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.

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.

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.

Correction: Determining soil particle-size distribution from infrared spectra using machine learning predictions: Methodology and modeling.

[This corrects the article DOI: 10.1371/journal.pone.0233242.].

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.

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.

Determining soil particle-size distribution from infrared spectra using machine learning predictions: Methodology and modeling.

Accuracy of infrared (IR) models to measure soil particle-size distribution (PSD) depends on soil preparation, methodology (sedimentation, laser), settling times and relevant soil features. Compositional soil data may require log ratio (ilr) transformation to avoid numerical biases. Machine learning can relate numerous independent variables that may impact on NIR spectra to assess particle-size distribution. Our objective was to reach high IRS prediction accuracy across a large range of PSD methods and soil properties. A total of 1298 soil samples from eastern Canada were IR-scanned. Spectra were processed by Stochastic Gradient Boosting (SGB) to predict sand, silt, clay and carbon. Slope and intercept of the log-log relationships between settling time and suspension density function (SDF) (R2 = 0.84-0.92) performed similarly to NIR spectra using either ilr-transformed (R2 = 0.81-0.93) or raw percentages (R2 = 0.76-0.94). Settling times of 0.67-min and 2-h were the most accurate for NIR predictions (R2 = 0.49-0.79). The NIR prediction of sand sieving method (R2 = 0.66) was more accurate than sedimentation method(R2 = 0.53). The NIR 2X gain was less accurate (R2 = 0.69-0.92) than 4X (R2 = 0.87-0.95). The MIR (R2 = 0.45-0.80) performed better than NIR (R2 = 0.40-0.71) spectra. Adding soil carbon, reconstituted bulk density, pH, red-green-blue color, oxalate and Mehlich3 extracts returned R2 value of 0.86-0.91 for texture prediction. In addition to slope and intercept of the SDF, 4X gain, method and pre-treatment classes, soil carbon and color appeared to be promising features for routine SGB-processed NIR particle-size analysis. Machine learning methods support cost-effective soil texture NIR analysis.

Current and next-year cranberry yields predicted from local features and carryover effects.

Wisconsin and Quebec are the world leading cranberry-producing regions. Cranberries are grown in acidic, naturally low-fertility sandy beds. Cranberry fertilization is guided by general soil and tissue nutrient tests in addition to yield target and vegetative biomass. However, other factors such as cultivar, location, and carbon and nutrient storage impact cranberry nutrition and yield. The objective of this study was to customize nutrient diagnosis and fertilizer recommendation at local scale and for next-year cranberry production after accounting for local factors and carbon and nutrient carryover effects. We collected 1768 observations from on-farm surveys and fertilizer trials in Quebec and Wisconsin to elaborate a machine learning model using minimum datasets. We tested carryover effects in a 5-year Quebec fertilizer experiment established on permanent plots. Micronutrients contributed more than macronutrients to variation in tissue compositions. Random Forest model related accurately current-year berry yield to location, cultivars, climatic indices, fertilization, and tissue and soil tests as features (classification accuracy of 0.83). Comparing compositions of defective and successful tissue compositions in the Euclidean space of tissue compositions, the general across-factor diagnosis differed from the local factor-specific diagnosis. Nutrient standards elaborated in one region could hardly be transposed to another and, within the same region, from one bed to another due to site-specific characteristics. Next-year yield and nutrient adjustment could be predicted accurately from current-year yield and tissue composition and other features, with R2 value of 0.73 in regression mode and classification accuracy of 0.85. Compositional and machine learning methods proved to be effective to customize nutrient diagnosis and predict site-specific measures for nutrient management of cranberry stands. This study emphasized the need to acquire large experimental and observational datasets to capture the numerous factor combinations impacting current and next-year cranberry yields at local scale.

Conditioning Machine Learning Models to Adjust Lowbush Blueberry Crop Management to the Local Agroecosystem.

Agroecosystem conditions limit the productivity of lowbush blueberry. Our objectives were to investigate the effects on berry yield of agroecosystem and crop management variables, then to develop a recommendation system to adjust nutrient and soil management of lowbush blueberry to given local meteorological conditions. We collected 1504 observations from N-P-K fertilizer trials conducted in Quebec, Canada. The data set, that comprised soil, tissue, and meteorological data, was processed by Bayesian mixed models, machine learning, compositional data analysis, and Markov chains. Our investigative statistical models showed that meteorological indices had the greatest impact on yield. High mean temperature at flower bud opening and after fruit maturation, and total precipitation at flowering stage showed positive effects. Low mean temperature and low total precipitation before bud opening, at flowering, and by fruit maturity, as well as number of freezing days (<-5 °C) before flower bud opening, showed negative effects. Soil and tissue tests, and N-P-K fertilization showed smaller effects. Gaussian processes predicted yields from historical weather data, soil test, fertilizer dosage, and tissue test with a root-mean-square-error of 1447 kg ha-1. An in-house Markov chain algorithm optimized yields modelled by Gaussian processes from tissue test, soil test, and fertilizer dosage as conditioned to specified historical meteorological features, potentially increasing yield by a median factor of 1.5. Machine learning, compositional data analysis, and Markov chains allowed customizing nutrient management of lowbush blueberry at local scale.

Balance design for robust foliar nutrient diagnosis of "Prata" banana (Musa spp.).

The "Cavendish" and "Prata" subgroups represent respectively 47% and 24% of the world banana production. Compared to world average progressing from 10.6 to 20.6 t ha-1 between 1961 and 2016, and despite sustained domestic demand and the introduction of new cultivars, banana yield in Brazil has stagnated around 14.5 t ha-1 mainly due to nutrient and water mismanagement. "Prata" is now the dominant subgroup in N-E Brazil and is fertigated at high costs. Nutrient balances computed as isometric log-ratios (ilr) provide a comprehensive understanding of nutrient relationships in the diagnostic leaf at high yield level by combining raw concentration data. Although the most appropriate method for multivariate analysis of compositional balances may be less efficient due to non-normal data distribution and limited nutrient mobility in the plant, robustness of the nutrient balance approach could be improved using Box-Cox exponents assigned to raw foliar concentrations. Our objective was to evaluate the accuracy of nutrient balances to diagnose fertigated "Prata" orchards. The dataset comprised 609 observations on fruit yields and leaf tissue compositions collected from 2010 to 2016 in Ceará state, N-E Brazil. Raw nutrient concentration ranges were ineffective as diagnostic tool due to considerable overlapping of concentration ranges for low- and high-yielding subpopulations at cutoff yield of 40 Mg ha-1. Nutrient concentrations were combined into isometric log-ratios (ilr) and normalized by Box-Cox corrections between 0 and 1 which may also account for restricted nutrient transfer from leaf to fruit. Despite reduced ilr skewness, Box-Cox coefficients did not improve model robustness measured as the accuracy of the Cate-Nelson partition between yield and the multivariate distance across ilr values. Sensitivity was 94%, indicating that low yields are attributable primarily to nutrient imbalance. There were 148 false-positive specimens (high yield despite nutrient imbalance) likely due to suboptimal nutrition, contamination, or luxury consumption. The profitability of "Prata" orchards could be enhanced by rebalancing nutrients using ilr standards with no need for Box-Cox correction.

Long-term impact of tillage practices and phosphorus fertilization on soil phosphorus forms as determined by p nuclear magnetic resonance spectroscopy.

Conservation tillage practices have become increasingly common in recent years to reduce soil erosion, improve water conservation, and increase soil organic matter. Research suggests that conservation tillage can stratify soil test phosphorus (P), but little is known about the effects on soil organic P. This study was conducted to assess the long-term effects of tillage practices (no-till [NT] and mouldboard plowing) and P fertilization (0 and 35 kg P ha) on the distribution of P species in the soil profile. Soil samples from a long-term corn-soybean rotation experiment in Québec, Canada, were collected from three depths (0-5, 5-10, and 10-20 cm). These samples were analyzed for total P (TP), total C (TC), total N (TN), pH, and Mehlich-3 P (PM3); P forms were characterized with solution phosphorus-31 nuclear magnetic resonance spectroscopy (P-NMR). Results showed a stratification of TP, TC, TN, pH, PM3, and Mehlich-3-extractable aluminum and magnesium under NT management. The PM3 and orthophosphate concentrations were greater at the soil surface (0-5 cm) of the NT-P (soil treatment with 35 kg P ha) treatment. Organic P forms (orthophosphate monoesters, especially -IP, and nucleotides) had accumulated in the deep layer of NT treatment possibly due to preferential movement. We found evidence that the NT system and P fertilization changed the distribution of P forms along the soil profile, potentially increasing soluble inorganic P loss in surface runoff and organic P in drainage and decreasing bioavailability of inorganic and organic P in deeper soil layers.

Nitrous oxide emissions from clayey soils amended with paper sludges and biosolids of separated pig slurry.

Wastes from animal production and from the paper industry are often used as amendments to agricultural soils. Although data exist on the impacts of raw animal wastes on NO production, little is known regarding the effects of paper wastes and biosolids from treated animal waste. We measured NO emissions for two consecutive snow-free seasons (mid-May through the end of October) from poorly drained clayey soils under corn ( L.). Soils were amended with raw pig slurry (PS) or biosolids (four PS-derived and two paper sludges) and compared with soils with mineral N fertilizer (CaNHNO) or without N addition (Control). Area-based NO emissions from the mineral N fertilizer (average, 8.2 kg NO-N ha; 4.2% of applied N) were higher ( < 0.001) than emissions from the organic amendments, which ranged from 1.5 to 6.1 kg NO-N ha (-0.4 to 2.5% of applied N). The NO emissions were positively correlated with mean soil NO availability (calculated as "NO exposure"), which was highest with mineral N fertilizer. In plots treated with organic amendments (i.e., biosolids and raw PS), NO exposure was negatively correlated to the C:N ratio of the amendment. This resulted in lower NO emissions from the higher C:N ratio biosolids, especially compared with the low C:N ratio PS. Application of paper sludge or PS-derived biosolids to these fine-textured soils, therefore, reduced NO emissions compared with raw PS and/or mineral N fertilizers ( < 0.01).

The plant ionome revisited by the nutrient balance concept.

Tissue analysis is commonly used in ecology and agronomy to portray plant nutrient signatures. Nutrient concentration data, or ionomes, belongs to the compositional data class, i.e., multivariate data that are proportions of some whole, hence carrying important numerical properties. Statistics computed across raw or ordinary log-transformed nutrient data are intrinsically biased, hence possibly leading to wrong inferences. Our objective was to present a sound and robust approach based on a novel nutrient balance concept to classify plant ionomes. We analyzed leaf N, P, K, Ca, and Mg of two wild and six domesticated fruit species from Canada, Brazil, and New Zealand sampled during reproductive stages. Nutrient concentrations were (1) analyzed without transformation, (2) ordinary log-transformed as commonly but incorrectly applied in practice, (3) additive log-ratio (alr) transformed as surrogate to stoichiometric rules, and (4) converted to isometric log-ratios (ilr) arranged as sound nutrient balance variables. Raw concentration and ordinary log transformation both led to biased multivariate analysis due to redundancy between interacting nutrients. The alr- and ilr-transformed data provided unbiased discriminant analyses of plant ionomes, where wild and domesticated species formed distinct groups and the ionomes of species and cultivars were differentiated without numerical bias. The ilr nutrient balance concept is preferable to alr, because the ilr technique projects the most important interactions between nutrients into a convenient Euclidean space. This novel numerical approach allows rectifying historical biases and supervising phenotypic plasticity in plant nutrition studies.

Agri-environmental thresholds using Mehlich III soil phosphorus saturation index for vegetables in histosols.

The P concentration in Norton Creek which drains cultivated Histosols in Quebec showed median concentration exceeding up to 14 times the environmental guideline of 0.03 mg total P L(-1). The aim of this study was to develop environmental and agronomic thresholds using soil tests to provide a tool for P management in Histosols. Soil samples were collected from Histosols across Quebec (82) and in fertilizer trials (66) to calibrate soil test methods against the degree of P saturation (DPS(OX)) using the acid-oxalate method and setting alpha(m) = 0.4, and the water-extractable P (P(W)) (Sissingh, 1971). The field trials on crop response to added P were conducted with carrots (8), potatoes (11), onions (10), Chinese cabbage (7), celery (10), and lettuce (20). Relative yields were computed as yield in control without P divided by highest yield with added P. The Mehlich III (M-III) P extraction was more closely related (r(2) = 0.73) to DPS(OX) than the Bray 1 method (r(2) = 0.62) and the Florida extraction method (r(2) = 0.53). The [P/(Al+gammaFe)](M-III) ratio as index of P saturation (IPS(M-III)) was the most closely related to DPS(OX) (r(2) = 0.88) setting gamma = 5. The critical [P/(Al+5Fe)](M-III) ratio of 0.05 at DPS(OX) = 0.25 and P(W) = 9.7 mg P L(-1) was validated by an independent study from North Carolina. The soil group (low- vs. high-IPS(M-III) soils) significantly influenced crop response to added P. Critical agronomic IPS(M-III) values were found between 0.10 and 0.15. Those environmental and agronomic benchmarks are instrumental for managing the P in vegetable-grown Histosols.