Accurate prediction and precise management of greenhouse environments contribute to improving crop yield and quality. However, conventional process-based models exhibit inherent recalibration constraints due to their fixed parameterization schemes, particularly when confronting nonlinear dynamics in cross-seasonal greenhouse environments. This study presents a novel hybrid mechanistic model capable of dynamic parameter calibration for multi-season applications. These dynamic parameters in the mechanistic model were adaptively predicted by deep neural networks. The greenhouse model calibration results showed that the errors for indoor air temperature and relative humidity were RMSE = 1.6104 degrees C, 6.9379 %, MAE = 1.0463 degrees C, 4.3797 %, R2 = 0.9090, 0.8290, and PBIAS = -1.3807 %, -0.0005 %, respectively. Finally, in the absence of indoor environmental reference data, the hybrid greenhouse model with adaptive parameters was validated from September 5, 2024, to November 25, 2024. The validation involves two approaches: one using measured weather data as inputs, and the other utilizing a public weather forecast API. The validation results indicate robust model performance regardless of the input data source, including both measured weather data and weather forecast data. This study develops a robust tool for forecasting greenhouse microclimates throughout growing seasons, thereby enabling optimized environmental management.

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.

Cucumber downy mildew, caused by the obligate parasitic oomycete Pseudoperonospora cubensis [(Berkeley & M. A. Curtis) Rostovzev], is a major threat to global cucumber production. Effective disease management relies on rapid and accurate pathogen detection. However, due to the specialized parasitic nature of P. cubensis, conventional methods are often laborious, low-throughput and inadequate, necessitating the development of a new approach for high-throughput sporangia counting. To address this limitation, we developed a rapid, high-throughput flow cytometry (FCM) assay for the direct quantification of P. cubensis sporangia. The optimal staining protocol involved adding 30 mu L of 1000x diluted SYBR Green I to 500 mu L of sporangial suspension and incubating at room temperature for 20 min. The flow cytometry parameters were set to a high sample loading speed with a 30-s acquisition time. Instrumental settings included an FL1 (green fluorescence) threshold of 8 x 104 and an SSC (side scatter) threshold of 3 x 105, with low gain. Validation against hemocytometer counts revealed a strong positive correlation (r = 0.8352). The assay demonstrated high reproducibility, with relative standard deviations (RSDs) ranging from 1.96-9.84%, and a detection limit of 1-10 sporangia/mu L. Operator-dependent variability ranged from 8.85% to 18.79%. These results confirm that the established flow cytometry assay is a reliable and efficient tool for P. cubensis quantification, offering considerable potential for improving cucumber downy mildew monitoring and control strategies.

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.

Greenhouse microclimates are highly heterogeneous, yet capturing this spatial variability typically requires dense sensor networks that are impractical due to cost and maintenance. Consequently, climate management often relies on incomplete spatial data. To address this, a synchronized Digital Twin (DT) was developed to characterize greenhouse microclimate behavior by generating air temperature estimates at 39 distributed locations. A key contribution is the integration of a CFD-based DT into a standardized, scalable IoT ecosystem, enabling continuous synchronization and operational deployment beyond offline simulation. The DT utilizes a CFD model in ANSYS FLUENT coupled with a nodal energy balance model to represent thermal dynamics under real operating conditions. This virtual model is deployed within a modular IoT architecture based on the FIWARE platform and OMA NGSI standards. Through the iVeg platform, physical sensors, actuators, and CFD-derived virtual sensors are exposed via Representational State Transfer Application Programming Interface (REST API) and an interactive dashboard, ensuring seamless interaction between the physical greenhouse and its virtual counterpart. Experimental validation demonstrates satisfactory agreement between simulated and measured temperatures, with offline validation achieving Mean Absolute Errors (MAE) values between 0.74 ∘C and 1.04 ∘C (RMSE: 0.94–1.35 ∘C; NMAE: 3.55–5.28 %), and online validation achieving MAE values between 1.13 ∘C and 2.12 ∘C (RMSE: 1.45–2.35 ∘C; NMAE: 5.3–9.3 %) across all validated sensor locations and contrasting meteorological conditions. By extending spatial temperature monitoring without additional hardware, this DT generates spatially distributed temperature estimates that complement physical measurements and establishes a foundation for predictive monitoring and decision support in greenhouse climate management.

There is an increasing number of centralized vegetable productions that appear as clusters of greenhouse rows and columns. Differences in temperature distributions and ventilation rate are not well-known and quantified between these greenhouses. Very few greenhouse microclimate models consider the influence of surrounding greenhouse shading on natural ventilation and the variation caused by it on mass and heat transfer. This paper presents a three-dimensional greenhouse cluster model that covers a total area of 3 ha for an interior and exterior flow field, including 22 greenhouses, which is solved using the finite volume method in conjunction with a supercomputer. One of the major contributions is a proposed optimal mesh design methodology for large-scale greenhouse cluster models. It allows for precise control over the quality and size of the mesh elements. Results show that the simulated MAE (Mean Absolute Error) at the lower/upper vents air speed measurement points and 15 distributed temperature measurement points in a greenhouse are respectively 0.19 m s-1, 0.24 m s-1 and 1.67 degrees C. The model was also used to assess the variation of natural ventilation rate and temperature distribution that depends on greenhouse specific position inside a farm. This work contributes to refining greenhouse models and control methods, while also serving as a potential reference for both researchers and practitioners in crop yield and quality prediction.

To address the challenges in microscopic image detection of cucumber downy mildew sporangia, where extremely small target sizes and pronounced geometric deformations hinder detection performance, this study proposes a novel detection model, YOLOv11-DAFNet. First, to overcome the limitations of conventional convolutions in accurately representing edge pixels and capturing multi-directional features of sporangia due to fixed convolutional orientations, a Directional Attention Fusion Convolution (DAFConv) is designed, which effectively enhances the modeling capability for multi-directional edge features. Second, in response to the limited receptive field of the original C3k2 module and its insufficient adaptability to the multi-scale deformation of sporangia, a Multi-Dilated Residual Block (C3k2_MDRBlock) is introduced. By embedding multiple dilation rate convolution kernels into the C3k2 structure, this module strengthens the network’s ability to perceive complex shapes and multi-scale features. Finally, to reinforce the interaction and fusion between shallow and deep features, a Context-Aware Attention Fusion Module (CAFMFusion) is proposed, which integrates a context-aware mechanism with pixel attention to adaptively generate fine-grained pixel-level weights, thereby enabling precise, dynamic spatial fusion and selection between shallow and deep features. Experimental results demonstrate that YOLOv11-DAFNet achieves an mAP@0.5 of 88.2 % on the test dataset, representing a 6.9 percentage point improvement over the baseline YOLOv11n, while precision and recall are increased to 90.7 % and 85.4 %, respectively. This work provides a fast and accurate detection approach for cucumber downy mildew sporangia.

The proportion of renewable energy has increased in the context of zero-carbon targets, highlighting the need to explore its role in carbon emission reduction. This study first calculated Moran's I to assess the existence of spatial autocorrelation in carbon emissions. Next, the geographical detector method was employed to evaluate the contributions of six factors to the temporal-spatial dynamics of carbon emissions. Finally, the role of these factors in driving carbon emissions was assessed using the Spatial Durbin Model (SDM). The results indicate that carbon emissions exhibit significant spatial autocorrelation characteristics. The analysis revealed that private car ownership (q = 0.2993) emerged as the dominant driving force influencing the evolution of carbon emission patterns. Additionally, the interaction detector identified interaction links between pairs of factors as either enhanced and bivariate (EB) or enhanced and nonlinear (EN). The findings from the Spatial Durbin Model revealed an inverse U-shaped relationship between the expansion of renewable energy and carbon emission outcomes.

Traditionally, the North-South (N-S) orientation has been the predominant planting configuration in Chinese solar greenhouses. However, limitations in the longitudinal operational span dimensions have prompted a gradual transition to East-West (E-W) planting configurations in agricultural practices. This study investigated the impact of changes in the planting orientation on internal airflow, temperature, and humidity during tomato cultivation under varying crop heights and ventilation conditions, utilising computational fluid dynamics (CFD) modelling and analysis of measured data. The CFD model accurately predicted the microclimate, yielding a root mean square error of 0.88 K for air temperature and 3.02 % for humidity. Simulation results indicated that the E-W planting configuration was associated with reduced airflows and a higher number of zones characterised by elevated air temperature and reduced air relative humidity, particularly under conditions of taller crop canopies and higher outdoor wind speeds. Compared with the N-S pattern, the E-W pattern demonstrated a 59.19 % reduction in the air mass flow rate through ventilation openings, whereas the mean temperatures increased by 1.77 K in the air, 0.51 K on the surface of the north wall, and 0.98 K at the ground level, accompanied by a 7.08 % decrease in air relative humidity. Long-term seasonal monitoring confirmed that the E-W orientation provides superior thermal insulation and dehumidification, contributing to a reduced risk of pests and diseases; however, continuous crop rows obstruct ventilation, with this effect becoming more significant as crop height increases. These findings offer insights for optimising greenhouse design and planting to balance thermal and ventilation performance.

White rot, caused by the fungus Coniella diplodiella, can severely reduce grapevine yields worldwide. Currently, white rot control mainly relies on fungicides applied on a calendar basis or following hailstorms that favor disease outbreaks; however, the control achieved with this strategy is often inconsistent or otherwise unsatisfactory. Realizing more rational control requires an improved understanding of white rot epidemiology. To this end, we conducted experiments with grapevine berries of two Vitis vinifera cultivars (either injured or not before artificial inoculation with a conidial suspension of C. diplodiella) to determine the effect of temperature on the length of latency (i.e., the time between infection and onset of mature pycnidia on berries) and the production of pycnidia and conidia. Sporulation occurred between 10 and 35°C, with the optimum detected at 20°C. The latency period (LP) was shorter at 25 to 35°C than at lower temperatures; the shortest LP was 120 h at 30°C on injured berries. Affected berries produced abundant conidia at 15 to 30°C (the optimum was 20°C) for more than 2 months following inoculation. Mathematical equations were developed that fit the data, with strong associations with temperature for the LP (R 2 = 0.831) and for the production dynamics of secondary conidia (R 2 = 0.918). These equations may contribute to the development of a risk algorithm to predict infection periods, which can inform risk-based disease control strategies rather than calendar-based disease control strategies.

Sclerotinia stem rot (SSR) caused by Sclerotinia sclerotiorum (Lib.) De Bary is a devastating disease infecting hundreds of plant species. It also restricts the yield, quality, and safe production of rapeseed (Brassica napus) worldwide. However, the lack of resistance sources and genes to S. sclerotiorum has greatly restricted rapeseed SSR-resistance breeding. In this study, a previously identified GDSL motif-containing lipase gene, B. napus GDSL LIPASE-LIKE 1 (BnaC07.GLIP1), encoding a protein localized to the intercellular space, was characterized as functioning in plant immunity to S. sclerotiorum. The BnaC07.GLIP1 promoter is S. sclerotiorum-inducible and the expression of BnaC07.GLIP1 is substantially enhanced after S. sclerotiorum infection. Arabidopsis (Arabidopsis thaliana) heterologously expressing and rapeseed lines overexpressing BnaC07.GLIP1 showed enhanced resistance to S. sclerotiorum, whereas RNAi suppression and CRISPR/Cas9 knockout B. napus lines were hyper-susceptible to S. sclerotiorum. Moreover, BnaC07.GLIP1 affected the lipid composition and induced the production of phospholipid molecules, such as phosphatidylethanolamine, phosphatidylcholine, and phosphatidic acid, which were correlated with decreased levels of reactive oxygen species (ROS) and enhanced expression of defense-related genes. A B. napus bZIP44 transcription factor specifically binds the CGTCA motif of the BnaC07.GLIP1 promoter to positively regulate its expression. BnbZIP44 responded to S. sclerotiorum infection, and its heterologous expression inhibited ROS accumulation, thereby enhancing S. sclerotiorum resistance in Arabidopsis. Thus, BnaC07.GLIP1 functions downstream of BnbZIP44 and is involved in S. sclerotiorum resistance by modulating the production of phospholipid molecules and ROS homeostasis in B. napus, providing insights into the potential roles and functional mechanisms of BnaC07.GLIP1 in plant immunity and for improving rapeseed SSR disease-resistance breeding. Activation of a GDSL motif-containing lipase gene by a basic leucine zipper transcription factor changes lipid metabolism in Brassica napus in response to Sclerotinia sclerotiorum.

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.

Nitrogen (N) is an essential element for plant growth, development, and metabolism. In apple production, the excessive use of N fertilizer may cause high N stress. Whether high N stress can be alleviated by regulating melatonin supply is unclear. The effects of melatonin on root morphology, antioxidant enzyme activity and 13C and 15N accumulation in apple rootstock M9T337 treated with high N were studied by soil culture. The results showed that correctly raising the melatonin supply level is helpful to root development of M9T337 rootstock under severe N stress. Compared with HN treatment, HN+MT treatment increased root and leaf growth by 11.38%, and 28.01%, respectively. Under high N conditions, appropriately increasing melatonin level can activate antioxidant enzyme activity, reduce lipid peroxidation in roots, protect root structural integrity, promote the transport of sorbitol and sucrose to roots, and promote further degradation and utilization of sorbitol and sucrose in roots, which is conducive to the accumulation of photosynthetic products, thereby reducing the inhibitory effect of high N treatment on root growth. Based on the above research results, we found that under high N stress, melatonin significantly promotes nitrate absorption, enhances N metabolism enzyme activity, and upregulates related gene expression, and regulate N uptake and utilization in the M9T337 rootstock. These results presented a fresh notion for improving N application and preserving carbon-nitrogen balance.

Grapevine trunk diseases (GTDs) are among the most devastating grapevine diseases globally. GTDs are caused by numerous fungi belonging to different taxa, which release spores into the vineyard and infect wood tissue, mainly through wounds caused by viticultural operations. The timing of operations to avoid infection is critical concerning the periodicity of GTD spores in vineyards, and many studies have been conducted in different grape-growing areas worldwide. However, these studies provide conflicting and fragmented information. To synthesize current knowledge, we conducted a systematic literature review, extracted quantitative data from published papers, and used these data to identify trends and knowledge gaps that need to be addressed in future studies. Our database included 26 papers covering 247 studies and 3,529 spore sampling records concerning a total of 29 fungal taxa responsible for Botryosphaeria dieback (BD), Esca complex (EC), and Eutypa dieback (ED). We found a clear seasonality in the presence and abundance of BD spores, with a peak from fall to spring, more in the northern hemisphere than in the southern hemisphere, but not for EC and ED. Spores of these fungi were present throughout the growing season in both hemispheres, possibly because of higher variability in spore types, sporulation conditions, and spore release mechanisms in EC and ED fungi than in BD. Our analysis has limitations because of knowledge gaps and data availability for some fungi (e.g., basidiomycetes, which cause EC). These limitations are discussed to facilitate further research.

Peanut leaf spot is a worldwide disease whose prevalence poses a major threat to peanut yield and quality, and accurate prediction models are urgently needed for timely disease management. In this study, we proposed a novel peanut leaf spot prediction method based on an improved long short-term memory (LSTM) model and multi-year meteorological data combined with disease survey records. Our method employed a combination of convolutional neural networks (CNNs) and LSTMs to capture spatial–temporal patterns from the data and improve the model’s ability to recognize dynamic features of the disease. In addition, we introduced a Squeeze-and-Excitation (SE) Network attention mechanism module to enhance model performance by focusing on key features. Through several hyper-parameter optimization adjustments, we identified a peanut leaf spot disease condition index prediction model with a learning rate of 0.001, a number of cycles (Epoch) of 800, and an optimizer of Adma. The results showed that the integrated model demonstrated excellent prediction ability, obtaining an RMSE of 0.063 and an R2 of 0.951, which reduced the RMSE by 0.253 and 0.204, and raised the R2 by 0.155 and 0.122, respectively, compared to the single CNN and LSTM. Predicting the occurrence and severity of peanut leaf spot disease based on the meteorological conditions and neural networks is feasible and valuable to help growers make accurate management decisions and reduce disease impacts through optimal fungicide application timing.

Grapevine trunk diseases are caused by a complex of fungi that belong to different taxa, which produce different spore types and have different spore dispersal mechanisms. It is commonly accepted that rainfall plays a key role in spore dispersal, but there is conflicting information in the literature on the relationship between rain and spore trapping in aerobiology studies. We conducted a systematic literature review, extracted quantitative data from published papers, and used the pooled data for Bayesian analysis of the effect of rain on spore trapping. We selected 17 papers covering 95 studies and 8,778 trapping periods, concerning a total of 26 fungal taxa causing Botryosphaeria dieback (BD), Esca complex (EC), and Eutypa dieback (ED). Results confirmed the role of rain in the spore dispersal of these fungi but revealed differences among the different fungi. Rain was a good predictor of spore trapping for ED (AUROC = 0.820) and BD (0.766) but not for the ascomycetes involved in EC (0.569) and not for the only basidiomycetes, Fomitiporella viticola, studied as for spore discharge (AUROC not significant). Prediction of spore trapping was more accurate for negative prognosis than for positive prognosis; a rain cutoff of ≥0.2 mm provided an overall accuracy of ≥0.61 for correct prognoses. Spores trapped in rainless periods accounted for only <10% of the total spores. Our analysis had some drawbacks, which were mainly caused by knowledge gaps and limited data availability; these drawbacks are discussed to facilitate further research.

This study develops an IoT-based labor productivity monitoring and measurement system (iLPMMS) in the context of intralogistics in aviation maintenance, repair, and overhaul (MRO). The system utilizes Internet of Things (IoT) technology to enable real-time monitoring of employee work performance through the integration of smart devices. Additionally, this study designs an evaluation system that measures labor productivity from multiple perspectives in an IoT-based environment. Finally, a case study validates the practical application value of the IoT-based labor productivity monitoring and measurement system in the context of internal logistics in aviation maintenance, highlighting its significance in improving operational efficiency and employee performance.

White rot, caused by the fungus Coniella diplodiella, is an important but poorly studied disease that mainly affects grapevine clusters. White rot control typically involves the repeated application of fungicides, which may be unjustified in some cases given that the key period of berry susceptibility to infection remains unclear and controversial. In this study, germination of C. diplodiella conidia and mycelium growth were investigated on water agar (conidial germination only) and artificial media similar to berry juice at five growth stages from pea-sized to berries ripe for harvest. On water agar, conidia germinated from 10 degrees C to 35 degrees C (with an optimum of 20-30 degrees C) with >2 h of moisture incubation. Both conidial germination and mycelial growth were higher on agar similar to berry juice at v & eacute;raison to berry softening than at other stages, with the lowest values detected for the ripe berries. The berries were also artificially inoculated with conidia at the different growth stages, showing that grape clusters were susceptible to infection for a long period, albeit with varying degrees of susceptibility at different stages. This implies that effective disease control requires interventions from early berry development, whenever weather conditions are conducive to infection. Further development of a predictive model accounting for weather conditions and berry susceptibility dynamics would facilitate the dynamic estimation of the disease risk during the grapevine-growing season and contribute to a risk-based application of fungicides for white rot control.