Machine Learning, Compositional and Fractal Models to Diagnose Soil Quality and Plant Nutrition

Parent, Léon E.; Natale, William; Brunetto, Gustavo

doi:10.5772/intechopen.98896

Cited by 3 publications

(2 citation statements)

References 82 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Brazilian national yield average of 26 Mg bulb ha -1 2 is still far below expectations. High onion productivity requires the right combination of yield impacting factors 3 that are traceable in successful onion agroecosystems. The idea of combining features and local knowledge into a global assessment of successful ecosystems 4 poses a challenge in nutrient management of agroecosystems.…”

Section: Introductionmentioning

confidence: 99%

Customized nutrient management of onion (Alium cepa) agroecosystems

Hahn

Kürtz

Paula

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

While onion cultivars, irrigation and soil and crop management practices have been given much attention in Brazil, nutrient management at growers’ scale is still challenging. Our objective was to customize the fertilization of onion crops. We attempted to adjust nutrient management to the complexity of onion cropping systems by combining ML and compositional methods. We assembled climatic, edaphic, and managerial features as well as tissue tests into a data set of 1182 observations collected across fertilizer experiments conducted over 13 years. Data were processed using machine learning methods. Fertilization (NPK) treatments as well as edaphic and managerial features that are easy to acquire by stakeholders sufficed to explain 93.5% of total variation in marketable onion yields. Customized crop response models differed from state-base fertilizer recommendations, indicating potential benefits to customize fertilizer recommendations using a median experimental site condition in southern Brazil. Foliar nutrient standards to reach > 50 Mg bulb ha− 1 differed among cultivars grown under a large range of edaphic and managerial features, supporting local nutrient diagnosis. Larger and more diversified observational and experimental data sets could be acquired to customize fertilization across more Brazilian onion agroecosystems and document successful combinations of growth-impacting features through close ethical collaboration among stakeholders.

show abstract

Section: Introductionmentioning

confidence: 99%

Customized nutrient management of onion (Alium cepa) agroecosystems

Hahn

Kürtz

Paula

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…A long-term experiment is required to associate the nutrient status of perennials measured at time t to predict the stand performance at time t + 1 and adjust the fertilization in time [21][22][23]. There is a great challenge to decipher the complexity of site-specific feature combinations between geology, geomorphology, soil, climate, micro-biology, vine biology, and human interventions to make accurate predictions of the grape yield and quality and meet the production targets [7,24,25].…”

Section: Introductionmentioning

confidence: 99%

Prediction of Nitrogen Dosage in ‘Alicante Bouschet’ Vineyards with Machine Learning Models

Brunetto

Silva

Kulmann

et al. 2022

Plants

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Accumulation of nutrients during the formation of star fruit cultivars under different irrigation regimes

Rozane

Prado

Paula

et al. 2022

Rev. Colomb. Cienc. Hortic

Self Cite

View full text Add to dashboard Cite

Nutrient accumulation during the formation of star fruit (Averrhoa carambola) trees can be affected by the water regime and by the cultivar, but the details are not yet known for this species. The aim of this study was to evaluate the nutrient uptake of two star fruit cultivars in the formation phase under two irrigation regimes. The experiment was developed with a completely randomized design, with subdivided plots, with two irrigation levels (with and without irrigation) as plots, and two star fruit cultivars as subplots ('B-10' and 'Golden Star') and seven collection times from 0 to 720 days after transplanting (DAT) into the field as sub-subplots with six replicates. Nutrient uptake was evaluated in stem and leaves, and it was possible to observe that nutrient uptake and the average accumulation rate followed the dry matter mass accumulation of star fruit trees in formation. Nutrient uptake by shoots at 720 DAT differed for the Golden Star cultivar in the rainfed regime and for the B-10 cultivar in both irrigation regimes. There was no difference and followed the sequence Ca > K > N > Mg > S > P > Mn > Fe > Zn > B > Cu, and for Golden Star cultivar in the irrigated regime, the accumulation sequence was Ca> K> N> Mg> Mn> P> S> Fe> Zn > B> Cu. The highest accumulation occurred in the irrigated regime regardless of cultivar. Golden Star cultivar accumulated, on average, larger amounts of N, P, K, Mg, S, Fe and Mn.

show abstract

Machine Learning, Compositional and Fractal Models to Diagnose Soil Quality and Plant Nutrition

Cited by 3 publications

References 82 publications

Customized nutrient management of onion (Alium cepa) agroecosystems

Customized nutrient management of onion (Alium cepa) agroecosystems

Prediction of Nitrogen Dosage in ‘Alicante Bouschet’ Vineyards with Machine Learning Models

Accumulation of nutrients during the formation of star fruit cultivars under different irrigation regimes

Contact Info

Product

Resources

About