Abstract
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.
Highlights
Brazil is the fourth largest producer of banana (Musa spp.) in the world, and ranks fifth in harvested area [1]
We hypothesized that (1) machine learning (ML) models could accurately predict yield from soil tests, tissue tests and local factors, and (2) local diagnoses at the plot scale, where factors interact in a unique manner, differ from regional diagnoses, where nutrient standards are averaged across factors
Compositional systems are defined explicitly by soil and tissue tests that may be arranged into balances to facilitate interpretations of the results in terms of a physiological system or for management purposes
Summary
Brazil is the fourth largest producer of banana (Musa spp.) in the world, and ranks fifth in harvested area [1]. The main banana subgroups in Brazil are “Prata” (AAB), that dominates in the north and the northeast, and “Cavendish” (AAA), dominant in the south and the southeast. In 2018, the Brazilian production was 6.75 × 106 Mg on 449 × 103 ha, averaging 15.0 Mg ha−1 yr−1. The average banana yield of the top ten banana producing countries reached 44.8 to 65.5 Mg ha−1 yr−1. While the productivity of banana orchards nearly doubled globally over the past 50 years from 11.7 to. 20.2 Mg ha−1 yr−1 , that of the Brazilian orchards stagnated around 15.0 Mg ha−1 yr−1.
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call