Search Results (6,197)

The integration of Selective Laser Melting (SLM) into high-end manufacturing necessitates robust machine-condition monitoring and subsystem fault classification to navigate the intricate coupling and dynamic transients inherent in these systems. Current diagnostic frameworks often struggle to decouple high-dimensional state variables or track their underlying temporal evolution. To overcome these bottlenecks, this paper develops a spatiotemporal deep learning architecture by coupling Convolutional Neural Networks (CNNs) with Long Short-Term Memory (LSTM) units. This hybrid approach leverages CNNs to distill multi-dimensional spatial features from subsystem sensor arrays, while LSTMs interpret the sequential dependencies critical for identifying systemic drifts. The proposed framework was validated using an extensive industrial dataset comprising over 310,000 temporal samples across seven critical SLM subsystems, including optical, cooling, and energy units. We systematically investigated three data-handling strategies—feature weighting, balancing, and distribution-based synthesis—to optimize the model’s sensitivity to rare-event anomalies. Benchmarking across six architectural variants reveals that a specific CNN × 3 + LSTM × 1 configuration yields superior diagnostic fidelity, achieving a classification accuracy of 98.81%. Visualization of the feature space confirms high inter-class separability, demonstrating the model’s ability to isolate faults within complex manufacturing cycles. This research offers a scalable paradigm for the intelligent monitoring of SLM equipment and provides a technical benchmark for equipment health management and predictive maintenance in advanced additive manufacturing. Full article

Qinghai Province shoulders the heavy responsibility of serving as China’s ecological security barrier. In the process of implementing the “ecological priority” strategy, the green development of grassland animal husbandry in Qinghai Province plays an especially important driving role. To systematically reveal the temporal and spatial evolution characteristics and core driving mechanism of Green Total Factor Productivity (GTFP) and provide a decision-making basis for the green transformation and high-quality development of regional animal husbandry, this paper, based on relevant data from 2010 to 2024 in Qinghai Province, constructs a measurement and influencing factor index system for the GTFP of grassland animal husbandry. Then, it conducts a systematic analysis of the temporal evolution and spatial differentiation characteristics of the GTFP of grassland animal husbandry in Qinghai Province using methods such as trend surface analysis and standard deviation ellipse. Subsequently, the influencing factors are discussed through the geographic detector model. The research findings are as follows: (1) During the study period, the GTFP of grassland animal husbandry in Qinghai Province shows an overall upward trend. Spatially, it presents a regional pattern of “strong in the north and stable in the south,” with the migration center moving towards the northeast and the distribution becoming more concentrated. (2) The level of fiscal support for agriculture, accessibility of transportation, the degree of environmental governance and the degree of digitalization play core driving roles in the process of GTFP climbing in grassland animal husbandry. (3) Interaction analysis shows that the explanatory power of any two influencing factors in the study area is higher than that of a single factor, and the interaction between the level of fiscal support for agriculture and the degree of environmental governance is the most significant. Therefore, the key to improving the GTFP of grassland animal husbandry in Qinghai Province lies in the coordinated allocation and linkage of financial support for agriculture and environmental governance. At the same time, this study can provide reference value for the green transformation and high-quality development of plateau grassland animal husbandry. Full article

The accurate and explainable prediction of carbon emissions is crucial for the efficient operation of hybrid and electrified transportation systems and their integration with energy grids. An Explainable Spatio-Temporal Graph Neural Network (EST-GNN) is proposed for highly precise CO₂ emission forecasting using Lévy Flight-guided Optuna optimization. By modelling vehicles and their operational characteristics as nodes in a dynamic graph, the proposed framework can jointly learn timing and spatial correlations while sustaining interpretability. The accuracy of the EST-GNN model is compared with models based on one-hot encoded features, SMOTE-enhanced datasets, and ensemble regressors. Using a real-world dataset of 7385 vehicle registrations with 12 predictive features experiments are conducted. When applied the EST-GNN model outperformed all baseline and traditional models achieving the highest reliability (R² = 0.98754) while solving competitive error metrics (RMSE = 6.55, MAE = 2.556). There is strong indication that reasonable machine learning (ML) models can be used accurately to confirm their suitability for resource-prevented and real-time applications, while predictable ML techniques have relatively low reliability. The optimal solution ensures scalability, robustness, and independence of the deployment environment. The distribution analysis of best performing models develops the ability of EST-GNN, which accounts for the largest proportion of best results across evaluation metrics. To achieve superior predictive accuracy, graph-based learning, explainability, and advanced hyperparameter optimization are combined. EST-GNN provides a powerful tool for analyzing fleet emission levels, making energy-aware decisions, and planning sustainable transportation, while ML models continue to be a useful complement for deployment states with high computation costs and quick responses. Full article

Accurate measurement of ocean wave parameters is paramount for offshore engineering design and marine environmental monitoring. Distributed pressure sensing technology provides a robust data foundation for analyzing the spatio-temporal characteristics of wave fields through synchronized observations at multiple stations. However, multi-sensor data exhibit high-dimensional spatio-temporal coupling, posing significant challenges for traditional single-point signal processing methods in capturing the topological associations between measurement sites. To address these limitations, this study develops a framework for spatio-temporal feature modeling and wave height reconstruction based on Graph Neural Networks (GNNs). The proposed framework integrates the spatial configuration of sensor arrays with graph-theoretic topological representations. By fusing geometric distances and signal correlations, an adaptive adjacency matrix is constructed to establish a dynamically adjustable graph structure. On the feature extraction level, a spatio-temporal fusion method combining multi-scale graph convolutions and gated temporal modeling is proposed. The experimental results obtained on the Blancs Sablons Bay multi-sensor dataset demonstrate that the proposed method significantly outperforms traditional approaches, achieving lower prediction errors and validating the effectiveness of graph-structured modeling in distributed wave sensing. Full article

Background/Objectives: Visuomotor interception requires aligning action with the future state of moving targets under sensory and motor delays. This constraint provides a tractable framework to examine how predictive and feedback-driven processes interact. This narrative review evaluates theoretical and empirical accounts of interception, with emphasis on how prediction and online control are integrated across behavioral and neural levels. Methods: We conducted a narrative synthesis of behavioral, eye-tracking, computational, and neurophysiological studies on visuomotor interception. Literature was identified through searches of PubMed, Web of Science, and Google Scholar using search terms including “visuomotor interception,” “predictive motor control,” “eye–hand coordination,” “time-to-contact,” “sensorimotor delay,” and related combinations. Studies published between 1986 and 2026 were considered, with emphasis on peer-reviewed empirical and theoretical work. Preprints were included only when directly relevant and are identified as such. The review compares internal model, ecological, and hybrid frameworks, and organizes evidence around spatial (“where”) and temporal (“when”) components of control. Results: Across paradigms, interception behavior is not well accounted for by purely predictive or reactive mechanisms. Instead, trajectories reflect a continuous interaction between anticipatory guidance and online correction. Spatial and temporal components show partial dissociation across tasks and manipulations. Available evidence supports the involvement of distributed circuits, including parietal, frontal, cerebellar, and subcortical systems, while indicating that eye movements play an active role in both information sampling and motor planning. Conclusions: Interception is best understood as the product of interacting biological, environmental, and learned constraints. Similar behavioral signatures can arise from distinct mechanisms, arguing against a unitary account. Progress requires integrating behavioral analyses with model-based and neural approaches to dissociate underlying computations. Full article

Permeability anisotropy, which is widely present in natural soil deposits, plays an important role in controlling groundwater flow patterns and ground deformation during deep excavation dewatering. However, isotropic assumptions are still commonly adopted in engineering practice, making it difficult to accurately capture realistic subsurface hydraulic conditions. In this study, a deep foundation pit of a metro station in Jinan, China, is taken as a case study. A three-dimensional excavation–dewatering model incorporating permeability anisotropy is established using PLAXIS 3D to systematically investigate the influence of the permeability ratio (Kx/Kz) ranging from 0.1 to 10 on the seepage field evolution, dewatering influence radius, ground surface settlement, and consolidation time history. The results indicate that increasing permeability anisotropy promotes a fundamental transition of the seepage regime from vertically concentrated recharge to laterally dominated radial flow. Correspondingly, the dewatering influence radius exhibits a pronounced non-monotonic response to Kx/Kz, decreasing significantly with increasing permeability ratio and reaching a minimum at approximately Kx/Kz ≈ 5, followed by a slight rebound. Meanwhile, surface settlement profiles evolve from a localized concentration pattern to a widely distributed form as permeability anisotropy increases, accompanied by a remarkable outward expansion of the settlement influence zone. Both the magnitude and spatial distribution of settlement show high sensitivity to variations in permeability anisotropy. Based on these findings, a three-stage conceptual seepage structure model accounting for permeability anisotropy is proposed, characterized by vertically dominated flow, a transitional competition regime, and horizontally dominated flow. The staged evolution of seepage structures is shown to govern the non-monotonic variation in the dewatering influence radius and the spatial–temporal response of ground settlement. The results indicate a dual-scale influence mechanism of permeability anisotropy on dewatering-induced hydro-mechanical behavior, providing a theoretical basis for refined dewatering design and environmental impact assessment in deep excavation projects. Full article

Traditional financial early warning models often rely on the independent and identically distributed (IID) assumption, failing to adequately capture cross-sectional spatial contagion effects and temporal dynamic mutations, and are susceptible to the over-smoothing problem when processing highly imbalanced graph networks. To address these limitations, this study proposes a micro-manifold-based identity-preserving spatiotemporal graph neural network framework (Micro-STAGNN). In the spatial dimension, an identity-preserving graph convolutional operator (IP-GCN) is constructed. By hard-coding a self-preservation coefficient ($\mathsf{\lambda }=0.8$), it quantifies peer risk spillover while mitigating feature dilution, ensuring the transmission of heterogeneous default signals. In the temporal dimension, Long Short-Term Memory networks are cascaded with a temporal attention mechanism to capture the nonlinear temporal inflection points that trigger financial distress. The empirical study utilizes a sample of China’s A-share market from 2015 to 2025, evaluating the model using an Out-of-Time Validation protocol and Focal Loss. Results indicate that under a highly imbalanced distribution with a positive-to-negative sample ratio of approximately 1:50, Micro-STAGNN achieves an OOT ROC-AUC of 0.9095, a minority class default recall of 89%, and reduces the missed detection rate to 11%, outperforming traditional nonlinear cross-sectional models such as XGBoost. Furthermore, temporal attention weights provide explainable support for the early warning results. Full article

As a critical link between regional economic development and ecological security, understanding the dynamics of water retention is essential for sustainable water resource management in the Huaihe River Economic Belt. This study explores the spatio-temporal evolution and spatial explanatory factors of water retention across five temporal snapshots (2003, 2008, 2013, 2018, and 2023). Based on the InVEST model, we assessed water retention capacity at both grid and spatial development levels, thereby obtaining the retention characteristics of different land-use types and their responses to land-use transitions. Furthermore, a parameter-optimized geographical detector was employed to quantify the relative contributions of climatic-environmental and social-economic factors to the spatial variance of the modeled water retention index. Results indicate that the total water retention capacity exhibited significant interannual fluctuations, with the net capacity in 2023 being lower than the initial level in 2003. Retention values displayed obvious spatial heterogeneity, with high levels concentrated in the southwest and north and low levels distributed in the central area, closely mirroring precipitation distribution. While forest land exhibited the strongest unit water retention capacity, cropland contributed the most to the total volume (50.49%) due to its predominant areal proportion (73.92%). Notably, the conversion of forest to cropland was spatially associated with the most substantial loss in the modeled retention capacity. Soil saturated hydraulic conductivity and land-use type were identified as the dominant factors explaining the spatial variance of water retention. These findings underscore the methodological utility of coupling the InVEST model with a parameter-optimized geographical detector. For practical ecosystem management, the results suggest that spatial planning policies should strictly limit the conversion of ecological lands to agricultural use and prioritize targeted soil hydrological improvements in the central plains to secure long-term water resources. Full article

Accurate rainfall information is essential for rainfall–runoff modeling in monsoon-influenced basins, where pronounced spatial variability and limited gauge coverage introduce significant uncertainty. Satellite precipitation products provide spatially continuous estimates but are affected by systematic biases, and improvements in statistical rainfall accuracy do not necessarily translate into hydrologically consistent model forcing. This study interpreted satellite rainfall bias correction through a rainfall–runoff framework in the Phetchaburi River Basin, Thailand, using the DWCM-AgWU hydrological model. Simulations were driven by gauge observations and multiple satellite-based rainfall products (GSMaP, CMORPH, CHIRPS, and PERSIANN-CCS), with bias correction applied using Linear Scaling and Quantile Mapping under rainfall-specific calibration. Results showed that bias correction significantly modified rainfall characteristics in distinct ways. Linear Scaling primarily preserved temporal and spatial structure while adjusting rainfall magnitude, whereas Quantile Mapping improved the distributional representation of rainfall intensities. These differences propagated through hydrological processes, leading to systematic variations in runoff responses across multiple metrics, including water balance consistency, peak magnitude, and timing errors. This suggests that each method performs differently depending on the aspect of system response. Rather than identifying a universally optimal method, the findings highlight trade-offs in how rainfall correction strategies influence hydrological system response. Runoff behavior is interpreted as a process-level indicator of rainfall representation, emphasizing that hydrological consistency depends not only on rainfall accuracy but also on its interaction with model structure. These results suggest a process-oriented perspective for interpreting the role of satellite rainfall products in regulated and monsoon-affected basins. Full article

Characterizing multiscale fracture networks in shale gas reservoirs remains challenging, while the limited applicability of conventional continuum-based models and insufficient multi-objective coordination often lead to low efficiency in development optimization. To address these issues, this study proposes a production history matching and multi-objective collaborative optimization framework for shale gas horizontal wells based on an equivalent fractal fracture (EFF) model. By integrating fractal theory with intelligent optimization techniques, a multiscale equivalent fractal permeability tensor is constructed, forming a hybrid machine-learning framework that combines physics-based fractal constraints with data-driven learning for efficient representation of complex fracture networks. Microseismic event clouds were converted into continuous fracture-density and fractal-geometry descriptors through denoising, temporal alignment, and spatial interpolation, and these descriptors were mapped to the equivalent fractal fracture model to dynamically update key flow parameters for history matching and parameter inversion. On this basis, a multi-objective collaborative optimization strategy is developed to achieve simultaneous time-varying fracture characterization and dynamic regulation of development parameters. Comparative results indicate that the EFF-based approach yields a production prediction error of 6.8%, slightly higher than the 4.2% obtained using discrete fracture network (DFN) models, while requiring only one-eighteenth of the computational time. Using the net present value (NPV) as the unified objective function, constraints are imposed on bottom-hole flowing pressure, flowback rate and system switching time for optimization. With the optimized pressure drop being more uniform and the gas saturation distribution being more balanced, it is verified that “EFF + NPV” can achieve the coordinated optimization of “production capacity—decline—cost” and enhance the development efficiency. Full article

As a crucial national ecological barrier, China’s Southern Collective Forest Region (SCFR) plays an essential role in maintaining regional ecological security and promoting sustainable development. Understanding the mechanisms driving the evolution of its ecosystem service value (ESV) is of great significance. Based on county-level data from 2000 to 2023, this study integrated the equivalent factor method, spatial autocorrelation analysis, the XGBoost-SHAP model, geographically and temporally weighted regression (GTWR), and partial least squares structural equation modeling (PLS-SEM) to examine the spatio-temporal evolution patterns and driving mechanisms of ESV in the SCFR. The results showed that ESV in the SCFR exhibited an overall downward trend, with a cumulative loss of 1973.77 × 10⁸ CNY. This was primarily due to marked reductions in hydrological and climate regulation services. The spatial distribution of ESV exhibited a significant heterogeneity—higher in the southwestern and southeastern mountainous regions, and lower in the northern plains and coastal zones, with the center of gravity shifting first to the northeast and then to the southwest. Local spatial autocorrelation revealed relatively stable “High–High” and “Low–Low” clustering characteristics, where high-value clusters were consistently distributed in core forest zones, while low-value clusters overlapped highly with urban agglomerations. Socio-economic factors exerted a significantly stronger influence on ESV than natural factors. Population density (POP), land use intensity (LUI), and gross domestic product (GDP) were identified as the dominant drivers, exhibiting distinct non-linear threshold effects and significant spatio-temporal heterogeneity. PLS-SEM analysis further quantified LUI as the dominant direct inhibitory pathway on ESV, highlighting urbanization’s indirect negative effect mediated through intensified LUI. Meanwhile, terrain effects were confirmed to positively influence ESV indirectly by constraining LUI and modulating local climate. The analytical framework of “threshold identification–spatio-temporal heterogeneity–causal pathway analysis” proposed in this study elucidated the complex driving mechanisms of ESV evolution, providing valuable guidance for ecological restoration evaluation and differentiated environmental governance. Full article

Accurately identifying medium- and low-yield farmlands (MLYF) and diagnosing their constraints are essential for targeted improvement of productivity and national food security. However, traditional evaluation is usually limited by coarse spatial resolution and high labor costs, and a methodological gap remains between large-scale MLYF classification and system constraints diagnosis. To address the current methodological gaps, this study developed a comprehensive framework to determine the spatial distribution of MLYF in northern China and clarify their key constraints. The framework combined the Spatio-Temporal Random Forest (STRF) algorithm with vegetation indices (VIs), climate, and soil data to delineate MLYF and uses interpretable machine learning to diagnose major constraints. The model showed high explanatory power and ensured the reliability of attribution results. The results showed that MLYF exhibited obvious spatial heterogeneity, accounting for 48.66% of the total cultivated land in the study area. These MLYF are primarily concentrated in the northwestern Loess Plateau (LP), the central Along the Great Wall (ATGW) region, and the peripheries of the Huang-Huai-Hai (HHH) Plain. In addition to spatial classification, our analysis revealed significant differences in constraint mechanisms: soil structural, nutrient, and salinization constraints predominantly restrict productivity in the HHH Plain, whereas water stress and soil erosion are the primary drivers of yield gaps in the LP and ATGW regions. These findings provide new data and insights for understanding the spatial heterogeneity of farmland quality in typical dryland agricultural regions in northern China, and offer a scientific basis for targeted land improvement and regional agricultural sustainability. Full article

Water age reflects water sources, storage, and pathways, and regulates the solute retention and dissolution associated with biogeochemical processes, highlighting its hydrological and ecological importance. However, accurate water age estimation in tracer-aided models depends heavily on the quality and spatio-temporal resolution of precipitation isotopic signals. This study investigates how distributed rainfall δ²H signals affect the simulation of young water fraction (F_yw) via the Storage Age Selection (SAS) model in topographically complex subtropical mountain catchments. Eight precipitation δ²H scenarios were generated using two temporal approaches (stepwise and sinewave) and four spatial interpolation methods: (1) raw data, (2) reversed effective recharge elevation method (rERE), (3) linear regression with elevation (ER), and (4) regression-kriging (RK). Later on, the time-variant SAS model was calibrated against observed stream water δ²H collected from the year 2022 to the year 2024. Results show that the SAS model consistently produced similar F_yw estimates for catchments (8%~40%) across all eight scenarios, demonstrating strong robustness to input uncertainty and validating the dominant role of catchment characteristics in regulating water age. The combined stepwise temporal and rERE spatial approach provided better agreement with observed stream δ²H, particularly in the eastern, steeper catchments, yielding superior model efficiency along with better constrained uncertainty. This study highlights the sensitivity of age-tracking models to precipitation isotopic inputs and provides practical guidance for selecting an interpolation strategy in data-limited mountainous environments. Full article

Trajectory planning in dynamic multi-vehicle interaction environments faces three critical challenges, including the difficulty of quantifying spatial risk distributions, the complexity of characterizing behavioral uncertainty arising from the multimodal maneuvers of surrounding vehicles, and the challenge of simultaneously optimizing multiple competing objectives such as safety, efficiency, comfort, and energy consumption. To address these challenges, this paper proposes an Improved Driving Risk Field-based Multi-objective Trajectory Optimization (IDRF-MTO) method. First, a joint spatiotemporal social attention mechanism achieves unified modeling of spatial interactions, temporal dependencies, and spatiotemporal coupling, combined with a lateral–longitudinal intent strategy for multimodal trajectory prediction. Second, an improved dynamic risk field model is constructed comprising three components: a vehicle risk field that incorporates spatial orientation and motion direction factors for anisotropic risk representation, along with a collision tendency factor that converts objective risk into effective risk; a predicted trajectory risk field that achieves anticipatory quantification of future risk from surrounding vehicles through confidence-weighted fusion; and a driving environment risk field that encapsulates road geometry, static obstacles, and environmental conditions. Finally, a multi-objective cost function embedding risk field gradients is formulated, and multi-objective coordinated optimization is realized through a three-dimensional spatiotemporal situation graph with adaptive safety sampling. Simulation results demonstrate that the proposed method enhances safety while simultaneously improving comfort and efficiency and reducing energy consumption, exhibiting excellent planning performance in complex dynamic environments. Full article

Accurately predicting the temperature field of turbine blades is of great significance for evaluating the thermal reliability and service life of high-temperature components in aero-engines. However, due to the high computational cost of numerical simulations and the limitations imposed by complex geometric structures and harsh operating environments, experimental measurements can usually only obtain sparse sensor data, making the acquisition of complete temperature distributions still challenging. Therefore, reconstructing the complete temperature field under sparse measurement conditions has become a key research issue in turbine thermal analysis. To address this problem, this paper proposes an attention-enhanced CNN–LSTM framework for reconstructing transient turbine blade temperature fields from sparse data. The model combines the spatial feature extraction capability of Convolutional Neural Networks (CNNs) with the time-series modeling capability of Long Short-Term Memory networks (LSTM). An SE channel attention module is introduced in the CNN feature extraction stage to achieve adaptive recalibration of channel features, and a temporal attention mechanism is incorporated after the LSTM layer to highlight key transient thermal features. A multi-condition temperature field dataset was constructed by conducting Computational Fluid Dynamics (CFD) simulations on low-pressure turbine guide vanes, and the model was experimentally validated through thermal shock tests. The results show that the proposed model can accurately reconstruct the spatial distribution and transient evolution of the turbine blade temperature field under sparse measurement conditions. Under different operating conditions, the predicted temperature fields are highly consistent with the CFD results, with the maximum Reconstruction error remaining below 19 °C. Error distribution analysis indicates that the model has stable Reconstruction performance and good generalization ability. Full article