Cross-Session Reconstruction and Environmental Limitation Screening of Greenhouse Tomato Leaf Photosynthesis from Gas-Exchange Data Using a CatBoost–ExtraTrees–RBF-SVR Stacked Ensemble

Abstract

Reliable prediction and interpretation of photosynthetic rate are important for precision environmental management in greenhouse tomato production, but model stability is often limited by variable redundancy, measurement-session effects, and environmental heterogeneity. This study developed an integrated gas-exchange-data-based framework for key-factor selection, photosynthetic-rate reconstruction, cross-session validation, environmental correction, and physiology-informed limitation screening. Core predictors were first identified from high-dimensional gas-exchange variables using K-means clustering and random-forest importance analysis. A CatBoost–ExtraTrees–RBF-SVR stacked ensemble was then constructed to reconstruct the leaf photosynthetic rate from selected gas-exchange variables, and its cross-session generalization was evaluated using nested cross-validation and leave-one-file-out (LOFO) extrapolation. Environmental correction was further applied to improve cross-session comparability, and rule-based limitation screening was used to classify potential environmental constraints associated with reduced photosynthesis. The stacked model achieved an RMSE of 0.806 and an R2 of 0.9918 under nested cross-validation, and an RMSE of 0.814 and an R2 of 0.9917 under LOFO extrapolation. After environmental correction, the cross-session variability of the environmentally corrected photosynthetic indicator was reduced by 96.0%, reflecting improved cross-session comparability. Under deployable sensor inputs, performance decreased markedly (A1: RMSE = 4.578, R2 = 0.735; A2: RMSE = 4.610, R2 = 0.731), compared with the gas-exchange baseline (RMSE = 0.833, R2 = 0.991). Thus, routine greenhouse sensor models should be regarded as approximate rather than high-accuracy substitutes for the gas-exchange-based model.

Code and data availability

The paper analyzes a publicly available greenhouse tomato gas-exchange dataset (Manjarrez-Sanchez & Martinez-Carrillo, Data Brief 2020), which is the exact phenotype/sensor input data for this study's photosynthesis reconstruction analysis. The authors' own processed data and analysis scripts are only available upon请求,