In greenhouses, plant growth is directly influenced by internal environmental conditions, and therefore requires continuous management and proper environmental control. Inadequate environmental conditions make plants vulnerable to pests and diseases, lower yields, and cause impaired growth and development. Previous studies have explored the combination of greenhouse actuator control history with internal and external environmental data to enhance prediction accuracy, using deep learning-based models such as RNNs and LSTMs. In recent years, transformer-based models and RNN-based models have shown good performance in various domains. However, their applications for time-series forecasting in a greenhouse environment remain unexplored. Therefore, the objective of this study was to evaluate the prediction performance of temperature, relative humidity (RH), and CO2 concentration in a greenhouse after 1 and 3 h, using a transformer-based model (Autoformer), variants of two RNN models (LSTM and SegRNN), and a simple linear model (DLinear). The performance of these four models was compared to assess whether the latest state-of-the-art (SOTA) models, Autoformer and SegRNN, are as effective as DLinear and LSTM in predicting greenhouse environments. The analysis was based on four external climate data samples, three internal data samples, and six actuator data samples. Overall, DLinear and SegRNN consistently outperformed Autoformer and LSTM. Both DLinear and SegRNN performed well in general, but were not as strong in predicting CO2 concentration. SegRNN outperformed DLinear in CO2 predictions, while showing similar performance in temperature and RH prediction. The results of this study do not provide a definitive conclusion that transformer-based models, such as Autoformer, are inferior to linear-based models like DLinear or certain RNN-based models like SegRNN in predicting time series for greenhouse environments.
This study evaluated the growth performance and physiological responses of 24 Korean landrace accessions of pak choi (Brassica rapa subsp. chinensis) under polyethylene glycol (PEG)-induced drought stress to identify indicators for selecting drought-resistance genotypes. Electrolyte leakage (EL) and chlorophyll fluorescence (Fv/Fm) analyses showed that resistance accessions (IT262109(11), IT279432(12), IT293143(20)) had minimal increases in EL and maintained high Fv/Fm values under stress, indicating superior membrane stability and photosystem II activity. In contrast, sensitive accessions exhibited a sharp rise in EL and a decline in Fv/Fm to approximately 0.3 under 25% PEG treatment, reflecting severe physiological damage. Principal component analysis (PCA) biplot based on integrated growth and photosynthetic parameters differentiated resistance and sensitive groups, with PC1 representing photosynthetic efficiency versus membrane injury. Growth trait responses interaction analysis using GGE biplot of six representative accessions (three resistance, three sensitive) demonstrated that resistance genotypes had smaller positional shifts across treatments, indicating greater growth stability, while sensitive genotypes showed pronounced variability and environment-specific responses. This study provides a framework integrating growth and physiological indicators for identifying drought-resistance pak choi accessions, offering valuable implications for breeding programs aimed at climate-resilient cultivar development.
26 May 2026 in Horticultural Science and Technology
Tomato yellow leaf curl virus (TYLCV) is one of the most destructive viral diseases causing severe yield losses in tomato production worldwide. This study investigated the effects of TYLCV infection on plant growth, photosynthetic physiological responses, and yield formation in greenhouse-grown tomatoes and evaluated the applicability of physiological trait-based yield prediction models. Two large-fruited tomato cultivars widely cultivated in Korean protected horticulture systems, ‘Daphnis’ and ‘Pink Star’, were inoculated with TYLCV under greenhouse conditions, and their growth, physiological responses, and yield characteristics were compared under high- and low-temperature growing seasons. TYLCV infection significantly reduced leaf length, leaf width, and leaf area index (LAI), and decreased both flowering truss number and fruit-setting truss number, resulting in reduced total yield. Physiological analyses showed that infected plants exhibited decreases in the OJIP fluorescence rise curve and Fv/Fm values, indicating a reduced photochemical efficiency in photosystem II. In addition, A–Ci response curve analysis revealed a reduction in net photosynthetic rate, suggesting limited carbon assimilation capacity. Total yield showed significant positive correlations with maximum net photosynthetic rate (Amax), Fv/Fm, and Ci300. GGE and GT biplot analyses further indicated that yield was closely associated with photosynthetic performance and canopy development traits. A multiple regression model based on physiological traits and virus infection status explained a significant proportion of the variation in tomato yield (R2 = 0.367), indicating that TYLCV infection acts as a key limiting factor for yield reduction. These findings demonstrate that TYLCV infection restricts tomato productivity through reduced photosynthetic efficiency and altered canopy structure. Moreover, physiological trait-based yield prediction approaches may provide a useful framework for evaluating productivity under viral infection conditions and for developing data-driven crop management strategies in greenhouse tomato production systems.
12 June 2026 in Notulae Botanicae Horti Agrobotanici Cluj-Napoca
This study aimed to comprehensively evaluate the effects of LED light combinations on the germination, early growth, photosynthetic efficiency, and storage stability of okra (Abelmoschus esculentus L. Moench) in a plant factory system. Various combinations of red (R) and blue (B) light (R10, R7B3, R5B5, R3B7, and B10) were applied to analyse germination characteristics, growth parameters, the maximum quantum yield of photosystem II (Fv/Fm), as well as postharvest quality and microbial changes during storage. A higher proportion of red light significantly enhanced germination performance and early growth, with faster germination rates and improved vigour compared to blue-dominant treatments. The Fv/Fm values ranged from 0.78 to 0.84 across all treatments, indicating stable photosynthetic performance under different spectral conditions. During storage, the packaging method had a significant impact on quality maintenance; modified atmosphere packaging (MAP) reduced fresh weight loss to approximately 4.5-5.5%, compared to 8.7-10.6% under conventional packaging. In addition, microbial proliferation was markedly suppressed under MAP, with aerobic bacterial counts maintained at approximately 2.1-3.0 log CFU g⁻¹, whereas values exceeded 6.0 log CFU g⁻¹ under conventional conditions. A significant interaction between LED light quality and packaging treatment was also observed, indicating that preharvest light conditions influence postharvest quality. These findings suggest that the integrated application of optimized LED light spectra and appropriate storage technologies can simultaneously improve productivity and storage stability of okra cultivated as a leafy vegetable in plant factory systems.
This study investigated how different LED spectral compositions affect seed germination, early growth, photosynthetic efficiency, and the postharvest quality and microbiological stability of Ipomoea aquatica Forsk. cultivated in a plant factory system, aiming to propose an integrated management strategy for stable year-round production. Five LED light treatments with varying red and blue light ratios (R10, R7B3, R5B5, R3B7, and B10) were applied during cultivation. After harvest, the plants were stored under low-temperature conditions using either carton box packaging or modified atmosphere packaging (MAP) to evaluate postharvest quality and microbial changes. Germination analysis indicated that red-dominant treatments (R10 and R7B3) significantly enhanced germination percentage, rate, and uniformity. These treatments also promoted greater plant height and fresh biomass accumulation during early growth while maintaining a higher maximum quantum yield of photosystem II (Fv/Fm), indicating improved photochemical efficiency. In contrast, blue-dominant treatments led to reduced growth performance and lower Fv/Fm values. Postharvest quality and microbiological stability were more significantly affected by the packaging method than by the LED light treatment. MAP effectively minimized fresh weight loss and inhibited the growth of aerobic bacteria, Escherichia coli, total coliforms, and yeast and mold during storage. Overall, the findings demonstrate that red-centered LED spectra are optimal for enhancing early growth and physiological stability of I. aquatica, while MAP is crucial for preserving postharvest quality and microbial safety. This study underscores the synergistic potential of combining LED spectral management during cultivation with optimized packaging strategies to achieve stable year-round production and extended shelf life of I. aquatica in controlled plant factory systems.