Automatic Detection of Different Harvesting Stages in Lettuce Plants by Using Chlorophyll Fluorescence Kinetics and Supervised Self Organizing Maps (SOMs)

Agriculture aims at increasing production and provision of high quality products to the market. Most of the times, quality is strongly correlated with harvesting stage of each product. Specifically, lettuce qualitative characteristics and nutrients appear to vary strongly in different development stages. In 46, 60 and 70 days of growth, the plants were harvested at baby, immature and mature stage. Then, the parameters of chlorophyll fluorescence were determined in two middle leaves of 3 plants of each hybrid at different harvest stage by using chlorophyll fluorescence kinetics. The measurements revealed significant differences between harvesting stages. The fluorescence parameters were utilized as inputs for training different models of supervised Self Organizing Maps (SOMs) aiming at the prediction of harvesting stage. It was shown that the prediction of different harvesting stages is h by supervised SOMs due to non-linearity nature of the problem which is owned to the heterogeneity of the fluorescence kinetics parameters.