Search Results (997)

Cropland and rural settlements are core components of rural human–environment systems, and their coordinated development is crucial for regional sustainability, particularly in China’s major agricultural production regions. Taking the Huang-Huai-Hai region as the study area, this study systematically investigates the spatiotemporal evolution of cropland and its coupling relationship with rural settlements using land use data from 1990 to 2020. Grid-based analysis and multiple spatial modeling methods were employed. The results show that: (1) From 1990 to 2020, the cropland in the region decreased by a net total of 21,021.94 km², with annual dynamic degrees ranging from −0.13% to −0.28%. Cropland conversion to other land uses far exceeded conversion from others, with construction land being the primary destination. Among these, rural settlements and urban construction land accounted for 43.75% and 55.58% of the total cropland loss, respectively. (2) The spatial distribution of cropland exhibited a distinct pattern of “hot in the center and south, cold in the periphery and north” (Moran’s I = 0.232, p < 0.001), indicating significant positive spatial autocorrelation. Hot spot areas clustered in the North China Plain and the Huang-Huai Plain, while cold spot areas were distributed in the Yanshan–Taihang mountains and the hilly regions of the Shandong Peninsula, clearly controlled by topography. (3) Cropland change exhibited stage-specific characteristics. The pattern was relatively stable during 1990–2000. During 2000–2010, cropland conversion to other uses intensified, with high-value conversion areas concentrated around urban agglomerations. In the 2010–2020 period, these high-value conversion areas diffused from the core plain areas to urban fringe zones. (4) The spatial coupling between cropland and rural settlements was predominantly characterized by the Moderately Coordinated Type (MCT), accounting for 48.38–58.44% of the area. However, the proportion of Rural Settlement-Dominant Type (RC) increased from 15.51% to 21.58%, indicating a trend toward intensifying human–environment conflicts. Overall, the Huang-Huai-Hai region experienced significant cropland changes. While its spatial pattern remains relatively stable, the coupling relationship between cropland and rural settlements is deteriorating, posing challenges to regional food security and rural sustainable development. Full article

Accurate air pollutant concentration prediction is crucial for public health and sustainable urban development. Existing methods predominantly rely on single-modal data, resulting in inadequate representation of pollutant spatiotemporal evolution, poor prediction accuracy, and limited generalization capabilities. To address these challenges, this research proposes a novel PM_2.5 prediction framework termed MFD-DF that integrates ground-station time series and satellite remote sensing images. In feature extraction, learnable decomposition and deformable convolution are introduced, and a Cross-Modal Slot Attention module explicitly decomposes features to resolve information blurring. Subsequently, a dynamic cross-modal alignment mechanism is designed alongside a learnable Time-Expansion Network (TEN) to ensure fine-grained interaction. Furthermore, a local-global attention feature fusion mechanism is proposed to optimize data integration efficacy. Experimental results demonstrate that in single-step PM_2.5 prediction tasks, the proposed MFD-DF achieves significant improvements of approximately 10–20% in MAE, RMSE, and MAPE compared to state-of-the-art baselines. In multi-step PM_2.5 prediction, it effectively alleviates the error accumulation problem in long-sequence forecasting, demonstrating superior robustness and accuracy. Full article

Sandy coastlines are dynamic geomorphological units supporting dense human populations and intensive economic activities. However, their evolution is increasingly dominated by anthropogenic modification rather than natural processes. This study investigates shoreline evolution along the western Liaodong Bay coast, China, where extensive anthropogenic engineering has potentially altered natural dynamics. A 30-year satellite-derived shoreline (SDS) analysis of 23 sandy beaches (Xingcheng–Suizhong, 1995–2024) was conducted using the CoastSeg framework and DSAS statistical methods across three sub-periods (1995–2005, 2005–2015, 2015–2024). Shoreline change rates ranged from −1.35 to +2.12 m/yr; 11 beaches (47.8%) exhibited net erosion and 12 (52.2%) net accretion or stability, with marked spatial heterogeneity within individual beaches. This complex spatio-temporal pattern shows the strongest spatial correspondence with the non-uniform distribution of anthropogenic structures—including ports, breakwaters, and land reclamation—which generate an “engineering proximity effect” that may fragment natural beach continuity and contribute to a regional alternating erosion–accretion mosaic pattern, though direct mechanistic verification awaits future hydrodynamic modeling. Shoreline evolution along the western Liaodong Bay coast has entered a stage of “multi-layered anthropogenic control,” requiring frameworks that integrate multi-scale, multi-process coupling mechanisms and transcend traditional regional-averaging approaches. These findings provide critical insights for spatially differentiated management of engineering-intensive sandy coasts. Full article

The integration of the digital and real economies is a pivotal engine driving the development of new, quality productive forces. Tourism ecological governance is the concrete manifestation of the green dimension of new-quality productive forces in the cultural and tourism sector, as well as being a path for converting ecological value to drive regional sustainable development. The relationship and mechanisms between digital–real integration and tourism ecological governance are critical issues requiring urgent breakthroughs. However, existing research primarily explores the economic factors influencing tourism ecology and has yet to systematically reveal the intrinsic mechanisms through which digital–real integration affects tourism ecological efficiency from the perspective of typical ecological functional zones. Based on data from 78 counties (municipalities, districts) in China’s Taihang Mountains from 2011 to 2023, this study examines the impact of digital–real integration on tourism ecological efficiency and its operational pathways. The findings are as follows: Firstly, from a temporal evolution perspective, tourism ecological efficiency in the Taihang Mountains underwent a phase of dynamic adjustment and gradual improvement between 2011 and 2023, while the level of digital–real integration experienced a phase of general enhancement and phased advancement. From a spatial evolution perspective, neighboring sub-regions within the Taihang Mountains exhibit positive spatial correlations in terms of both digital–real integration and tourism ecological efficiency. From the perspective of spatiotemporal transfer characteristics, changes in tourism ecological efficiency and the level of integration of the digital and real economies in the Taihang Mountains are influenced by neighboring regions. The development processes of tourism ecology and digital–real integration exhibit a relatively stable and gradually improving pattern, driving the agglomeration of regions toward higher levels. Secondly, digital–real integration has a positive impact on improving tourism ecological efficiency by releasing ecological pressure, promoting industrial synergy agglomeration, and driving green innovation development. Heterogeneity analysis reveals that the positive effect of this integration on tourism ecological efficiency is more pronounced in national e-commerce demonstration cities. Digital–real integration has had a positive impact on improving tourism ecological efficiency in the Southern and Western Taihang Mountain regions, while its impact on the Eastern Taihang Mountain region was not statistically significant. This study incorporates digital–real integration with tourism ecological efficiency, as well as environmental, structural, and capacity factors, into a unified analytical framework, providing theoretical references and practical insights for exploring pathways of digital transformation and innovative tourism ecological governance in ecologically sensitive functional zones. Full article

Magnetocardiography (MCG) is currently a promising technique for non-invasive diagnosis of myocardial ischemia. Clinicians can evaluate the degree of ischemia and categorize subjects into three groups: mild ischemia, severe ischemia, and healthy individuals, by examining the spatiotemporal evolution of cardiac magnetic three-field maps. However, the complex spatiotemporal dynamics of MCG data make it challenging for a single modality to characterize ischemia severity. Consequently, we propose a causal-driven multimodal fusion framework that integrates handcrafted key features with MCG image representations. This framework systematically models two types of confounders using a Structural Causal Model (SCM), namely latent visual confounders and cross-modal fusion confounders. To mitigate spurious correlations and feature redundancy during representation learning, we design two causal-inspired modules based on front-door adjustment and counterfactual intervention. Experimental results on our dataset demonstrate the effectiveness of the proposed framework in improving MCG-based ischemia severity grading. Full article

Urban healthcare systems are fundamentally constrained by the mismatch between static resource configurations and dynamically evolving patient demand. Under the tiered healthcare system, traditional static planning methods struggle to capture the complexity and randomness of patient flows. While recent reinforcement learning (RL) approaches enable adaptive decision-making, they suffer from dimensionality explosion and unstable convergence due to massive action spaces and delayed spatiotemporal credit assignment in city-scale environments. To address this gap, we propose Twin–Game: a digital twin-driven hierarchical reinforcement learning (HRL) framework that formulates adaptive healthcare resource optimization as a “Twin Game” between a simulation-based game environment (Strategic Sandbox) and a hierarchical decision policy. First, we construct the “first twin”—an offline digital twin that serves as the Strategic Sandbox parameterized with Wuhan’s observed facility, population, and transportation data, while patient arrivals and disease profiles are generated synthetically under documented assumptions because individual-level clinical flow data are not publicly available. This environment integrates a dynamic gravity model with a two-way referral mechanism to represent the nonlinear coupling between hospital attractiveness, crowding levels, and patient choice behaviors. Second, we build the “second twin”—an Option-based HRL policy. The Manager (Macro-level Strategic Layer) uses a Deep Q-Network (DQN) for discrete spatial attention allocation; the Worker (Micro-level Execution Layer) uses Proximal Policy Optimization (PPO) for continuous, fine-grained controls such as bed expansion ratios and personnel scheduling. The two twins interact in a closed-loop game, performing strategy search and game evolution under complex constraints to optimize allocation. Experimental results from the Wuhan case indicate that the Twin–Game framework outperforms static baselines and single-layer RL in reducing average travel times, enhancing resource utilization, and improving tiered diagnosis and treatment within the simulation setting. The results should be interpreted as simulation-based decision-support evidence rather than direct clinical validation. This study provides a data-driven, game-theoretic decision support tool for building resilient urban healthcare systems. Full article

Wind speed prediction is an essential spatiotemporal forecasting task in wind energy systems, yet it remains challenging due to the nonlinear and dynamic characteristics of atmospheric processes. The evolution of wind is governed by physical laws, which can be effectively described using partial differential equations (PDEs). To improve forecasting reliability and accuracy, this paper proposes a novel network model, termed DynWindNet, which integrates equation-based dynamics with data-driven dynamics within a unified framework. Specifically, an interactive dual-branch architecture is designed, where a Physics–Data Coupling Module (PDCM) enables adaptive information exchange between the two dynamics via attention-based gating mechanisms. In addition, a frequency-aware enhancement module (FAEM) is introduced to refine the representations of the data-driven branch by selectively emphasizing informative frequency components. Experimental results on the ERA5 dataset demonstrate that DynWindNet consistently outperforms representative baseline methods across atmospheric pressure levels. Overall, the proposed framework provides an effective approach for integrating physics-guided evolution modeling with deep spatiotemporal representation learning in wind field forecasting. Full article

Accurate short-term prediction of network service traffic is essential for communication resource allocation and proactive fault warning in smart grids. However, smart grid service traffic is characterized by nonlinear fluctuations, strong spatio-temporal coupling, and considerable uncertainty, making it difficult for existing methods to capture long-range dependencies, adapt to dynamic topological relationships, and reflect prediction risks. To address these issues, this work develops a deep learning framework that integrates a spatio-temporal Transformer with a diffusion mechanism. The spatio-temporal Transformer extracts temporal evolution patterns and spatial logical correlations from historical traffic matrices, while the diffusion module improves robustness to abrupt traffic variations through latent uncertainty modeling. Furthermore, attention-guided recurrent units are used to generate stable multi-step forecasting sequences. Experiments on a real-world network dataset show that, compared with mainstream benchmark models, the proposed framework reduces Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Root Relative Squared Error (RRSE) by 46.62%, 47.05%, and 44.18%, respectively. These results indicate that the framework improves prediction accuracy and stability while alleviating error accumulation in long-horizon forecasting, thereby providing reliable technical support for smart grid network management. Full article

Drought is a widespread natural hazard in China that can sequentially trigger meteorological, hydrological, agricultural, and socio-economic drought types, yet traditional drought indices typically focus on a single hydrologic component and cannot capture integrated water deficits across multiple compartments. This study aims to systematically characterize the spatiotemporal evolution of comprehensive drought across China’s ten major river basins and to identify and quantify the main natural and anthropogenic factors associated with drought dynamics. We utilized the Gravity Recovery and Climate Experiment (GRACE) Mascon dataset spanning the entire mission period (April 2002–June 2017), which provides a continuous 15-year observation window suitable for detecting decadal-scale trends and inter-annual variability. Given the documented asynchrony between precipitation and terrestrial water storage changes, a zoned index framework was applied: the Combined Climatologic Deviation Index (CCDI) for arid basins and the Drought Severity Index (DSI) for humid basins. The Theil–Sen estimator and Mann–Kendall test, both non-parametric and robust to outliers, were employed for trend detection, and Pearson correlation analysis was used to evaluate statistical associations between drought indices and potential influencing factors. The results reveal a clear “dry gets drier, wet gets wetter” pattern during 2002–2017: severe drought episodes in humid basins (e.g., the Yangtze) were concentrated in 2002–2006, whereas those in arid basins (e.g., the Haihe) occurred mainly in 2013–2017. Groundwater storage anomaly (GWSA) constituted the primary component of total water storage changes in most basins, with the most rapid depletion rate of −45 mm yr⁻¹ in the northern arid basins. Land use/cover change, especially urban expansion, showed a significant statistical association with drought intensification in arid regions, with its standardized contribution being comparable to that of natural factors such as runoff. This study provides a systematic cross-basin assessment and offers scientific insights for differentiated drought mitigation strategies and water resources management. Full article

To address the lack of systematic quantitative characterization of oil bank dynamic evolution and unclear dominant controlling factors in polymer flooding, this study combines reservoir numerical simulation with Python-based quantitative analysis and a machine learning framework (random forest + SHAP). We established 1D and 2D reservoir models: the 1D model develops a precise quantitative characterization method for oil bank width (defined by front/rear edge saturation offsets Pf < 1.0% and Pb < 1.0%, fitted with a cubic polynomial, R² > 0.95) and height (derived from optimal oil saturation difference time curves and integral calculation); the 2D model investigates the regulatory mechanism of reservoir heterogeneity. Based on 15,000 sets of physically consistent simulation data, the random forest model achieves high prediction accuracy (R² = 0.98). Sensitivity analysis reveals that main flow direction permeability, reservoir temperature, and water-phase exponent (nw) of the Corey model are the dominant controlling parameters, exhibiting substantially higher sensitivity than polymer adsorption capacity and residual resistance coefficient. The oil bank height shows a negative correlation with the first two parameters, while it displays a peak-type variation with the water-phase exponent. Under heterogeneous conditions, permeability anisotropy amplifies the regulatory effect of relative permeability exponents, leading to unbalanced oil bank migration (quantified by front ratio R). This study breaks through the limitations of traditional qualitative characterization, elucidates the spatiotemporal evolution laws and heterogeneous regulatory mechanisms of the oil bank, and provides reliable theoretical and dataset support for optimizing polymer flooding schemes. Full article

Rainfall is a critical factor inducing slope instability, and accurate prediction of the factor of safety (FOS) of slopes under rainfall conditions is of paramount importance for disaster prevention and mitigation. Conventional numerical simulation methods incur high computational costs, while individual machine learning models are often insufficient to adequately capture the nonlinear spatiotemporal evolution characteristics of multiple factors under coupled multi-physics fields. To address these limitations, this paper proposes a Transformer–LSTM prediction framework. First, a fluid–structure coupling model for rainfall-affected slopes is constructed using COMSOL, and multi-factor orthogonal experiments are performed to generate multi-dimensional time-series data. Subsequently, a Transformer–LSTM fusion deep learning model is built, in which LSTM is employed to extract the temporal dynamic characteristics of rainfall infiltration, and the self-attention mechanism of the Transformer is leveraged to enhance feature extraction and global dependency modeling of key disaster-causing factors. Experimental results demonstrate that the Transformer–LSTM model significantly outperforms traditional PSO-LSTM, PSO-SVM, and standalone Transformer or LSTM models in terms of both prediction accuracy and generalization capability. Its coefficient of determination (R²) remains above 0.94, and key evaluation metrics—including mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE)—attain the lowest values among the compared models. Furthermore, the SHAP (SHapley Additive exPlanations) interpretability framework is introduced to quantitatively elucidate the model’s predictive decision-making and to establish a physically grounded causal mapping with geotechnical mechanisms. It is confirmed that effective cohesion and slope angle exert a dominant interactive effect on the degradation of slope stability, providing data-driven support for wide-area monitoring of rainfall-induced landslides. Full article

Urban sustainable development increasingly depends on interactions among multiple urban subsystems, yet existing studies often overlook cross-regional linkages and nonlinear development processes. This study investigates the coordinated development of urbanization, smart development, resilience, and low-carbon transition (USRL) from an efficiency perspective. Using panel data from 278 Chinese cities during 2010–2023, this work integrates the Super-SBM model, the Local–Tele Coupling Coordination Degree (LTCCD) framework, Dagum Gini decomposition, and machine learning techniques to examine the spatiotemporal evolution, spatial disparities, and driving mechanisms of coordinated development. The results show that coordinated development improved steadily over time, although subsystem evolution remained uneven, with resilience lagging behind other dimensions. Regional disparities gradually narrowed, but inter-regional differences remained the dominant source of spatial inequality. Innovation intensity, industrial upgrading, and high-quality foreign investment positively contributed to coordinated development, whereas fiscal and financial factors exhibited nonlinear effects. Interaction analysis further revealed that coordinated development is shaped by the combined influence of multiple drivers rather than by individual factors alone. Our findings suggest that urban sustainable development is jointly influenced by subsystem coordination, cross-regional interactions, and nonlinear development dynamics, highlighting the importance of integrating local and tele-coupling processes in urban sustainability research. Full article

Strong seismic waves induced by drill-and-blast tunnel excavation threaten the structural integrity of adjacent existing tunnels; however, prevailing safety evaluation methods mostly simplify tunnel linings as homogeneous continua, failing to accurately characterize the meso-scale uncoordinated dynamic response between rebar and concrete under blast impact. To fill this research gap, a 1:1 full-scale separated three-dimensional finite element model of reinforced concrete composite linings was established using the LS-DYNA explicit dynamic numerical algorithm, which was verified by previous 1:25 scaled physical model tests. This study systematically quantifies the spatiotemporal evolution of lining dynamic responses under two core parameters—tunnel clear distance (10 m to 60 m) and single-delay detonating charge quantity (10.8 kg to 28.8 kg)—to validate the response differences between materials. It is abstracted that the structural failure is dominated by axial tensile stress, with the embedded rebar being significantly more sensitive to internal stress surges (reaching 3.5 times the peak stress of concrete), while the concrete is more sensitive to particle vibration velocity amplification, a mismatch that is particularly acute within a 30 m clear distance. This study highlights the severe interfacial stress gradient between rebar and concrete, providing an indirect but critical indicator for the potential risk of interface debonding under adjacent blasting, and offers a quantitative theoretical basis for extending safety assessments from macro-surface vibration control to refined meso-scale internal stress monitoring. Full article

In the process of deep hard rock mining, dynamic disasters, such as rockbursts and large-scale collapses, pose a serious threat to the production safety and sustainable development of mines. Microseismic monitoring has been widely used in mines as an efficient disaster monitoring tool. However, microseismic monitoring signals exhibit obvious nonlinear and disordered attributes due to the complex rock behavior, mine structure, and excavation disturbance. This poses great challenges for precise monitoring and forewarning of disasters in deep hard rock mines. This study introduced fractal theory and methods to characterize the spatiotemporal energy information of microseismic monitoring signals. Theoretical analysis, numerical simulation, in situ testing, and field monitoring were integrated to establish a comprehensive spatiotemporal energetic fractal characterization model of microseismic monitoring sources. A scale conversion method for the spatial and energy parameters of microseismic events was developed, and the fractal evolution of microseismic monitoring events induced by deep mining activities was systematically investigated. On this basis, a fractal-based grading forewarning system for deep mines was established, providing theoretical and methodological support for accurate disaster prediction in deep hard rock mines. Full article

Accurate coastline extraction in muddy and macro-tidal environments is challenging due to tidal variability and complex coastal surfaces. The Jiangsu coast of China, characterized by extensive tidal flats, silty coastlines, and strong land–sea interactions, provides an ideal case for long-term coastline change analysis. This study investigates the spatiotemporal evolution of the Jiangsu coastline from 2018 to 2025 using multi-temporal Sentinel-2 imagery. A tide-independent coastline extraction framework was developed by integrating the Normalized Difference Water Index, Modified Normalized Difference Water Index, and Normalized Difference Vegetation Index for different coastal environments. An annual maximum spectral index composite was applied to approximate the highest water-level conditions without explicit tidal correction. Coastline dynamics were quantified using fractal dimension analysis and a transect-based method. The extracted coastlines yielded an average Root Mean Square Error (RMSE) of 13.14 m and an average Mean Absolute Distance Error (MADE) of 9.39 m. Results show that the total coastline length varied within 5% during the study period, with a maximum of 1079.84 km in 2022 and a minimum of 1004.99 km in 2018. Coastline change was dominated by erosion, accounting for 56.21% of the total coastline length. Land cover analysis revealed that accretion mainly occurred near river mouths and aquaculture areas, whereas erosion was more common at interfaces between forested land and engineered coastlines. The proposed framework provides an efficient and consistent approach for short-term coastline monitoring in muddy coastal environments. Full article