Search Results (10,842)

Standard pushers for the relativistic equations of motion of a charged particle in an electromagnetic field—Boris, Vay, Higuera–Cary—do not, in general, preserve the full symplectic structure of the underlying Hamiltonian system, while high-order non-symplectic schemes such as Runge–Kutta accumulate secular error over long times. We propose a two-stage, symmetry-preserving framework (SP-PINN) for the 3+1-dimensional relativistic dynamics of a charged particle in a prescribed field, including a focused Gaussian laser pulse, that pairs a physics-informed neural network with an explicit symplectic integrator: the network learns a surrogate relativistic Hamiltonian, while the integrator—which is not itself learned—advances it. In Stage 1, an unsupervised physics-informed neural network learns the surrogate from the covariant equations of motion using a Lorentz-invariant loss that enforces the mass-shell constraint $\mathcal{H}=m{c}^2\gamma$; in Stage 2, the surrogate is advanced with an explicit symplectic map built on Tao’s extended phase space, valid for the non-separable relativistic Hamiltonian. To isolate the geometric integrator from neural-network approximation error, every benchmark figure advances the analytic relativistic Hamiltonian through Stage 2, the learned Stage-1 surrogate being assessed separately. We benchmark against the Boris pusher and Runge–Kutta on three core test problems (adding the Higuera–Cary pusher in the symplecticity diagnostic), supplemented by plane-wave, ensemble, and pulse-family studies, and we measure the first Poincaré–Cartan loop invariant directly as a quantitative diagnostic of symplecticity. The magnetic-field test illustrates the contrast between bounded and secular error growth: Runge–Kutta drifts secularly, the Boris pusher conserves the invariants to machine precision as a volume-preserving gyro-integrator, and the symplectic map keeps the error bounded for all time; on a non-integrable magnetic trap, where no exact volume-preserving rotation exists, the symplectic map alone keeps the energy error bounded. The learned surrogate is the current accuracy bottleneck—not yet competitive with the conventional pushers for the static cases—but for the demanding laser case, a vector-potential light-cone reformulation reduces this surrogate error to $(3.0\pm 0.1)\times {10}^{-4}$ (three seeds) and yields learned trajectories that remain phase-coherent over essentially the whole interaction. The framework targets laser–plasma acceleration, synchrotron-radiation modeling, and particle tracking. Full article

Solder-joint detection and localization on large, complex printed circuit boards (PCBs) remain challenging because PCB images often contain unevenly distributed features, nonuniform illumination, specular reflection, scale variation and geometric distortion. Conventional SIFT-based registration methods usually use fixed matching parameters and therefore cannot adapt well to regions with different component densities. To address this limitation, this study proposes a hardware–software integrated PCB image registration framework that combines a robotic end effector with a locally adaptive K-nearest neighbor (LAKNN) strategy and SIFT descriptors. The hardware platform provides stable image acquisition through a lifting mechanism and ring-light illumination, while the software module adjusts the neighbor-search space according to local feature density and matching confidence. Experimental results show that the proposed LAKNN method achieves 90.8% inlier-match accuracy in the ablation experiment and improves registration robustness under height, region and viewpoint variations. The proposed framework provides a practical basis for automated PCB inspection and robotic soldering alignment. Full article

For final-state quality inspection of three-dimensional stamped hairpin windings, existing studies still lack multimodal methods that integrate mechanical geometric constraints, prior-guided fusion, and decision interpretability. This study proposes a span-prior-guided explainable multimodal neural network method and develops SPIMA-Net. The final-state images were acquired at a fixed inspection station with a fixed camera position and imaging angle under a CCD vision light source. Final-state images are used as visual inputs, while geometric priors are constructed from span measurements and model-type information. A visual branch and a span branch extract image and prior features, and a span-prior-assisted gating mechanism modulates visual features to enable collaborative fusion. Experimental results show that SPIMA-Net achieves an accuracy of 98.14%, an F1-score of 96.55%, and an AUC of 0.9983 on the test set. Its nonconforming-class F1-score is improved by 10.44, 3.04, 6.27, 1.38, and 0.66 percentage points over the image-only, span-only, direct-fusion, SE-fusion, and CBAM-fusion models, respectively, while the total number of misclassifications decreases to five. Interpretability analysis shows that the model mainly focuses on span openings, end profiles, and local abnormal regions. Relative and absolute span deviations are identified as the main mechanical geometric factors affecting final-state quality classification. The proposed method provides a neuro-mechanical fusion approach that demonstrates high discriminative performance and engineering interpretability for hairpin winding quality inspection on the investigated industrial dataset. Full article

Student dropout remains a persistent challenge in higher education, with significant academic, social and institutional implications. Although machine learning (ML) models for dropout prediction have proliferated, most select input variables based on data availability rather than theory and rarely report psychometric validation of the constructs used. This study addresses both gaps by developing and validating an early warning system at a Mexican university using exclusively pre-enrollment data from more than 46,000 student records from 2014 to 2025. Following the CRISP-DM methodology, eight theoretically grounded constructs, anchored in Tinto’s integration model, Bean’s attrition model, and Cabrera et al.’s persistence model, were operationalized from institutional intake questionnaires and assessed for internal consistency using Cronbach’s alpha prior to model training. Eight supervised ML algorithms were benchmarked across distance-based (Logistic Regression, SVM, AdaBoost, ANN) and tree-based (Random Forest, XGBoost, LightGBM, CatBoost) families. A tuned and isotonically calibrated Random Forest achieved the best overall performance (recall = 0.743, F1 = 0.524, ROC-AUC = 0.734, PR-AUC = 0.478) on a strictly held-out test set that was not used at any stage of model development. The 2023–2025 cohorts, whose dropout labels were not yet observable under the institutional definition, were scored prospectively to generate operational risk profiles. SHAP analysis identified high-school GPA, parental education, and household asset indices as dominant predictors, which mapped directly onto the three theoretical frameworks. These findings demonstrate that psychometrically grounded pre-enrollment data alone can support an operationally deployable dropout detection system, enabling proactive, evidence-based retention interventions from the first day of enrollment. Full article

Rapid urbanization and unplanned land development have transformed Dhaka into one of the most densely built metropolitan areas in South Asia, leading to increased surface heat accumulation and growing pressure on urban energy systems. Numerous studies have reported a progressive rise in Dhaka’s Land Surface Temperature (LST), accompanied by a strong negative correlation between the Normalized Difference Vegetation Index (NDVI) and LST and a positive correlation between the Normalized Difference Built-Up Index (NDBI) and LST. However, spatially explicit assessments that integrate multiple geospatial proxies to characterize urban energy-intensity patterns remain limited, particularly in data-scarce cities where direct energy-consumption data are unavailable. The present study aims to develop and map a proxy-based Urban Energy Intensity Index (UEI) for Dhaka by integrating remote sensing, GIS, and AHP-MCDA techniques. Landsat 9 imagery and VIIRS nighttime light data were processed to derive NDVI, NDBI, and LST layers, while building footprints and road networks were extracted from OpenStreetMap to represent urban form. Eight environmental, built-environment, and anthropogenic indicators were standardized and weighted using the Analytic Hierarchy Process (AHP) before integration through a GIS-based weighted overlay approach. Results show that dense, impervious, and intensely illuminated built-up cores exhibit elevated LST and UEI values, while peri-urban and vegetated areas consistently display lower values, producing spatially distinct high-UEI clusters concentrated within Dhaka’s urban core. Because the index is derived from proxy indicators and was not validated against observed energy-consumption data, the findings should be interpreted as relative spatial patterns rather than direct measures of energy use or energy efficiency. These findings demonstrate the effectiveness of integrating remotely sensed and geospatial indicators to capture intra-urban variability in proxy-based urban energy intensity. The study provides a scalable and data-efficient framework for identifying priority zones for urban planning interventions and supports targeted strategies such as urban greening, surface albedo enhancement, and sustainable land-use planning to mitigate thermal stress. Full article

To address the limitations of existing approaches that rely primarily on individual operational indicators and provide limited insight into the dynamic evolution of airport operational states, this study develops a two-stage analytical framework integrating unsupervised state identification and supervised temporal classification. Using monthly operational data from seven major Japanese airports between January 2010 and March 2024, the proposed framework first applies K-means clustering to identify latent operational states based on multidimensional indicators reflecting growth dynamics, operational efficiency, and relative operational level. Three distinct states are identified: a low-activity state, a recovery state, and a rapid-rebound state. Here, the rapid-rebound state denotes a temporary operational regime characterized by exceptionally strong year-on-year growth from a comparatively depressed base, rather than the highest absolute utilization rates or 2019-relative operational level. The results reveal clear stage-specific characteristics and transition patterns, with the recovery state serving as the most persistent and relatively stable operational regime, while rapid-rebound episodes are less frequent, less stable, and often transition back to the recovery state. The supervised component subsequently evaluates whether recovery and rapid-rebound labels retrospectively identified through full-sample clustering can be distinguished using lagged operational characteristics. Six classification algorithms, including logistic regression, radial basis function support vector machine (RBF-SVM), random forest, gradient boosting, XGBoost, and LightGBM, are compared using a chronologically ordered 60/20/20 partition applied only at the supervised-classifier stage, with SMOTE applied exclusively to the training subset. Because the standardization parameters, K-means solution, and target state labels were derived from the complete 2010–2024 sample, and because several 2019-relative variables were constructed using an ex post benchmark, the reported results represent classifier-stage temporal evaluation of retrospectively identified full-sample labels rather than end-to-end out-of-sample validation or prospective real-time prediction. Under the prespecified common SMOTE-based six-model comparison, LightGBM yields the highest point estimates for macro-F1 and rapid-rebound-state recall, reaching 0.6864 and 0.5588, respectively. Given that the training subset contains only seven rapid-rebound observations, these estimates should be interpreted cautiously. An exploratory sensitivity analysis using alternative imbalance-handling strategies produces materially different point estimates, indicating that minority-state classification performance is sensitive to the selected imbalance treatment. The SHAP-based feature attribution results indicate that short-term lagged growth indicators and twelve-month 2019-relative operational-level variables contribute strongly to the fitted distinction between the recovery and rapid-rebound state labels. Although the supervised analysis is restricted to distinguishing the recovery and rapid-rebound state labels, the proposed framework provides a multidimensional approach for airport state identification, temporal evolution analysis, retrospective operational monitoring, and post-shock recovery assessment. A genuinely prospective application would require reconstructing all input variables using information available at each forecast origin and re-estimating the models accordingly. Full article

Fish mucosal barriers are sensitive interfaces between the organism and the aquatic environment and may reflect integrated tissue responses in natural populations. This study assessed the reactivity of the gill and intestinal mucosal barriers in common bream, Abramis brama, from the Ile–Balkhash Basin and Lake Alakol, Kazakhstan. A total of 50 individuals were examined using light microscopy, transmission electron microscopy, quantitative cell counting, and semi-quantitative histopathological assessment. Background hydrochemical parameters of the studied waters were within guideline values and were used as environmental context rather than as a control condition for tissue normality. Histopathological alterations were recorded in both organs. The gills showed epithelial desquamation, respiratory epithelial edema, deformation and fusion of secondary lamellae, epithelial hyperplasia, and vascular abnormalities, with a median Gill Lesion Score of 2.00 (IQR 1.86–2.29). The intestine showed epithelial sloughing, intestinal fold disruption, brush-border damage, cellular infiltration, fibrosis/collagenization, and vascular changes, with a median Intestinal Lesion Score of 2.14 (IQR 1.86–2.57). Rodlet cells were more abundant in the gills, whereas mast/eosinophilic granular cells occurred at comparable densities in both organs. These findings indicate shared but organ-specific patterns of mucosal reactivity and support paired gill–intestine analysis as an informative morphological approach for assessing wild fish populations under natural multifactorial conditions. Full article

In complex UAV aerial scenes, small object detection tasks face challenges such as extremely low pixel occupancy, strong background interference, and sparse effective features, which are further compounded by environmental factors like low illumination. Consequently, single-modality detection algorithms are prone to severe target feature loss and missed detections. Multi-modal image fusion, which complements the texture details of visible light with the thermal radiation characteristics of infrared, is considered an effective approach to overcome the limitations of single physical imaging. However, conventional fusion mechanisms often suffer from semantic gaps when processing heterogeneous data, easily introducing redundant noise and background false alarms. To further improve the accuracy and robustness of small object detection in UAV aerial scenes, this paper proposes a multi-modal detection network that integrates direction-aware multi-granularity and asymmetric context guidance, termed DMAC-Net. Specifically, a Direction-Aware Granularity Enhancement (DAGE) module is first constructed for unified backbone feature extraction, which captures local directions and contour edges of small objects in UAV aerial images with high sensitivity, and expands the receptive field through a multi-granularity mechanism, effectively suppressing false positives induced by complex backgrounds while enhancing the recall of occluded and weakly featured targets. Additionally, the Asymmetric Context Guided Fusion (ACGF) module builds a spatial mechanism via asymmetric receptive fields and performs semantic soft alignment of cross-modal features with dynamic weight assignment, effectively filtering out artifacts and clutter from cross-modal interaction. Experimental results on multiple aerial datasets, including RGBTDronePerson, AVMS and LLVIP demonstrate that the proposed method outperforms existing mainstream models in terms of overall detection accuracy and missed-detection suppression, while exhibiting strong generalization capability and stability under complex lighting transitions and multi-scale variations in UAV monitoring environments. Full article

This study investigates the forced transverse vibration of a thin rotating annular disc subjected to time-varying point forces that are fixed in space and act perpendicular to the disc surface. Earlier analytical treatments of this problem have almost always been restricted to a single support condition, most often the clamped–free disc of a hard-disk drive. The boundary conditions of the disc have not been treated as a design variable of the forced response. The contribution of this work is to remove that restriction: the same generalised Galerkin formulation is applied to clamped–clamped, clamped–free and free–clamped rotating annular discs, and the sensitivity of the forced response to the excitation parameters is compared across all three. The governing differential equation, which includes gyroscopic coupling and the membrane stresses induced by rotation, is nondimensionalised and solved by the Galerkin method with polynomial radial trial functions. The modal equations are then integrated in state-space form with light modal damping. The physical transverse response at a fixed observation point is characterised by power spectral density diagrams assembled into waterfall plots, and the corresponding steady-state harmonic responses are obtained in closed form from the frequency-domain resolvent of the same state-space model. The formulation is verified against an independent radial finite-element model for all three boundary conditions and against published rotating clamped–free natural frequencies. The central finding concerns how the excitation parameters act on the response. The excitation frequency, the radial position of a force, and the angular separation and phase of a pair of forces act as largely independent levers. The quantitative sensitivity to each lever, however, is set by the boundary conditions, as is the force placement that minimises a chosen travelling-wave family. The radial position that minimises the excitation of a chosen radial family is governed by the interior node of that mode, which lies at $r\approx 52$, 68 and 44 mm for the clamped–clamped, clamped–free and free–clamped discs, respectively, and does not in general coincide with a free edge. Angular separation, by contrast, suppresses a nodal-diameter family in a manner that is essentially boundary-condition independent. The parameter dependences are shown to be steady-state properties: the driven spectral line of the finite-duration records reproduces the resolvent solution to within $0.09$ dB. Full article

Probiotics play an important role in maintaining human gastrointestinal health and immune function, driving a rapidly expanding global market for probiotic-fortified foods. Lacticaseibacillus paracasei is one of the most widely applied probiotic strains in functional foods and dairy formulations, with well-documented health-promoting properties. For probiotic foods, authenticity requires rigorous verification for efficacy and compliance, which depends on rapid strain-specific identification. However, conventional culture-based methods are time-consuming and cannot distinguish closely related Lacticaseibacillus species, while PCR-based assays require expensive thermal cyclers and trained personnel, barring deployment in resource-limited settings. Here, we report the development and validation of a MIRA-CRISPR/Cas12a fluorescence assay for rapid, species-specific, and highly sensitive on-site detection of Lacticaseibacillus paracasei. This integrated workflow combines 8 min rapid crude DNA extraction, 30 min isothermal MIRA pre-amplification, and 20 min CRISPR/Cas12a signal amplification with naked-eye fluorescence readout under blue light excitation, and requires only miniaturized portable equipment. The assay achieved a reliable limit of detection of 100 CFU/mL in milk-matrix spiked samples, showing no cross-reactivity across 17 tested lactic acid bacteria strains. In a validation set of 48 food samples, our method demonstrated 100% concordance with the gold-standard species-specific qPCR assay. This field-deployable method is appropriate for on-site quality control in probiotic manufacturing, label compliance verification, and frontline market regulatory inspections. Full article

Microalgae biophotovoltaic (BPV) systems convert solar energy into electricity through photosynthetic electron transfer (PET) and have emerged as a promising solar-integrated bioenergy technology. However, high-density tubular arrays suffer from the “canyon effect” at low solar angles and from photoinhibition under peak irradiance (>450 W/m²), where non-photochemical quenching (NPQ) and reactive oxygen species (ROS) dissipate bioelectric potential as heat. To address this, a hysteresis-based dual-mode PID controller with hysteresis switching is proposed within an optical–mechanical–biological co-optimization framework, integrating array self-shading, nonlinear microalgal photoresponse, and tracking parasitic losses. In low-light mode, the system actively tracks the sun to minimize shading; in peak-light mode, it defocuses the incident angle to limit irradiance near the saturation threshold, mitigating the risk of photoinhibition. Structural control boundaries, including tube spacing and connecting rod length, are determined numerically. Under the nominal clear-sky design day, the defocusing mode reduces the daily exposure of the culture to irradiance above the saturation threshold (450 W/m²) from 5.28 h to 3.08 h. Numerical simulations indicate a daily net energy yield improvement of +14.9% over continuous dual-axis tracking and +6.3% over the latitude-based fixed-tilt baseline under idealized clear-sky design-day conditions. These values are simulation-derived estimates; experimental validation with a physical prototype is required before the framework can be interpreted as a validated system-level performance gain. Full article

Researchers regularly perform numerical simulations to study dam-break flooding and predict hydraulic quantities such as Water Surface Elevation (WSE). Mesh-based models, such as HEC-RAS, commonly solve Shallow Water Equations discretized on a computational mesh. As an emerging mesh-free approach for flood prediction, Smoothed Particle Hydrodynamics (SPH) typically involves solving unsteady incompressible Euler flow equations and requires the evaluation of numerical parameters controlling particle resolution, smoothing, dissipation, and time integration. This study examines how the time-stepping scheme, smoothing length, kernel function, interparticle distance, and artificial viscosity coefficient affect WSE predictions in SPH dam-break simulations. The analysis is based on three-dimensional SPH simulations of the Cleveland Dam failure in North Vancouver using DualSPHysics with Light Detection and Ranging (LiDAR)-derived topography. Sensitivity analysis is performed using variance-based Sobol’ indices to quantify the relative influences of numerical parameters on the WSE predictions. The findings reveal that the time-stepping scheme has the largest influence, with percentage differences of 0.87% and 0.63% in the average and maximum WSEs, respectively. The interparticle distance shows a minimal impact on accuracy beyond the optimal resolution of 298,188 particles, while the artificial viscosity coefficient has a negligible impact within the tested range of 0.2 to 0.3. This study suggests appropriate values for SPH numerical parameters for dam-break flooding. Full article

Ultrafast laser micro- and nanofabrication has emerged as a powerful platform for precision manufacturing due to the unique capability of femtosecond pulses to provide highly localized energy deposition and controlled laser–matter interactions. However, conventional scanning-based processing approaches remain limited by a fundamental trade-off between spatial resolution and fabrication throughput. Recent advances in ultrafast optical field engineering provide new strategies for overcoming these limitations through coordinated control of temporal, spatial, and spatiotemporal characteristics of ultrashort laser fields. This review presents recent developments in ultrafast optical field engineering for laser micro- and nanofabrication, covering programmable pulse shaping, spatiotemporal control, spatial light modulation, structured light approaches, holographic methods, and hybrid optical architectures. The operating principles of these technologies are discussed together with their influence on energy deposition, processing accuracy, scalability, and manufacturing efficiency. Particular attention is given to applications in high-throughput surface structuring, parallel microfabrication, three-dimensional processing, photonic device fabrication, and functional material modification. Different optical architectures are compared in terms of flexibility, optical efficiency, power-handling capability, and industrial applicability. The review highlights the transition from conventional single-spot processing toward adaptive, parallel, and programmable optical manufacturing systems, emphasizing integrated control of ultrafast optical fields as a key direction for future laser fabrication. Full article

Forests play an important role in timber and fiber production, carbon storage, biodiversity conservation, and various other ecosystem services, necessitating accurate and scalable inventory methods. Recent advances in remote sensing have enabled large-scale forest monitoring; however, challenges remain in extracting reliable information across varying spatial, temporal, and environmental conditions. Deep learning has emerged as a promising tool for addressing these limitations by learning complex patterns from diverse remote sensing data sources. This review synthesizes deep learning applications in forest inventory methods across three tasks: tree counting and localization, tree species identification, and tree measurement. In total, we evaluated 122 unique primary studies (37 for tree counting and localization, 57 for species identification, and 29 for tree measurement, with one study contributing to both the counting/localization and measurement tasks) spanning terrestrial, unmanned aerial vehicle (UAV), airborne, and satellite platforms, with a primary focus on optical imagery, Light Detection and Ranging (LiDAR) data, and their fusion. Across these studies, deep learning models frequently outperformed conventional machine learning and statistical baselines, with reported gains including up to 18% improvements in biomass estimation accuracy from data fusion and individual-tree species classification accuracies exceeding 90% for select architectures. However, performance differences were influenced strongly by forest structure, species complexity, sensor capability, and validation design. Counting and localization were generally more reliable in plantations than in complex natural or urban forests, while LiDAR was particularly valuable in dense, multilayer canopies. Species-identification accuracy was highest in studies with small, distinctive species sets, whereas mixed stands with many species showed lower accuracy. Only about a third of the reviewed studies (42 of 122) were externally validated on data or sites independent of model training, and reference data for tree measurement tasks were rarely based on direct destructive sampling. External validation often revealed lower performance than within-study testing, suggesting that reported accuracies may overestimate performance in new locations or conditions. Major advances are evident in the growing use of high-resolution UAV and smartphone-based imagery for tree-level analysis, the continued value of LiDAR for structural characterization, and the increasing integration of multimodal data fusion to improve detection, classification, and measurement accuracy. Persistent challenges include the limited availability of high-quality reference data, class imbalance and inconsistent species coverage, and weak model transferability across forest types, environmental conditions, and geographic regions. Future progress will likely depend on three priorities: development of larger and more standardized labeled datasets, stronger integration of structural, spectral, and phenological information, and the design of more transferable and application-oriented deep learning frameworks. Overall, this review provides a comprehensive, quantitatively grounded overview of deep learning-driven forest inventory methods and outlines future directions for improving scalability and applicability in forest monitoring and management. Full article

To address the difficulty of directly incorporating crop growth-stage information into industrial control processes and the limited adaptability of control parameters to different developmental stages in conventional greenhouse fertigation management, this study developed a vision-based growth-stage determination and PLC-based fertigation parameter invocation system for greenhouse blueberry cultivation. The system integrated greenhouse blueberry image acquisition, edge-based visual recognition, STM32-based encoding conversion, PLC control, human–machine interaction, and actuator linkage. Image samples were collected from greenhouse blueberry plants, whereas system-level linkage verification was conducted on a small greenhouse prototype platform. The edge vision module was used to output preliminary blueberry growth-stage labels, while environmental and substrate sensor data were used for sensor status verification and control safety validation. The final growth-stage label was converted by the STM32 unit into a discrete coded signal and then transmitted to the PLC. Based on a predefined stage-strategy table, the PLC invoked the corresponding target parameters and drove the irrigation, fertilizer delivery, supplemental lighting, ventilation, and shading devices for coordinated control. The image-level stage classification evaluation based on an independent test set showed that different lightweight YOLO classification models exhibited different performance levels in identifying the major growth stages of blueberry. YOLO11n-cls achieved the highest Accuracy and Macro F1-score, reaching 85.71% and 84.81%, respectively. YOLOv8n-cls achieved an Accuracy, Macro F1-score, and Macro AP of 80.95%, 81.10%, and 91.25%, respectively, showing a favorable balance between model size and recognition performance. The confusion matrix indicated that misclassifications mainly occurred between the fruit expansion stage and the ripening stage, reflecting the morphological continuity of blueberry fruit development during the transitional period. The system linkage test results showed that blueberry growth-stage labels could be output by the edge vision terminal, converted by the STM32 unit, read by the PLC, and used for stage-specific target parameter invocation. Sensor acquisition, HMI display, and actuator response were completed cooperatively. The single determination and output time of the edge terminal was 500–1000 ms, and the remote-control response delay was 0.3–1.0 s. No obvious communication interruption, command loss, or abnormal shutdown occurred during system operation. These results indicate that blueberry growth-stage recognition results can serve as input conditions for PLC parameter invocation and device-control testing on a small greenhouse prototype platform. This study did not conduct a complete closed-loop cultivation experiment under real production greenhouse conditions or establish long-term blueberry cultivation control treatments. Therefore, no quantitative conclusions are drawn regarding water and fertilizer use efficiency, fertilizer application reduction, plant physiological responses, yield, or fruit quality improvement. Full article