Phosphorus is essential for potato cultivation; however, its low natural availability and high fixation in the soil require efficient management strategies. In this context, rapid and non-destructive methods for estimating foliar phosphorus content are important to reduce waste and improve production efficiency. This study evaluated the use of multispectral images acquired by a Survey 3 (MAPIR) camera to estimate foliar phosphorus content in potato crops at the tuberization stage, when topdressing fertilization is typically applied. To generate variability in foliar phosphorus levels, an experiment was conducted under greenhouse conditions using a randomized complete block design with eight P₂O₅ rates (0, 50, 100, 200, 400, 800, 1,600, and 3,200 kg ha−1) and 40 replications. Spectral indices (NDVI, GNDVI, and GRVI) were analyzed, and regression models and machine learning algorithms (Random Forest, Multilayer Perceptron, and SMOreg) were applied to predict foliar phosphorus content. NDVI showed a significant inverse correlation with phosphorus content, attributed to the nutritional dilution effect. Among the evaluated methods, Random Forest showed the best performance, with a relative root mean square error of 19.01%. The results demonstrate that the integration of multispectral variables and machine learning techniques increases diagnostic accuracy, highlighting the potential of these technologies for nutritional monitoring of potato crops in precision agriculture.
Full publication URL
