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.

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.

Morfogênese de plantas de alho in vitro: papel dos reguladores de crescimento na indução e desenvolvimento de bulbos / In vitro morphogenesis of garlic plants: The role of growth regulators in bulb induction and development

Protocolos eficientes de crescimento de ápices caulinares de alho (Allium sativum L.) e posterior bulbificação in vitro são importantes para limpeza clonal e manutenção da fidelidade genética. O trabalho teve como objetivo avaliar os efeitos de tipos e concentrações de reguladores de crescimento sobre a morfogênese de plantas de alho in vitro. Ápices caulinares com até dois primórdios foram excisados de bulbilhos de alho da cv. 'Jonas' e submetidos ao cultivo in vitro em meio de cultura suplementado de ácido indolacético (0; 1,07; 2,69 e 5,37µM), ácido indolbutírico (0; 0,49; 0,98 e 2,46µM), ácido naftalenoacético (0; 1,07; 2,69 e 5,37µM), ácido jasmônico (0; 1,0; 5,0 e 10,0µM) e ácido abscísico (0; 0,38; 1,89; e 3,78µM). A concentração de 1,07µM de ácido naftalenoacético aplicado ao meio de cultura promoveu incrementos na maioria das variáveis analisadas. O ácido jasmônico induziu a formação de bulbos de alho in vitro, embora tenha apresentado performance inferior ao verificado com o uso de ANA. Por outro lado, a adição de ácido abscísico no meio de cultura inibiu o crescimento de plantas, porém, não impediu a formação de bulbos, sobretudo em concentrações reduzidas. De um modo geral, as variáveis número de bulbos e porcentagem de bulbificação diminuiram com o uso de concentrações elevadas dos reguladores de crescimento testados. Entre os reguladores de crescimento de plantas, o ANA apresenta maior efeito na morfogênese in vitro de plantas de alho, entretanto, o ácido jasmônico e o ABA também apresentam potencial para induzir a formação de bulbos de alho in vitro como o ANA.

Efficient protocols for garlic (Allium sativum L.) shoot tips growth and later in vitro bulbing are significant for pathogen removal and maintenance of genetic fidelity. The objective of this study was to assess the effects of different types and concentrations of growth regulators on in vitro morphogenesis of garlic plants. Shoot meristems with up to two primordial were excised from garlic bulbils (cv. 'Jonas') and cultivated in vitro in culture media supplemented with indoleacetic acid (0; 1,07; 2,69 e 5,37µM), indolbutyric acid (0; 0,49; 0,98 e 2,46µM), naphthaleneacetic acid (0; 1,07; 2,69 e 5,37µM), and abscisic acid (0; 0,38; 1,89; e 3,78µM). The concentration of 1,07µM indoleacetic acid applied to the culture medium promoted increases in most variables analyzed. Jasmonic acid induced formation of garlic bulbs in vitro, although it showed lower performance than that verified with the use of NAA. On the other hand, addition of abscisic acid in culture media inhibited plant growth. However, it did not impede the formation of bulbs, especially when in reduced concentrations. Generally speaking, variables such as number of bulbs and rate of bulbing decreased with the use of high concentrations of the assessed growth regulators. Among plant growth regulators, NAA showed a stronger effect on in vitro morphogenesis of garlic plants. Nonetheless, jasmonic acid and ABA also showed potential to induce formation of garlic bulbs in vitro such as NAA.