Accurate scientific predicting of water requirements for protected agriculture crops is essential for informed irrigation management. The Penman-Monteith model, endorsed by the Food and Agriculture Organization of the United Nations (FAO), is currently the predominant approach for estimating crop water needs. However, the complexity of its numerous parameters and the potential for empirical parameter inaccuracies pose significant challenges to precise water requirement predictions. In this study, we introduce a novel water demand prediction model for greenhouse tomato crops that leverages multi-source data fusion. We employed the ExG (Excess Green) algorithm and the maximum inter-class variance method to develop an algorithm for extracting canopy coverage from image segmentation. Subsequently, Spearman correlation analysis was utilized to select the combination of canopy coverage and environmental data, followed by the random forest feature importance ranking method to identify the most optimal feature variables. We constructed average fusion, weighted fusion, and stacking fusion models based on RandomForest, LightGBM, and CatBoost machine learning algorithms to accurately predict the water requirements of greenhouse tomato crops. The results show that the stacking model has the best prediction effect, and the error is lower than that of RandomForest, LightGBM, CatBoost, Average fusion model and Weighted fusion model. The feature combination of Tmax, Ts, and CC, filtered using Spearman and RandomForest, demonstrated the lowest prediction errors, with reductions in MSE, MAE, and RMSE of over 4%, 14%, and 3%, respectively, compared to other parameter combinations. The R² value increased by 1%, indicating enhanced reliability and generalization. This research comprehensively considered various factors, including environmental, soil, and crop growth conditions, that influence crop water requirements. By integrating image and environmental data, we developed a water requirement prediction model for greenhouse tomato crops based on the principles of decoupling and minimizing characteristic parameters, offering innovative technical support for scientific irrigation practices.

Agricultural water scarcity has become a global issue. Optimizing irrigation water quality and effectively utilizing non-conventional water resources are essential strategies to alleviate pressure on agricultural water use and achieve sustainable development. This study employed Italian lettuce as the test crop to explore the effects of magnetization treatment (M) at a magnetic field strength of 0.2 T and various irrigation water sources (T) on its growth. The following six treatments were established: fresh water irrigation (M0T1), recycled water irrigation (M0T2), saline water irrigation (M0T3), magnetized fresh water irrigation (M1T1), magnetized recycled water irrigation (M1T2), and magnetized saline water irrigation (M1T3). The results showed that the magnetization treatment increased the electrical conductivity (EC), power of hydrogen (pH), and dissolved oxygen (DO) of the three water sources compared to the non-magnetized treatment. Furthermore, magnetized irrigation with fresh water, recycled water, and saline water increased the contents of nitrogen (N), potassium (K), calcium (Ca), and magnesium (Mg) in lettuce. It also led to increases in the contents of soluble proteins (by 9.27% to 22.25%), soluble sugars (by 13.45% to 20.50%), and vitamin C (VitC) (by 4.18% to 19.33%) in lettuce. Additionally, it enhanced the above-ground fresh weight of lettuce (by 9.36% to 8.81%) and water productivity (WPc) (by 5.85% to 10.40%), while reducing water consumption. Among these treatments, magnetized fresh water irrigation was the most effective in improving quality, fresh weight, and WPc, followed by magnetized recycled water. Gene expression analysis revealed that differentially expressed genes (DEGs) were primarily enriched in metabolic pathways such as the MAPK signaling pathway—plant, phytohormone signaling, and cysteine and methionine metabolism. In summary, magnetized irrigation significantly enhanced DO levels in irrigation water, along with the fresh weight, quality, and WPc of lettuce, demonstrating its effectiveness as an efficient method for agricultural irrigation.

The online dynamic collection of irrigation and plant physiological information is crucial for the precise irrigation management of nutrient solutions and efficient crop cultivation in vegetable soilless substrate cultivation facilities. In this study, an intelligent weighing system was installed in a tomato substrate cultivation greenhouse. The monitored values from the intelligent weighing system’s pressure-type module were used to calculate irrigation start–stop times, frequency, volume, drainage volume, drainage rate, evapotranspiration, evapotranspiration rate, and stomatal conductance. In contrast, the monitored values of the suspension-type weighing module were used to calculate the amount of weight change in the plants, which supported the dynamic and quantitative characterization of substrate cultivation irrigation and crop growth based on an intelligent weighing system. The results showed that the monitoring curves of pressure and flow sensors based on the pressure-type module could accurately identify the irrigation start time and number of irrigations and calculate the irrigation volume, drainage volume, and drainage rate. The calculated irrigation amount was closely aligned with that determined by an integrated-water–fertilizer automatic control system (R² = 0.923; mean absolute error (MAE) = 0.105 mL; root-mean-square error (RMSE) = 0.132 mL). Furthermore, transpiration rate and leaf stomatal conductance were obtained through inversion, and the R², MAE, and RMSE of the extinction coefficient correction model were 0.820, 0.014 mol·m⁻²·s⁻¹, and 0.017 mol·m⁻²·s⁻¹, respectively. Compared to traditional estimation methods, the MAE and RMSE decreased by 12.5% and 15.0%, respectively. The measured values of fruit picking and leaf stripping linearly fitted with the calculated values of the suspended weighing module, and R², MAE, and RMSE were 0.958, 0.145 g, and 0.143 g, respectively. This indicated that data collection based on the suspension-type weighing module could allow for a dynamic analysis of plant weight changes and fruit yield. In summary, the intelligent weighing system could accurately analyze irrigation information and crop growth physiological indicators under the practical application conditions of facility vegetable substrate cultivation, providing technical support for the precise management of nutrient solutions.

This study investigated the effects of irrigation with a fully inorganic nutrient solution (control; NNNN) and an organic instead of an inorganic nutrient solution (OIINS) at the flowering–fruit setting (ONNN), fruit expanding (NONN), color turning (NNON), and harvest (NNNO) stages of the first spike on the type and content of tomato fruit volatiles to provide a theoretical basis for tomato aroma improvement and high-quality cultivation. Compared with the control (NNNN), the results showed that all OIINS-related treatments decreased the number of fruit volatiles and increased the relative content of common volatile compounds, characteristic effect compounds, aldehydes, and cis-3-hexenal. In particular, the relative order of performance of the OIINS-related treatments was NNNO > NNON > ONNN > NONN in terms of the relative content of characteristic compounds. For all treatments, the relative cis-3-hexenal and trans-2-hexenal percentages were 20.99–51.49% and 20.22–27.81%, respectively. Moreover, hexanal was only detected in tomato fruits under the NNNN and NNNO treatments. The effects of irrigation with OIINS on tomato fruit volatiles were related to the fruit developmental stage. At the mature stage, the organic nutrient solution was conducive to the accumulation of characteristic compounds and improved the fruit aroma quality.