Jun Zhang

Accurate prediction of the net photosynthetic rate (Pn) is important for understanding crop responses to environmental conditions in protected cultivation. The Pn responds nonlinearly to the temperature, photosynthetic photon flux density (PPFD), and CO₂ concentration, making accurate prediction under combined environmental conditions challenging. However, these effects make it difficult for mechanistic models to precisely predict the Pn. In this study, 1800 repeated Pn records of zucchini leaves were obtained during flowering and fruiting stages and used to construct and evaluate a GA-optimized adaptive neuro-fuzzy inference system (GA-ANFIS), ANFIS, random forest (RF), and radial basis function (RBF), as well as backpropagation (BP) models. The maximum Pn values were 43.22 and 45.21 μmol·m⁻²·s⁻¹ during flowering and fruiting, respectively, at 32 and 28 °C, a PPFD of 1800 μmol·m⁻²·s⁻¹, and a CO₂ concentration of 1200 μmol·mol⁻¹. On the test set, the GA-ANFIS achieved R² values of 0.9811 and 0.9901 and RMSE values of 1.4808 and 1.1889 μmol·m⁻²·s⁻¹, respectively. It also achieved the highest R² and lowest RMSE on the additional temperature interpolation set. The test set regression slopes were 0.9876 and 1.0001, with intercepts of 0.1060 and −0.0465. Overall, the GA-ANFIS showed the best predictive performance among the five models under the evaluated conditions.

Plant photosynthetic rate prediction models have the potential to enhance production efficiency and advance intelligent control in protected agriculture. However, due to the complexity of and variability in multiple environmental factors, conventional prediction models often fail to accurately predict photosynthetic rates. We hypothesize that the prediction accuracy of a photosynthetic rate model for cucumber could be significantly improved through the application of machine learning algorithms, including support vector regression (SVR), backpropagation (BP), neural network, random forest (RF), and radial basis function (RBF) neural network. To test this hypothesis, we designed experimental treatments with varying combinations of temperature, light intensity, and CO₂ concentration and measured the photosynthetic rate (Pn) during the peak fruiting period to construct a comprehensive dataset; we then determined optimal hyperparameters for each algorithm and established and verified four prediction models, thereby identifying the optimal model. The results showed that the maximum Pn value occurred at 28 °C, 1500 µmol m⁻² s⁻¹, and 1200 µmol mol⁻¹. Among all models, the SVR model exhibited superior performance on the test set, with an R² of 0.9941 and an RMSE of 0.7802 µmol m⁻² s⁻¹. This was further demonstrated by its performance on the validation set, where it achieved the highest R² (0.96443) and the lowest errors. In conclusion, the SVR model accurately predicted the cucumber photosynthetic rate, providing a solid theoretical foundation for intelligent environmental control in protected cucumber production.