27 days of exposure to the treatments, biomass and growth rates, leaf gas exchange with the environment, photosynthetic pigment concentrations of malondialdehyde and H2O2, antioxidant enzyme activities (SOD and POD), and subcellular distribution of Mn were evaluated. Most of the grasses showed high concentration of Mn in tissues, mainly, in the shoot. In the presence of 900 µM Mn, more than 80% of the absorbed Mn was compartmentalized in the cell walls and vacuoles of the cells. Compartmentalization of Mn excess into metabolically less active organelles is the main tolerance factor in grasses. Physiological and biochemical responses were stimulated in the presence of 300 µM Mn, while 900 µM Mn negatively affected biochemical-physiological responses of grasses. The species L. multiflorum was most sensitive to excess Mn, while P. notatum was the most tolerant.

Kinetic parameters related to nitrogen uptake in 'Okinawa' peach rootstocks are altered by 'Chimarrita' scion Nitrogen uptake in 'Okinawa' peach rootstock.

BACKGROUND: The kinetic parameters of peach rootstock are a major factor contributing to its nitrogen (N) uptake efficiency, which directly affects the yield and quality parameters. However, the impact of grafting on N kinetic parameters is not sufficiently known as rootstocks are grafted with other scion cultivars before being transplanted to the field. The objective of this study was therefore to evaluate whether the grafting of 'Okinawa' rootstock with the scion cultivar 'Chimarrita' can alter the kinetic parameters related to N uptake. RESULTS: The plants were acclimatized in Hoagland solution for 21 days and, sequentially, were tested to assess the depletion of the internal reserves at 15 and 30 days in CaSO4 solution. Morphological and physiological parameters were evaluated, and kinetic parameters were calculated. The depletion period for to reach the minimum concentration (Cmin ) of NO3 - and NH4 + in the plant was 62 h and 56 h, respectively. The optimal time for internal reserve depletion for 'Okinawa' rootstock with and without the 'Chimarrita' scion was 30 days. CONCLUSION: 'Okinawa' rootstock grafted with 'Chimarrita' scion cultivar was more efficient in NO3 - and NH4 + uptake. © 2022 Society of Chemical Industry.

Physiological and biochemical characterization of copper-toxicity tolerance mechanism in grass species native to Pampa Biome and Atlantic Forest for use in phytoremediation.

Orchards and vineyards account for significant copper (Cu) accumulation in the soil due to frequent Cu fungicide applications to control leaf diseases. Although grass species are distributed in these areas likely because of their physiological mechanisms to combat Cu toxicity-related stress, the aim of the present study is to identify grass species presenting biochemical-physiological responses that feature adaptive Cu toxicity tolerance mechanisms. Three grass species native to the Pampa and Atlantic Forest biomes (Paspalum notatum, P. plicatulum, and P. urvillei) and an exotic species (Cynodon dactylon) were tested. Plants were cultivated in pots filled with 4 kg of typic Hapludalf soil, under two Cu availability, control, and toxicity conditions (80 mg Cu kg soil-1). Photosynthetic parameters, relative growth rate, root dry matter, shoot dry matter, the activity of stress-fighting enzymes (superoxide dismutase and guaiacol peroxidase), root biometry, soluble organic carbon, soil pH, and electrical conductivity were evaluated. P. notatum and P. urvillei have physiological characteristics that allow high translocation factor and Cu accumulation in the root and shoot, and it allows their use in phytoremediation processes due to (1) greater activity of stress-fighting enzymes such as POD in the shoot; (2) to larger diameter roots, which allow greater Cu complexation in them - they are lesser sensitive to stress caused by Cu than the other species; and (3) greater soluble organic carbon exudation in the rhizosphere than species P. plicatulum and C. dactylon, which can complex Cu2+ and reduce the presence of forms toxic to plants.

Prediction of Nitrogen Dosage in 'Alicante Bouschet' Vineyards with Machine Learning Models.

Vineyard soils normally do not provide the amount of nitrogen (N) necessary for red wine production. Traditionally, the N concentration in leaves guides the N fertilization of vineyards to reach high grape yields and chemical composition under the ceteris paribus assumption. Moreover, the carryover effects of nutrients and carbohydrates stored by perennials such as grapevines are neglected. Where a well-documented database is assembled, machine learning (ML) methods can account for key site-specific features and carryover effects, impacting the performance of grapevines. The aim of this study was to predict, using ML tools, N management from local features to reach high berry yield and quality in 'Alicante Bouschet' vineyards. The 5-year (2015-2019) fertilizer trial comprised six N doses (0-20-40-60-80-100 kg N ha-1) and three regimes of irrigation. Model features included N dosage, climatic indices, foliar N application, and stem diameter of the preceding season, all of which were indices of the carryover effects. Accuracy of ML models was the highest with a yield cutoff of 14 t ha-1 and a total anthocyanin content (TAC) of 3900 mg L-1. Regression models were more accurate for total soluble solids (TSS), total titratable acidity (TTA), pH, TAC, and total phenolic content (TPC) in the marketable grape yield. The tissue N ranges differed between high marketable yield and TAC, indicating a trade-off about 24 g N kg-1 in the diagnostic leaf. The N dosage predicted varied from 0 to 40 kg N ha-1 depending on target variable, this was calculated from local features and carryover effects but excluded climatic indices. The dataset can increase in size and diversity with the collaboration of growers, which can help to cross over the numerous combinations of features found in vineyards. This research contributes to the rational use of N fertilizers, but with the guarantee that obtaining high productivity must be with adequate composition.

Potential phytoremediation of Pampa biome native and invasive grass species cohabiting vineyards contaminated with Cu in Southern Brazil.

The objectives were (a) to evaluate whether grasses native to the Pampa biome, Axonopus affinis Chase, Paspalum notatum Flüggé and Paspalum plicatulum Michx, and the invasive grass Cynodon dactylon (L.). Pers have the potential to phytoremediate soil contaminated with Cu (0, 35 and 70 mg Cu kg-1); (b) assess whether the growth of these species is compromised by the excess of Cu available in the soil; and (c) determine the impact of excess Cu on the physiological responses of the studied species. C. dactylon presented the best performance in soil contaminated with 35 mg of Cu kg-1. In C. dactylon, the concentrations of chlorophyll b and carotenoids increased, as did the photosynthetic rate and plant growth. Phytotoxic effects of Cu in soil contaminated with 70 mg of Cu kg-1 were more severe on A. affinis and led to plant death. The other species presented reduced photosynthetic and growth rates, as well as increased activity of antioxidant enzymes such as superoxide dismutase and guaiacol peroxidase. This very same Cu level has decreased photosynthetic pigment concentrations in P. notatum and P. plicatulum. On the other hand, it did not change chlorophyll a and b concentrations in C. dactylon and increased carotenoid concentrations in it. High values recorded for Cu bioaccumulation-in-grass-root factor, mainly in P. plicatulum, have indicated that the investigated plants are potential phytostabilizers. High C. dactylon biomass production-in comparison to other species-compensates for the relatively low metal concentration in its tissues by increasing metal extraction from the soil. This makes C. dactylon more efficient in the phytoremediation process than other species.

Proposition of critical thresholds for copper and zinc transfer to solution in soils.

Several studies have reported increased copper (Cu) and zinc (Zn) levels in agricultural soils worldwide, mainly due to organic waste and successive leaf fungicide applications in crops. However, the critical transfer thresholds in soils, which can indicate the real risk of environmental contamination and toxicity to plants, remain poorly understood. This study aimed to define the maximum Cu and Zn adsorption capacity (MAC) and threshold (T-Cu and T-Zn) in different soils in Southern Brazil, which present different clay and organic matter (OM) levels. Bw (Oxisol) and A horizon (Inceptisol) samples were used to obtain soils with clay and OM contents ranging from 4 to 70% and from 0.5 to 9.5%, respectively. Cu and Zn adsorption curves were plotted for MAC determination purposes. Based on Cu and Zn MAC values, different concentrations of these elements were applied to the soils for subsequent quantification of available Cu and Zn levels (Mehlich-1 and water). T-Cu in soils with different clay contents ranged from 81 to 595 mg Cu kg-1, whereas T-Zn, from 195 to 378 mg Zn kg-1. T-Cu in soils with different OM levels ranged from 97 to 667 mg Cu kg-1, whereas T-Zn, from 226 to 495 mg Zn kg-1. T-Cu can be calculated through the equation: T-Cu = 75 × (%CL0.34) × (%OM0.39), whereas T-Zn: T-Zn = 2.7 × (CL) + 126 (by taking into consideration the clay content) and T-Zn = - 9.3 × (%OM)2 + 92.4 × (%OM) + 66 (by taking into consideration OM content). T-Cu and T-Zn can be used by researchers, inspection bodies, technical assistance institutions, and farmers as safe indicators to monitor the potential for environmental contamination.

The tolerance of grapevine rootstocks to copper excess and to the use of calcium and phosphorus to mitigate its phytotoxicity.

High soil copper (Cu) concentrations in vineyards can cause phytotoxicity to grapevine rootstocks. In order to mitigate toxicity, the use of grapevine rootstock genetic variation and the application of amendments are possible strategies. The aim of this study is to assess the tolerance of grapevine rootstocks to Cu excess and whether phosphorus (P) and calcium (Ca) can reduce phytotoxicity caused by Cu. Grapevine rootstock seedlings were produced from selected stakes: Paulsen 1103 (Vitis berlandieri × Vitis rupestris); SO4 (Vitis berlandieri × Vitis riparia); IAC 572 ((Vitis Riparia × Vitis rupestris) × Vitis caribaea); and Isabel (Vitis labrusca). Seedlings were grown in nutrition solution added with the following treatments: 0.3 µM Cu (control); 60 µM Cu; 60 µM Cu and 62 mg L-1 P; 60 µM Cu and 400 mg L-1 Ca. High Cu concentration caused phytotoxicity in all rootstocks, impairing their growth and decreasing nutrient concentration and photosynthetic activity. P and Ca addition had positive effect on the photosynthetic activity of all rootstocks, although it was not enough to revert growth to levels comparable with controls. Overall, based on the results, the application of P and Ca was not efficient in mitigating Cu phytotoxicity in grapevine plants grown in solution. Isabel was the most sensitive rootstock to Cu phytotoxicity, whereas Paulsen 1103 and SO4 presented more tolerance and can be used, together with other management strategies, in contaminated vineyard areas. Therefore, careful genotype rootstock selection for use in high Cu soils is important, while Ca and P are not efficient mitigators of Cu toxicity.

Garlic (Allium sativum) feature-specific nutrient dosage based on using machine learning models.

Brazil presents large yield gaps in garlic crops partly due to nutrient mismanagement at local scale. Machine learning (ML) provides powerful tools to handle numerous combinations of yield-impacting factors that help reducing the number of assumptions about nutrient management. The aim of the current study is to customize fertilizer recommendations to reach high garlic marketable yield at local scale in a pilot study. Thus, collected 15 nitrogen (N), 24 phosphorus (P), and 27 potassium (K) field experiments conducted during the 2015 to 2017 period in Santa Catarina state, Brazil. In addition, 61 growers' observational data were collected in the same region in 2018 and 2019. The data set was split into 979 experimental and observational data for model calibration and into 45 experimental data (2016) to test ML models and compare the results to state recommendations. Random Forest (RF) was the most accurate ML to predict marketable yield after cropping system (cultivar, preceding crops), climatic indices, soil test and fertilization were included features as predictor (R2 = 0.886). Random Forest remained the most accurate ML model (R2 = 0.882) after excluding cultivar and climatic features from the prediction-making process. The model suggested the application of 200 kg N ha-1 to reach maximum marketable yield in a test site in comparison to the 300 kg N ha-1 set as state recommendation. P and K fertilization also seemed to be excessive, and it highlights the great potential to reduce production costs and environmental footprint without agronomic loss. Garlic root colonization by arbuscular mycorrhizal fungi likely contributed to P and K uptake. Well-documented data sets and machine learning models could support technology transfer, reduce costs with fertilizers and yield gaps, and sustain the Brazilian garlic production.

Physiological responses of beet and cabbage plants exposed to copper and their potential insertion in human food chain.

Copper (Cu) can be toxic to vegetables when it is absorbed and accumulated at large concentrations, a fact that increases the risk of excessive addition of this metal to the human food chain. The aims of the current study are (1) to determine the Cu concentrations that have critical toxic effects on beet and cabbage plants, and the potential of these plants to enter the human food chain, as well as (2) to assess the physiological and biochemical responses of representatives of these vegetables grown in nutrient solution presenting increasing Cu concentrations. Beet and cabbage plants were grown for 75 days in pots filled with sand added with nutrient solution presenting six Cu concentrations: 0.00, 0.52, 1.02, 1.52, 2.02 and 2.52 mg Cu L-1. Dry matter yield and Cu accumulation in different plant organs were evaluated. Photosynthetic pigment contents, lipid peroxidation levels (TBARs), superoxide dismutase (SOD) and peroxidase (POD) activity and hydrogen peroxide (H2O2) concentrations in leaves were evaluated. Critical Cu concentrations that led to toxicity in plant organs such as beetroot and cabbage head, which are often found in human diets, corresponded to 1.43 mg Cu L-1 and 1.59 mg Cu L-1, respectively. High Cu concentrations in the nutrient solution have increased Cu concentrations and accumulation in plant tissues. This outcome justified the increased POD and SOD enzyme activity in the leaves of beet and cabbage plants, respectively, and was the cause of reduced plant growth in both crops. Cabbage plants presented higher tolerance to increased Cu levels in the growing environment than beet plants. However, it is necessary being careful at the time to consume both vegetables, when they are grown in Cu-enriched environments.

Identification and phytoremediation potential of spontaneous species in vineyard soils contaminated with copper.

Copper (Cu) contents in vineyard soils due to the application of cupric fungicides cause changes in the native covering flora. Under these conditions, the surviving individuals accumulate the metal in and decrease its availability in the soil, reducing the potential toxicity to grapevine. We have identified spontaneous plant species and their phytoremediation potential from vineyards of Isabella (Vitis labrusca) on two distinct soil types (Inceptisol and Entisol) contaminated with Cu. The results demonstrated that wild species displayed higher Cu contents in the roots than in the shoot, but had low bioaccumulation potential. During summer, the plants were unable to extract and stabilize the metal, although during the winter, Lolium multiflorum, Cyperus compressus and Chrysanthemum leucanthemum demonstrated phytostabilization potential. Among the investigated species, dry matter production and Cu accumulation by Lolium multiflorum indicated that the species is effective to decrease Cu availability in the soil.

Esmeralda Peach (Prunus persica) Fruit Yield and Quality Response to Nitrogen Fertilization.

'Esmeralda' is an orange fleshed peach cultivar primarily used for juice extraction and secondarily used for the fresh fruit market. Fruit yield and quality depend on several local environmental and managerial factors, mainly on nitrogen, which must be balanced with other nutrients. Similar to other perennial crops, peach trees show carryover effects of carbohydrates and nutrients and of nutrients stored in their tissues. The aims of the present study are (i) to identify the major sources of seasonal variability in fruit yield and qu Fruit Tree Department of Federal University of Pelotas (UFPEL), Pelotas 96010610ality; and (ii) to establish the N dose and the internal nutrient balance to reach high fruit yield and quality. The experiment was conducted from 2014 to 2017 in Southern Brazil and it followed five N treatments (0, 40, 80, 120 and 160 kg N ha-1 year-1). Foliar compositions were centered log-ratio (clr) transformed in order to account for multiple nutrient interactions and allow computing distances between compositions. Based on the feature ranking, chilling hours, degree-days and rainfall were the most influential features. Machine learning models k-nearest neighbors (KNN) and stochastic gradient decent (SGD) performed well on yield and quality indices, and reached accuracy from 0.75 to 1.00. In 2014, fruit production did not respond to added N, and it indicated the carryover effects of previously stored carbohydrates and nutrients. The plant had a quadratic response (p < 0.05) to N addition in 2015 and 2016, which reached maximum yield of 80 kg N ha-1. In 2017, harvest was a failure due to the chilling hours (198 h) and the relatively small number of fruits per tree. Fruit yield and antioxidant content increased abruptly when foliar clrCu was >-5.410. The higher foliar P linearly decreased total titratable acidity and increased pulp firmness when clrP > 0.556. Foliar N concentration range was narrow at high fruit yield and quality. The present results have emphasized the need of accounting for carryover effects, nutrient interactions and local factors in order to predict peach yield and nutrient dosage.

Root system structure as a criterion for the selection of grapevine genotypes that are tolerant to excess copper and the ability of phosphorus to mitigate toxicity.

Using tolerant genotypes and the correct use of fertilizers can mitigate the negative effect of elevated Cu levels in the growing medium. In this context, the study aimed to evaluate the effects of excess Cu in the root system and the effectiveness of phosphorus (P) in minimizing the phytotoxicity of Cu in three genotypes: IAC 572 [(Vitis riparia x V. rupestris) x V. caribaea], Magnolia (V. rotundifolia) and Paulsen 1103 (V. berlandieri x V. rupestris). The plants were grown in nutrient solutions and were supplemented with the following treatments: 0.3 µM Cu (Control), 60 µM Cu (Cu) and 60 µM Cu and 62 mg L-1 P (Cu + P). Root samples were sectioned for microscopy analyses, and the shoot lengths, shoot and root dry matter, relative growth rates (RGR) and tissue nutrient contents were also evaluated. The roots of the genotypes that were cultivated with high Cu concentrations produced greater numbers of branches and larger diameters, except for Magnolia genotype that was cultivated in a Cu + P solution, which had an organization similar to the control. Excess Cu caused accumulations of phenolic compounds and decreased shoot lengths, dry matter and RGR in the genotypes. In the treatments with excess Cu, there were increases in this element in the tissues, but P decreased the metal concentrations in Magnolia roots. Therefore, Cu accumulations alter the root system development patterns, growth parameters and tissue nutrient contents in the studied genotypes. Magnolia has a higher tolerance and is also the only genotype for which the use of P has been shown to be effective.