Grape white rot is an important fungal disease that affects grapes worldwide. Recently, Coniella vitis has replaced Coniella diplodiella as the dominant pathogen causing grape white rot in China. However, its key epidemiological parameters remain undefined, hindering the development of specific disease management strategies. Thus, the effects of temperature and nutrient conditions (culture media) on the mycelial growth of C. vitis, and the combined effects of temperature and wetness duration on conidial germination were examined in this study. The results showed that the mycelial growth of C. vitis was optimal at 20°C-30°C under organic-rich nutrient conditions. On water agar, conidia germinated across a temperature range of 10°C-35°C (optimum 20°C-30°C) and required wet periods longer than 2 h. Nonlinear models described these processes with estimated optimal temperatures of 27.3°C for mycelial growth and 23.9°C for conidial germination (R² > 0.89). This study revealed fundamental differences in the responses of C. vitis to temperature and wetness duration compared with C. diplodiella, providing key information for refining existing white rot prediction models and supporting the transition from calendar-based to risk-based precision fungicide applications.

Quantitative phenotyping of pepper seedlings is important for greenhouse plug tray seedling cultivation, but it remains constrained by inefficient manual monitoring, complex greenhouse backgrounds, and growth-stage-dependent discrepancies between two-dimensional image traits and actual leaf biomass. In this study, a cascaded vision framework with stage-specific morphological correction was developed for nondestructive seedling phenotyping. The framework integrated Visual Dynamic Momentum YOLO (VDM-YOLO) for individual seedling localization and growth-stage recognition, Variance Guided Strip Ghost Gated UNet (VSG-UNet) for lightweight, high-resolution leaf segmentation, and a stage-aware correction model for leaf dry biomass estimation. In performance evaluation, VDM-YOLO achieved a mean average precision at an intersection over union threshold of 0.5 (mAP0.5) of 89.27%, improving mAP0.5 by 1.82 percentage points over YOLOv12. VSG-UNet achieved a mean intersection over union (mIoU) of 83.9% and a Dice coefficient of 81.8%, while reducing floating point operations (FLOPs) and parameters by 44.2% and 61.2%, respectively, compared with U-Net. After stage-aware calibration, the coefficient of determination (R2) between segmented area and leaf dry weight increased from 0.764 to 0.813, and the root mean square error (RMSE) decreased from 0.0210 g to 0.0190 g. These results demonstrated that the proposed framework provided a proof of concept approach based on RGB images for the nondestructive assessment of leaf area and leaf dry biomass in pepper seedlings under restricted experimental conditions.

Sponge gourd fruit browning decreases edibility and sensory quality, with adverse effects on marketability. Physiological, transcriptomic, and metabolomic approaches were combined to clarify the differences in YN-20 and Z-37 fruit browning. The degree of browning as well as the melanin, total phenol, and soluble quinone contents were higher in Z-37 than in YN-20. Similarly, polyphenol oxidase (PPO), phenylalanine ammonia-lyase (PAL), and peroxidase (POD) activities as well as the malondialdehyde content were higher in Z-37 than in YN20. Transcriptome and metabolome analyses identified 80 differentially expressed genes (DEGs) and 78 differentially accumulated metabolites (DAMs) potentially associated with sponge gourd fruit browning. An integrated analysis suggested that DEGs and DAMs related to lipid metabolism and phenylpropanoid biosynthesis contribute to sponge gourd fruit browning. Furthermore, PPO in YN-20 and Z-37 had a higher affinity for caffeic acid than for ferulic acid, with higher affinities in Z-37 than in YN-20. A potential mechanism involving key DEGs (4, 1, 1, 1, and 10 genes encoding lipoxygenase, allene oxide synthase, PAL, PPO, and POD, respectively) and DAMs (lipid peroxidation products, ferulic acid, and caffeic acid) underlying fruit browning was proposed. The study findings provide new insights into the fruit browning mechanism and serve as a theoretical foundation for the breeding of browning-resistant sponge gourd varieties.

Greenhouse microclimates exhibit substantial spatial heterogeneity. Conventional evaluations based on average measurements cannot adequately describe the environmental conditions experienced by crops. This study developed a spatial frequency analysis method to quantify long-term temperature and relative humidity heterogeneity. This method was coupled with cucumber yield and downy mildew models to evaluate the biological consequences of environmental variability. Environmental conditions in four representative greenhouse structures were monitored using distributed sensor networks under different weather conditions. The proposed method successfully identified persistent environmental hotspots. The spatial distribution of environmental heterogeneity differed among greenhouse structures, whereas solar radiation primarily controlled its intensity. Long-season monitoring data indicate that the maximum spatial variations in temperature and relative humidity within the brick-wall solar greenhouse, the assembled greenhouse, the glass greenhouse, and the plastic multi-span greenhouse reach up to 10 °C and 46%, 8.5 °C and 46%, 12 °C and 50%, and 7 °C and 32%, respectively. The assembled solar greenhouse and plastic greenhouse exhibited higher environmental uniformity, while the brick-wall solar greenhouse and glass multi-span greenhouse showed pronounced spatial gradients. Environmental heterogeneity resulted in significant within-greenhouse differences in simulated cucumber yield, with the smallest variation occurring in the assembled solar greenhouse (5.3%) and the largest in the glass multi-span greenhouse (39.2%). Disease simulations further revealed clear spatial aggregation of cucumber downy mildew risk, with the southern region of the solar greenhouse exhibiting 17–67% higher cumulative infection risk than other positions. This study establishes an integrated framework linking greenhouse environmental heterogeneity with crop productivity and disease risk, providing a practical basis for spatially differentiated precision greenhouse management and greenhouse structural optimization.

Accurate detection and counting of emergence-stage tray seedlings are essential for intelligent greenhouse nursery management. However, this task is challenging due to the tiny size, dense distribution, subtle features, and susceptibility to complex backgrounds of seedlings. In this study, an improved YOLOv11-based framework, called Tray Seedling Monitoring YOLO (TSM-YOLO), is introduced for precise greenhouse tray seedling detection and localization. TSM-YOLO incorporates a Spatial Reorganization Downsampling Convolution (SRDC) for preserving spatial detail during downsampling, a Multi-branch Perception Attention (MPA) block to strengthen local feature discrimination, and a Bidirectional Auxiliary Feature Pyramid Network (BAFPN) for effective multiscale feature fusion. Furthermore, a composite regression loss blending WIoU v3 and Normalized Wasserstein Distance (NWD) is used to stabilize the localization of small, densely packed targets. Experiments demonstrate that TSM-YOLO achieves 97.82% precision and 96.13% mAP@0.5, surpassing classic models. The model maintains high robustness under varying lighting and dense vermiculite conditions. Deployed on Jetson Xavier NX, TSM-YOLO sustains 96.41% precision and strong counting consistency. These results confirm TSM-YOLO as an effective solution for automated emergence monitoring in greenhouse nurseries.

Precise identification and accurate segmentation of disease lesions on cucumber leaves are crucial tasks in smart agriculture for early detection and effective management. Taking common foliar diseases of cucumber as an example, cucumber downy mildew, bacterial angular leaf spot and cucumber phytophthora blight are characterized by indistinct lesion boundaries and fuzzy appearance during early infection stages, poses significant challenges to traditional segmentation methods. To overcome these issues, we propose a novel semantic segmentation framework, named DTM-Unet, which effectively integrates DenseNet and Vision Transformer architectures into an enhanced U-Net model. The DenseNet backbone facilitates efficient feature reuse and propagation, capturing rich hierarchical features, while the Transformer encoder captured long-range contextual dependencies, enhancing global feature representation. Additionally, we designed multi-residual dilated convolution (MRDC) modules within skip connections to effectively expand the receptive field and capture fine-grained lesion details. The model was trained and validated on a dataset encompassing multiple cucumber leaf diseases, augmented with various image transformations to improve generalizability. Performance evaluation indicated that the DTM-Unet model achieves superior segmentation performance, attaining a Pixel Accuracy (PA) of 98.71%, Recall of 91.27%, F1-score of 86.96%, and Mean Intersection over Union (mIoU) of 87.26%. Comparative evaluations against existing segmentation models further verify its robustness and generalization ability, highlighting the potential of DTM-Unet for broader applications in intelligent crop disease diagnosis and precision agriculture management, offering valuable support for automated plant disease phenotyping and precise agricultural interventions.

To decipher the metabolic regulation of pepper fruit (Capsicum annuum L.) quality, tissue-scale matrix-assisted laser desorption/ionization mass spectrometry imaging (MALDI-MSI) was employed to systematically map 19 key metabolites across four developmental stages at a spatial resolution of 50 μm. Imaging revealed distinct spatiotemporal dynamics: capsaicinoids exhibited a localized "bimodal accumulation" in the placenta, while capsanthin precursors shifted from a uniform distribution to specific enrichment in the pericarp. Notably, a synthesis-distribution decoupling was observed in ascorbic acid metabolism, suggesting potential inter-tissue redistribution. Integration with high-performance liquid chromatography-tandem mass spectrometry (HPLC-MS/MS) for the absolute quantification of four core metabolites (n = 3) provided complementary insights, distinguishing continuous bulk accumulation from dynamic, non-linear local metabolic activity. This study constructs a tissue-scale spatial metabolomic atlas, highlighting the synergistic value of combining spatial imaging with bulk quantification to unravel metabolic heterogeneity in food matrices.

Salt stress is a critical constraint affecting the cultivation of Tunisian soft-seeded pomegranate (Punica granatum L.). To elucidate the molecular mechanisms underlying exogenous melatonin (MT)-mediated enhancement of salt tolerance in pomegranate seedlings, this study integrated physiological phenotyping and transcriptome sequencing to systematically investigate MT’s regulatory effects on antioxidant systems, photosynthetic apparatus function, osmotic adjustment, and core metabolic pathways under salt stress. The results demonstrated that 200 mM NaCl treatment induced reactive oxygen species (ROS) overaccumulation, elevating malondialdehyde (MDA) content and relative electrical conductivity (REC) by 0.43 and 0.46 fold, respectively. Concurrently, salt stress severely impaired photosynthetic performance: PSII maximum photochemical efficiency (FV/FM) decreased by 44.5%, actual photochemical efficiency (YII) and photochemical quenching (qP) were reduced, and non-photochemical quenching (NPQ) increased, indicating serious photoinhibition and energy wastage. In contrast, 400 μM MT treatment effectively mitigated oxidative damage by coordinated activation of superoxide dismutase (SOD,+14.3%), peroxidase (POD,+21.7%), and catalase (CAT,+11.7%) activities, thereby stabilizing membrane integrity. Furthermore, MT significantly alleviated photoinhibition: FV/FM increased by 39%, YII and qP rose, and NPQ decreased compared to salt-stressed plants, reflecting enhanced protection of the PSII reaction center and optimized light energy allocation. Transcriptomic analysis reveals that MT treatment is associated with alterations in the expression of key sucrose metabolism genes, including the upregulation of SUCROSE SYNTHASE (SUS) and UDP-GLUCOSE PYROPHOSPHORYLASE (UGP2), as well as the recovery of GLYCOGEN SYNTHASE (glgA) expression following salt stress inhibition. These changes suggest a potential role for MT in modulating carbon metabolic homeostasis. Additionally, MT application is linked to expression changes in genes within the Mitogen-Activated Protein Kinase (MAPK) signaling pathway. Concurrently, broad expression variations are observed in genes associated with multiple phytohormone signaling pathways. Weighted gene co-expression network analysis (WGCNA) further identifies two core gene modules: the blue module is enriched with antioxidant-related genes (e.g., LOC116212144), while the yellow module is closely associated with genes implicated in membrane stability (e.g., LOC116203737). Integrated physiological and transcriptional evidence indicates that exogenous melatonin may enhance salt tolerance in pomegranate seedlings by activating the antioxidant system, protecting photosynthetic apparatus, regulating carbon metabolism, and influencing multiple signal transduction pathways. This study provides a theoretical foundation for further elucidating the mechanistic basis of MT-mediated salt adaptation in plants.

IntroductionExisting facility environment prediction models often suffer from low accuracy, poor timeliness, and error accumulation in long-term predictions under multifactor nonlinear coupling conditions. These limitations significantly constrain the effectiveness of precise environmental regulation in agricultural facilities.MethodsTo address these challenges, this paper proposes a novel facility environment prediction model (LSTM-AT-DP) integrating Long Short-Term Memory networks with attention mechanisms and advanced data preprocessing. The model architecture employs: (1) a Data Preprocessing (DP) module combining Wavelet Threshold Denoising (WTD) for noise elimination and Sliding Window (SW) technique for feature matrix construction; (2) an LSTM core for deep temporal modeling; and (3) an Attention Mechanism (AT) for dynamic feature weighting to enhance critical temporal feature extraction.ResultsIn 24-hour prediction tests, the model achieved determination coefficients (R²) of 0.9602 (temperature), 0.9529 (humidity), and 0.9839 (radiation), representing improvements of 3.89%, 5.53%, and 2.84% respectively over baseline LSTM models. Corresponding RMSE reductions were 0.6830, 1.8759, and 12.952 for these parameters.DiscussionThe results demonstrate that the LSTM-AT-DP model significantly enhances prediction accuracy while effectively suppressing error accumulation in long-term forecasts. This advancement provides robust technical support for precise facility environment regulation, with particular improvements observed in humidity prediction. The integrated attention mechanism proves particularly effective in identifying and weighting critical temporal features across all measured environmental parameters.

Tomato is one of the highest-value fruit and vegetable crop worldwide, serving as an important source of micro-nutrients in the human diet. Understanding the spatial distribution changes of critical metabolites during fruit maturation is essential for investigating the physiological roles, nutritional value, and potential functional values of phytochemicals in tomato fruit. However, information on their spatial distribution remains limited. This study aimed to visualize the distribution differences of endogenous metabolites in tomatoes across four maturity stages (from green to red) using matrix-assisted laser desorption/ionization mass spectrometry imaging (MALDI-MSI). Relative quantification results showed that as the fruit ripened, levels of soluble sugars, amino acids and volatile organic compounds (VOCs) increased significantly at the red ripening stage, while L-hydroxysuccinic acid exhibited an opposite trend, and citric acid initially decreased, then increased. Mass spectrometry imaging revealed that soluble sugars, organic acids, and amino acids were evenly distributed throughout the fruit across all maturity stages. During maturation, nine VOCs transitioned from a widespread distribution in the flesh tissue to concentrating near the peel, suggesting that aromatic compounds predominantly localize in the fruit's outer regions at full maturity. Additionally, a colocalization phylogenetic tree was constructed based on the spatial distribution imaging of each metabolite. These findings provide a deeper understanding of the changes and distribution of phytochemicals during tomato fruit development, offering a scientific basis for breeding, utilization, and production strategies.

The tomato, a widely cultivated vegetable crop, is prized by consumers for its distinctive flavor. Fruit color and flavor are important quality characters of cherry tomatoes. In this study, HS-SPME-GC-MS was utilized to analyze the metabolomic profiles of cherry tomatoes in different colors, including pink, red, brown, and yellow. A total of 585 volatile flavor compounds were identified, with 435 being common metabolites. Terpenoids and heterocyclic compounds were found to be the dominant metabolites in cherry tomatoes. PCA and total ion current mapping effectively distinguished the seven cherry tomato varieties. Using the ROAV method, 90 key VOCs were identified. Among them, benzenemethanethiol, 2-thiophenemethanethiol, (Z)-6-nonenal, dimethyl trisulfide, (Z,Z)-3,6-nonadienal, and 5-methyl-(E)-2-hepten-4-one were found to be the primary VOCs contributing to the flavor of cherry tomatoes. A total of 270 DAMs were detected across all comparisons. The yellow and brown varieties exhibited the greatest metabolite diversity, while the brown and pink varieties showed the least variability. KEGG pathway analysis indicated that the terpenoid synthesis, alpha-linolenic acid, and phenylalanine pathways were the most significant metabolic routes influencing flavor. In conclusion, this study provides a comprehensive comparison of VOCs across cherry tomatoes of different colors and a systematic analysis of the chemical composition underlying flavor differences, ultimately identifying the main factors contributing to flavor differentiation.

Cherry tomatoes are widely appreciated for their distinctive taste and aroma. To explore the impact of low temperatures on the quality and flavor of ripe red tomatoes, this study examined changes in the volatile organic compounds (VOCs) in fruits stored at 4 °C and 25 °C using headspace-gas chromatography-ion mobility spectrometry (HS-GC-IMS). A flavor fingerprint was developed using topographic plots, identifying 75 VOCs predominantly associated with aldehydes, ketones, alcohols, esters, and other compounds such as acids, sulfides, and furans. During storage at 4 °C, the primary volatile compounds identified were 6-methyl-5-hepten-2-one, butanol, and 1-penten-3-ol. In contrast, at 25 °C, 2-hexenal, hexanal, and acetic acid were the predominant compounds. Notably, storage at 25 °C was more effective in preserving the C6 aldehydes, which are known for their fresh, green, fatty, fruity, and sweet aromas. Principal component analysis (PCA) and fingerprint similarity analysis (FSA) clearly differentiated the samples based on their storage temperature and duration, highlighting significant shifts in the flavor profile over time. Additionally, heat map clustering analysis supported the PCA results, further revealing differences and similarities among the samples. The study found that storage at 4 °C helped maintain the sensory quality, color, firmness, and soluble solids content (SSC) of the cherry tomatoes harvested at the red ripe stage. Significant correlations between fruit quality traits and certain VOCs suggest that key physicochemical indicators are closely tied to aroma compound dynamics during storage. However, the content of most VOCs decreased under refrigeration, indicating a reduction in flavor complexity at low temperatures. These findings contribute valuable insights into how storage conditions influence the flavor profile of cherry tomatoes and may guide optimization of postharvest storage protocols to balance quality retention and flavor preservation.

Sponge gourd is favored by consumers because of its nutritional and medicinal properties. However, the susceptibility of fruit browning significantly decreases sensory and nutritional quality. To explore the mechanism related to membrane lipids and energy metabolism involved in sponge gourd fruit browning, germplasm resources were evaluated in terms of fruit browning sensitivity, with Z-37 prone and YN-20 resistant to fruit browning. At 24 h, the relative electrolyte leakage, phospholipase D (PLD) and lipoxygenase (LOX) activities of Z-37 were 1.85-, 1.19-, and 1.15-times those of YN-20, respectively. Moreover, at 24 h, phosphatidic acid and lysophospholipid levels were higher in Z-37 than in YN-20. A comparison with 0 h revealed the decrease in the ratio of unsaturated fatty acid to saturated fatty acid (UFA:SFA) of Z-37 was 1.17-times that of YN-20 at 24 h. Additionally, succinate dehydrogenase (SDH), cytochrome c oxidase (CCO), H+-ATPase, and Ca2+-ATPase activities of YN-20 were 1.90-, 2.48-, 1.45-, and 1.98-times those of Z-37, respectively. Thus, increases in PLD and LOX activities likely accelerated the degradation of phospholipids [e.g., PC (16:0_18:2), PC (17:0_18:2), PE (16:1_16:0), PE (16:0_16:3), PG (16:0_17:0), PI (17:0_18:2), and PS(18:0_18:3)] in Z-37. Furthermore, the fruit cutting accelerated the decrease in energy metabolism-related enzyme activities in Z-37, leading to a significant energy deficiency and reduced membrane structural stability, which is a prerequisite for fruit browning. These results systematically revealed the mechanism underlying membrane lipids and energy metabolism involved in fruit browning, thereby laying the foundation for breeding browning-resistant sponge gourd varieties.

Facility agriculture cultivation is the main production form of the vegetable industry in the world. As an important vegetable crop, hot peppers are easily threatened by many diseases in a facility microclimate environment. Traditional disease detection methods are time-consuming and allow the disease to proliferate, so timely detection and inhibition of disease development have become the focus of global agricultural practice. This article proposed a generalizable and explainable machine learning model for hot pepper damping-off in intensive seedling production under the condition of ensuring the high accuracy of the model. Through Kalman filter smoothing, SMOTE-ENN unbalanced sample processing, feature selection and other data preprocessing methods, 19 baseline models were developed for prediction in this article. After statistical testing of the results, Bayesian Optimization algorithm was used to perform hyperparameter tuning for the best five models with performance, and the Extreme Random Trees model (ET) most suitable for this research scenario was determined. The F1-score of this model is 0.9734, and the AUC value is 0.9969 for predicting the severity of hot pepper damping-off, and the explainable analysis is carried out by SHAP (SHapley Additive exPlanations). According to the results, the hierarchical management strategies under different severities are interpreted. Combined with the front-end visualization interface deployed by the model, it is helpful for farmers to know the development trend of the disease in advance and accurately regulate the environmental factors of seedling raising, and this is of great significance for disease prevention and control and to reduce the impact of diseases on hot pepper growth and development.

Terpenoids constitute one of the most chemically diverse and functionally significant classes of plant secondary metabolites, involved in growth regulation, environmental responsiveness, and interactions with biotic factors. In fruit-bearing plants, terpenoids not only contribute to aromatic traits that affect flavor and commercial value but also serve as natural agents of defense. The biosynthesis of terpenoids proceeds through two evolutionarily conserved metabolic routes: the cytosolic mevalonate (MVA) pathway and the plastid-localized methylerythritol phosphate (MEP) pathway. At the final stage of these pathways, terpene synthases (TPSs) catalyze the formation of structurally diverse terpenoid compounds and are considered key enzymes in terpenoid biosynthesis. Recent genomic and functional studies have revealed both the expansion and diversification of TPS gene families across various horticultural species and the increasing complexity of their transcriptional regulation. This has led to growing interest in the transcriptional regulatory networks that coordinate terpenoid metabolism. Among these regulators, MYB transcription factors have emerged as central components, which can directly activate or repress the expression of TPS and other pathway genes and often function through cooperative or antagonistic interactions with other transcription factor families. Additionally, MYB factors respond to various environmental and endogenous signals such as light, hormones, and nutrient availability, positioning them as crucial regulators in adaptive terpenoid metabolic control.

This study addresses the limitations of current non-destructive techniques for assessing tomato quality, such as their high cost, strong dependence on spectroscopic instruments, and difficulty in dynamic monitoring. The study proposes an integrated tomato quality prediction model that combines a Long Short-Term Memory (LSTM)-based environmental predictor, a Gated Recurrent Unit with attention mechanism (GRU-AT) for dynamic maturity prediction, and a Deep Neural Network (DNN)-based quality evaluation module. The LSTM model demonstrated high accuracy in environmental prediction (R2 > 0.9559). The GRU-AT model excelled in color ratio prediction (R2 > 0.86), and the DNN model achieved R2 values exceeding 0.811 for lycopene (LYC), firmness (FI), and soluble solids content (SSC). Experimental results demonstrate that this approach can accurately predict multiple quality parameters using only standard RGB images. In summary, this study provides a low-cost, low-complexity solution enabling real-time, non-destructive monitoring of greenhouse tomato quality, offering a viable pathway for crop quality management in precision agriculture.

Pepper is a globally cultivated vegetable known for its distinct pungent flavor, which is derived from the presence of capsaicinoids, a class of unique secondary metabolites that accumulate specifically in pepper fruits. Since the accumulation of capsaicinoids is influenced by various factors, it is imperative to comprehend the metabolic regulatory mechanisms governing capsaicinoids production. This review offers a thorough examination of the factors that govern the metabolism of capsaicinoids in pepper fruit, with a specific focus on three primary facets: (1) the impact of genotype and developmental stage on capsaicinoids metabolism, (2) the influence of environmental factors on capsaicinoids metabolism, and (3) exogenous substances like methyl jasmonate, chlorophenoxyacetic acid, gibberellic acid, and salicylic acid regulate capsaicinoid metabolism. The findings of this study are expected to enhance comprehension of capsaicinoids metabolism and aid in the improvement of breeding and cultivation practices for high-quality pepper in the future.

The climatic parameters within greenhouse facilities, such as temperature, humidity, and light, exert significant influence on the growth and yield of crops, particularly seedlings. Therefore, it is crucial to establish an accurate predictive model to monitor and adjust the greenhouse microclimate for optimizing the greenhouse environment to the fullest extent. To precisely forecast the greenhouse microclimate and assess the suitability of nursery environments, this study focuses on greenhouse environmental factors. This study leveraged open-source APIs to acquire meteorological data, integrated a model based on Convolutional Neural Networks (CNN) and Long Short-Term Memory Networks (LSTM), and utilized the sparrow search algorithm to optimize model parameters, consequently developing a time series greenhouse microclimate prediction model. Furthermore, Squeeze-and-Excitation (SE) Networks were employed to enhance the model’s attention mechanism, enabling more accurate predictions of environmental factors within the greenhouse. The predictive results indicated that the optimized model achieved high precision in forecasting the greenhouse microclimate, with average errors of 0.540 °C, 0.936%, and 1.586 W/m2 for temperature, humidity, and solar radiation, respectively. The coefficients of determination (R2) reached 0.940, 0.951, and 0.936 for temperature, humidity, and solar radiation, respectively. In comparison to individual CNN or LSTM models, as well as the back-propagation (BP) neural network, the proposed model demonstrates a significant improvement in predictive accuracy. Moreover, this research was applied to the greenhouse nursery environment, demonstrating that the proposed model significantly enhanced the efficiency of greenhouse seedling cultivation and the quality of seedlings. Our study provided an effective approach for optimizing greenhouse environmental control and nursery environment suitability, contributing significantly to achieving sustainable and efficient agricultural production.