Cultivar-specific nutritional status of potato (Solanum tuberosum L.) crops

• Published in: PloS one Vol. 15; no. 3; p. e0230458
• Main Authors: Coulibali, Zonlehoua, Cambouris, Athyna Nancy, Parent, Serge-Étienne
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 13.03.2020; Public Library of Science (PLoS)
• Subjects: Agricultural industry; Agricultural production; Algorithms; Biology and Life Sciences; Book publishing; Chemical composition; Clustering; Computer and Information Sciences; Crop yield; Cultivars; Datasets; Diagnostic systems; Ecology and Environmental Sciences; Engineering; Environmental conditions; Environmental quality; Fertilization; Fisheries; Flowering; Flowers & plants; Food; Genetics; Learning algorithms; Leaves; Machine learning; Medicine and Health Sciences; Model accuracy; Nutrient concentrations; Nutrients; Nutritional status; Physical Sciences; Plant tissues; Potatoes; Research and Analysis Methods; Support vector machines; Vegetables; Canada; United States; Quebec; United States > US; Quebec Canada
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0230458

Gradients in the elemental composition of a potato leaf tissue (i.e. its ionome) can be linked to crop potential. Because the ionome is a function of genetics and environmental conditions, practitioners aim at fine-tuning fertilization to obtain an optimal ionome based on the needs of potato cultivars. Our objective was to assess the validity of cultivar grouping and predict potato tuber yields using foliar ionomes. The dataset comprised 3382 observations in Québec (Canada) from 1970 to 2017. The first mature leaves from top were sampled at the beginning of flowering for total N, P, K, Ca, and Mg analysis. We preprocessed nutrient concentrations (ionomes) by centering each nutrient to the geometric mean of all nutrients and to a filling value, a transformation known as row-centered log ratios (clr). A density-based clustering algorithm (dbscan) on these preprocessed ionomes failed to delineate groups of high-yield cultivars. We also used the preprocessed ionomes to assess their effects on tuber yield classes (high- and low-yields) on a cultivar basis using k-nearest neighbors, random forest and support vector machines classification algorithms. Our machine learning models returned an average accuracy of 70%, a fair diagnostic potential to detect in-season nutrient imbalance of potato cultivars using clr variables considering potential confounding factors. Optimal ionomic regions of new cultivars could be assigned to the one of the closest documented cultivar.