Describing Lettuce Growth Using Morphological Features Combined with Nonlinear Models

The aim of this study was to describe the sigmoidal growth behaviour a lettuce canopy using three nonlinear models. Gompertz, Logistic and grey Verhulst models were established for top projected area (TPCA), perimeter (TPCP) plant height (PH), which measured by two machine vision views 3D point clouds data. Satisfactory curve fitting obtained evaluation criteria: coefficient determination (R2) mean absolute percentage error (MAPE). produced better fit TPCA TPCP, with higher R2 (RTPCA2=0.9097, RTPCP2=0.8536) lower MAPE (MAPETPCA=0.0284, MAPETPCP=0.0794) values, whereas model changes in PH (RPH2=0.8991, MAPEPH=0.0344). maximum rate beginning end points rapid stage determined calculating second third derivatives models, permitting more detailed description their behaviour. initial 1–5.5 days, lasted from 5.6 26.2 days. After 26.3 entered senescent stage. These inflections critical can be used gain understanding lettuce, thereby helping researchers or agricultural extension agents promote growth, determine optimal harvest period plan commercial production.