PREDICTING LETTUCE CANOPY PHOTOSYNTHESIS WITH STATISTICAL AND NEURAL-NETWORK MODELS

An artificial neural network (NN) and a statistical regression model w ere developed to predict canopy photosynthetic rates (Pn) for 'Waldman 's Green' leaf lettuce (Latuca: sativa L.). All data used to develop a nd test the models were collected for crop stands grown hydroponically and under controlled-environment conditions. In the NN and regression models, canopy Pn was predicted as a function of three independent va riables: shootzone CO2 concentration (600 to 1500 mmol.mol(-1)), photo synthetic photon flux (PPF) (600 to 1100 mu mol.m(-2).s(-1)), and cano py age (10 to 20 days after planting). The models were used to determi ne the combinations of CO2 and PPF setpoints required each day to main tain maximum canopy Pn. The statistical model (a third-order polynomia l) predicted Pn more accurately than the simple NN (a three-layer, ful ly connected net). Over an 11-day validation period, average percent d ifference between predicted and actual Pn was 12.3% and 24.6% for the statistical and NN models, respectively. Both models lost considerable accuracy when used to determine relatively long-range Pn predictions (greater than or equal to 6 days into the future).