Facing the significant challenges posed by global population growth and urbanization, plant factories, as an efficient closed cultivation system capable of precise environmental control, have become a key direction in the development of modern agriculture. However, high energy consumption, particularly lighting (which accounts for over 50%), remains a major bottleneck limiting their large-scale application. This study systematically explored the effects of dynamic light regulation strategies on lettuce (Lactuca sativa L.) growth, physiological and biochemical indicators (such as chlorophyll, photosynthetic, and fluorescence parameters), nutritional quality, energy utilization efficiency, and post-harvest shelf life. Four different light treatments were designed: a stepwise increasing photosynthetic photon flux density (PPFD) from 160 to 340 μmol·m⁻²·s⁻¹ (T1), a constant light intensity of 250 μmol·m⁻²·s⁻¹ (T2), a three-stage strategy with high light intensity in the middle phase (T3), and a three-stage strategy with sequentially increasing light (T4). The results showed that the T4 treatment exhibited the best overall performance. Compared with the T2 treatment, the T4 treatment increased biomass by 23.4%, significantly improved the net photosynthetic rate by 50.32% at the final measurement, and increased ascorbic acid (AsA) and protein content by 33.36% and 33.19%, respectively. Additionally, this treatment showed the highest energy use efficiency. On the 30th day of treatment, the light energy use efficiency (LUE) and electrical energy use efficiency (EUE) of the T4 treatment were significantly increased, by 23.41% and 23.9%, respectively, compared with the T2 treatment. In summary, dynamic light regulation can synergistically improve crop yield, chlorophyll content, photosynthetic efficiency, nutritional quality, and energy utilization efficiency, providing a theoretical basis and solution for precise light regulation and energy consumption reduction in plant factories.

In the context of declining arable land, the development of plant architectures that maximise the use of finite resources is crucial for addressing food security. This study collected yield data, along with aboveground and root traits, from 263 cucumber varieties. Machine learning models and scenario simulations were utilised with the goal of identifying a high‐yielding cucumber architecture suitable for greenhouse cultivation. Our findings indicate that cucumber yields can be predicted using aboveground and root phenotypes, such as the position of the first female flower node, leaf width, stem diameter, and root angle, with the combination of GBDT and SVM algorithms yielding the most accurate results ( R ² = 0.6155, RMSE = 0.2601). Analysis of 157 464 phenotypic combinations revealed antagonistic interactions between robust aboveground structures and fine root systems, and synergistic interactions between slender aboveground parts and broad root systems. Yields were up to 20% higher in phenotypes that combined a compact, robust aboveground structure with a narrow yet larger‐diameter and shallower root system, reflecting additive effects rather than synergistic ones. Additionally, this study proposes a reference range for high‐yielding phenotypes. Overall, this research provides a theoretical foundation for optimising cucumber plant structures under greenhouse environments by predicting yields and investigating phenotypic interactions through modelling.

The light environment is a key factor in regulating crop growth and quality in plant factories, where both light intensity and photoperiod strongly influence photosynthetic productivity and energy consumption. This study aimed to elucidate the interactive effects of light intensity and photoperiod on the growth, photosynthetic performance, and energy-use efficiency of Pakchoi in a controlled environment, thereby optimizing lighting strategies. Here, three levels of light intensity (PPFD: 100, 175, and 250 μmol·m⁻²·s⁻¹) and four photoperiods (8, 12, 16, and 20 h·d⁻¹) were combined, resulting in twelve treatments. Plant growth parameters, chlorophyll content, gas exchange indices, CO₂ response curves, and chlorophyll fluorescence characteristics were measured, along with analyses of light-use efficiency (LUE) and electrical energy-use efficiency (EUE). The highest biomass accumulation was observed under a 20 h·d⁻¹–250 μmol·m⁻²·s⁻¹ treatment. In contrast, the optimal LUE (9.69%) and EUE (4.98%) were observed under a 20 h·d⁻¹–175 μmol·m⁻²·s⁻¹ treatment. The best photosynthetic performance (A_max 32.61 μmol·m⁻²·s⁻¹) occurred under a 16 h·d⁻¹–250 μmol·m⁻²·s⁻¹ treatment. This study integrates growth, photosynthetic physiology, and energy-use efficiency, revealing a trade-off between biomass production and energy utilization in Pakchoi cultivation. It clarifies that “moderate light intensity + long photoperiod” is the optimal strategy to balance yield and energy consumption in plant factories.