Identification of plant leaf phosphorus content at different growth stages based on hyperspectral reflectance

Abstract Background Modern agriculture strives to sustainably manage fertilizer for both economic and environmental reasons. The monitoring of any nutritional (phosphorus, nitrogen, potassium) deficiency in growing plants is a challenge precision farming technology. A study was carried out on three species popular crops, celery ( Apium graveolens L., cv. Neon), sugar beet Beta vulgaris Tapir) strawberry Fragaria × ananassa Duchesne, Honeoye), fertilized with four different doses phosphorus (P) deliver data non-invasive detection P content. Results Data obtained via biochemical analysis the chlorophyll carotenoid contents plant material showed that strongest effect availability diverse total content compared strawberry, which affects variety leaves. measurements performed using hyperspectral imaging, several stages development, were applied supervised classification experiment. machine learning algorithm (Backpropagation Neural Network, Random Forest, Naive Bayes Support Vector Machine) developed classify from variants fertilization. lowest prediction accuracy earliest measured stage development. Statistical analyses correlations between leaf constituents, fertilization mass leaf/roots plants. Conclusions Obtained results demonstrate imaging combined artificial intelligence methods has potential non-homogenous crop levels.