Search Results (944)

Soil moisture (SM) is a key variable regulating land–atmosphere energy exchange, hydrological processes, and ecosystem functioning. Though important, there are still unresolved problems in accurate SM monitoring and the practical application and validation of existing methods. In this review, we integrate mechanistic classification and applicability and constraint discussions to develop a coherent understanding of current SM monitoring approaches. Within this framework, in situ measurements, optical and thermal infrared methods, active and passive microwave remote sensing (RS) techniques, and model-based simulations are compared, and publicly accessible SM dataset products are comparatively analyzed in terms of product characteristics and application limitations. Different from other published reviews, this study covers a large scope of SM monitoring methods varying from in situ observation to RS inversion, and classifies them based on their mechanisms, thereby constructing a complete comparative framework for SM research. Moreover, three types of open-access SM dataset products are investigated, optical and microwave RS products, model simulation and data fusion products, and reanalysis dataset products, and evaluated according to their resolution, depth, applicability, advantages, and limitations. By doing so, it is concluded that in situ observations remain essential for calibration and validation but are spatially limited. Optical and thermal infrared methods are restricted by atmospheric conditions and a shallow penetration depth, while microwave techniques exhibit varying performances under different vegetation and soil conditions. Existing datasets differ significantly in resolution, consistency, and coverage, making no single product universally applicable. Future research should focus on multi-source and spatiotemporal data fusions, the integration of machine learning with physical mechanisms, enhancement for cross-sensor consistency, the establishment of standardized uncertainty evaluation frameworks, and the refinement of high-order RTMs and parameterization. Full article

In recent years, European cities have experienced rapid changes in their functional and spatial organisation, which have affected, among others, the natural environment, the economy and society. The intensive and often uncontrolled growth of residential development associated with suburbanisation significantly impacts areas located around urban areas. Growing investment pressures usually lead to the transformation of rural and naturally valuable areas, altering their character and functions. Solving these problems requires developing a method to determine the main directions and intensity of land use changes in the context of urbanisation pressures and sustainable spatial development. This article presents the results of a spatiotemporal analysis of the dynamics of built-up area development in rural and suburban zones, utilising Geographic Information Systems (GIS) technology. The study focused on the expansion of single- and multi-family housing around the city of Białystok, Poland, between 1997 and 2022. The analysis was based on spatial data, including available orthomosaics and cadastral data from the Topographic Objects Database (BDOT10k). The GIS-based analysis covered an area of nearly 2000 km² and included methods for change detection, analysis, and land cover classification. The results indicated a marked intensification in landscape transformations, particularly in transition zones between rural and urban areas. At the same time, forests and protected zones significantly influenced the direction and pace of development, acting as natural barriers limiting spatial expansion. The results indicate the need to consider environmental factors (e.g., protected areas and forests) in spatial planning processes and sustainable development policies. The study confirms the high usefulness of GIS tools in monitoring and forecasting spatial change at both the local and regional scales. This research also contributes to the discussion on urbanisation, its characteristics, causes, and consequences, and highlights the role of green spaces in limiting sprawl. Full article

Graph neural networks (GNNs) extend deep learning to non-Euclidean domains, offering a robust framework for modeling the spatial, structural, and functional relationships inherent in medical imaging. This paper reviews recent progress in GNN architectures, including recurrent, convolutional, attention-based, autoencoding, and spatiotemporal designs, and examines how these models have been applied to core medical imaging tasks, such as segmentation, classification, registration, reconstruction, and multimodal fusion. The review further identifies current challenges and limitations in applying GNNs to medical imaging and discusses emerging trends, including graph–transformer integration, self-supervised graph learning, and federated GNNs. This paper provides a concise and comprehensive reference for advancing reliable and generalizable GNN-based medical imaging systems. Full article

This study investigates the spatiotemporal changes in land use and land cover (LULC) in the Kağıthane basin, Istanbul, a region experiencing rapid urban growth, to assess its environmental sustainability. Sentinel-1 and Sentinel-2 satellite images processed on the Google Earth Engine (GEE) platform were used for 2017, 2020, and 2023. Optical data from Sentinel-2, after atmospheric and geometric corrections, combined with co- and cross-polarized radar backscatter from Sentinel-1, supported land cover classification. Additionally, 14 spectral indices, including the Normalized Difference Vegetation Index (NDVI), Normalized Difference Water Index (NDWI), and Urban Index (UI), enhanced discrimination between classes. To estimate LULC projections for 2035, 2050, 2065, 2080, and 2095, the Modules for Land Use Change Evaluation (MOLUSCE) model was used, which integrates artificial neural networks with a cellular automata framework. Six driving variables, roads, streams, topographic parameters (elevation, slope, and aspect), and population density, were incorporated into multiple scenarios. Model performance was evaluated using overall accuracy, Kappa statistics, and confusion matrices, yielding strong results (91.88% accuracy; Kappa = 0.84). The simulations indicate a significant decline in forest cover and barren lands, while vegetation and built-up areas are projected to grow steadily, raising concerns about long-term urban sustainability. Water bodies are projected to remain relatively stable. Under these changes, future direct carbon emissions were estimated using carbon emission coefficients by land class. Indirect carbon emissions were estimated based on natural gas and electricity consumption data. Considering both direct and indirect emissions, the results indicate a decrease in carbon emissions from 2023 to 2035, followed by an increase of up to 13% between 2035 and 2095. These findings emphasize the importance of combining multi-sensor remote sensing data with spatially explicit modeling to accurately assess land use changes in rapidly urbanizing basins. The study emphasizes the critical need to adopt sustainability measures that address changes in carbon emissions and guide future urban planning towards a more sustainable path. Full article

Land cover products are essential tools in environmental and ecological research. However, limited attention has been paid to their data quality issues. Many existing products suffer from pronounced spatiotemporal inconsistencies, characterized by frequent and repetitive classification fluctuations in specific regions and years, which substantially compromise the accuracy of analyses and models that rely on them. To address these challenges, this study introduces a method for deriving spatiotemporally stable samples to support high-precision land cover classification. The approach integrates national and regional land-use policies to assess temporal stability and incorporates advanced time-series processing techniques together with innovative vegetation indices to facilitate effective sample reuse. Experimental results show that this method markedly improves classification accuracy across vegetation types and reduces the extent of areas prone to frequent land-cover changes by 22.64%. Compared with existing products of similar spatial resolution, our approach achieves an overall classification accuracy of 91.1%, providing stable, high-quality input data that underpin precise and reliable regional-scale environmental and ecological modeling. Full article

Maintaining consistency in real-time multi-user editing of planar geospatial features remains challenging for traditional collaborative editing techniques, which are primarily designed for text documents. When applied to spatial data, these methods often yield inaccurate results and cause information loss, while also overlooking the geospatial and topological properties of such features. Moreover, they fail to differentiate processing priorities due to limited spatial awareness, hindering targeted performance optimization. To address these limitations, we propose a geometry-aware collaborative editing algorithm based on Conflict-Free Replicated Data Types (CRDTs), integrating a spatial–semantic data model with spatio-temporal operation merging strategies. As an extension of CRDTs tailored for spatial data, it leverages geometric vector clocks (GVCs) and minimum bounding rectangles (MBRs) to capture temporal and spatial dependencies among editing operations, detects topological anomalies through geometric constraints, resolves conflicts via spatio-temporal metadata encoded in GVCs, and optimizes performance through MBR-based operation classification. Experimental results show that this approach improves editing accuracy, contributes to preserving topological integrity, and maintains strong performance under collaborative editing workloads, with notable efficiency gains for large-scale datasets and visible features. This work provides a novel geometry-aware framework for scalable, accurate multi-user editing of planar geospatial features that helps preserve topological integrity. Full article

Isolated Sign Language Recognition (ISLR), which focuses on identifying individual signs from sign language videos, presents substantial challenges due to small and ambiguous hand regions, high visual similarity among signs, and large intra-class variability. This study investigates the adaptability of YOLO-Act, a unified spatiotemporal detection framework originally developed for generic action recognition in videos, when applied to large-scale sign language benchmarks. YOLO-Act jointly performs signer localization (identifying the person signing within a video) and action classification (determining which sign is performed) directly from RGB sequences, eliminating the need for pose estimation or handcrafted temporal cues. We evaluate the model on the WLASL2000 and MSASL1000 datasets for American Sign Language recognition, achieving Top-1 accuracies of 67.07% and 81.41%, respectively. The latter represents a 3.55% absolute improvement over the best-performing baseline without pose supervision. These results demonstrate the strong cross-domain generalization and robustness of YOLO-Act in complex multi-class recognition scenarios. Full article

Global climate change has profoundly affected agricultural ecosystems by altering the spatiotemporal patterns of temperature and precipitation, disrupting ecological equilibrium, and increasing environmental variability for crop growth, thereby posing significant challenges to food security. Based on 1 km-resolution gridded datasets of mean precipitation and temperature for Liaoning Province from 1950 to 2023, this study integrated the Miami and Thornthwaite Memorial models with climate tendency rate analysis, Mann–Kendall trend tests, and inverse distance weighting interpolation to assess spatiotemporal changes in climate potential productivity (CPP) and its relationship with grain yield dynamics. The results show that, from 1950 to 2023, annual precipitation exhibited a fluctuating downward trend (−8.5 mm/10a), while mean annual temperature increased significantly (0.3 °C/10a). Consequently, precipitation-based climatic production potential declined at a rate of 10.4 g·m⁻²·(10a)⁻¹, whereas temperature-based, evapotranspiration-based, and standard climate potential productivity (Yb) increased at rates of 23.3-, 6.6-, and 5.7 g·m⁻²·(10a)⁻¹, respectively. Spatially, CPP displayed a distinct gradient characterized by higher values in the southeast and lower values in the northwest, with a stronger correlation to precipitation than to temperature. Climate classification analysis indicated that warm-humid conditions enhanced CPP, whereas cold-dry, cold-humid, and warm-dry conditions reduced productivity. Although grain yield per unit area and climate resource utilization efficiency increased by 89.4 g·m⁻²·(10a)⁻¹ and 9.0% per decade, respectively, the yield-increasing potential declined by 84.1 g·m⁻²·(10a)⁻¹, indicating that while advances in agricultural technology have improved resource conversion efficiency, the potential for further yield gains through climate-dependent strategies alone is increasingly limited. Full article

Understanding soybean cultivation in Northeast China is essential for informing policies related to national food security. However, long-term, high-resolution soybean maps are still lacking, largely due to persistent cloud cover, limited availability of high-quality field labels, and the difficulty of capturing crop phenological dynamics using traditional remote sensing methods. To address this gap, this study aims to develop a robust framework for generating decade-long soybean distribution maps by integrating medium-resolution Landsat imagery with advanced deep learning techniques. We mapped the soybean distribution across Northeast China from 2013 to 2022 by constructing a bi-monthly NDVI-based composite and applying a deep learning model that combines the Transformer architecture with fully connected neural networks. The model was trained using a large set of field-surveyed samples collected between 2017 and 2019. Validation results demonstrate strong classification performance, with a user accuracy of 89.77% and a producer accuracy of 88.59%, sufficient for reliable spatiotemporal analysis. When compared with prefecture-level statistical yearbook data, the predicted annual soybean areas show a high degree of agreement (R² = 0.9226). Overall, this study not only fills an important gap in long-term soybean mapping for Northeast China, but also provides a replicable methodological framework for large-scale, time-series crop mapping. The approach has strong potential for broader application in agricultural monitoring and food security assessment. Full article

Flash droughts—characterized by their sudden development, severity, and short duration—impose considerable challenges on the soil–water complex of agricultural systems, especially under the Mediterranean climate. Though gaining increasing global significance, Mediterranean flash droughts are still understudied. This study examines the spatiotemporal variability of flash droughts in Greece for the period 1990–2024 using 5-day (pentad) ERA5-Land root-zone soil moisture (0–100 cm) at 0.25° resolution. A percentile-threshold approach detected flash drought events, and their main features—including frequency, duration, magnitude, intensity, decline rate, recovery rate, and recovery duration—were evaluated at the annual and seasonal levels. Findings indicate that Central Greece and Thessaly face the highest frequency and longevity of flash droughts, while Western Greece and Peloponnese and Western Macedonia are characterized by rapid development but intense recovery. An innovative empirical classification framework founded on decline and recovery rates indicated that Mild Fast Recovery events prevail in northern and central Greece, while Intense but Recovering events dominate in western and southern Greece. These results offer new perspectives on how flash droughts impact soil–water availability and agricultural resilience, providing a data-driven platform to aid sustainable water management, early warning systems, and adaptation strategies for Mediterranean agriculture in conditions of climate variability. Full article

Software-Defined Networking (SDN) provides centralized control over routing paths through a logically centralized controller. Although Graph Neural Networks (GNNs) such as GraphSAGE have shown strong potential for network topology analysis, their superiority over simpler models like the Multi-Layer Perceptron (MLP) in dynamic SDN control remains unclear. In this study, we compare MLP and GraphSAGE using three training data volumes (70, 100, and 140) and spatio-temporal features that integrate spatial and temporal characteristics of each node. Experimental results reveal a distinct discrepancy between offline classification metrics and online SDN performance. Offline evaluation showed that MLP achieved a slightly higher F1-score (0.62) than GraphSAGE (0.59). However, when deployed in a SDN controller, GraphSAGE reduced latency by 17%, increased throughput by 8%, and improved jitter by 31%. These results demonstrate that higher offline accuracy does not necessarily translate into better real-time control performance, since offline metrics fail to capture topology-aware routing, congestion recovery, and dynamic adaptation effects. The findings provide a practical guideline for SDN-oriented AI model evaluation, emphasizing end-to-end system performance over isolated offline metrics. Full article

Website fingerprinting (WF) attacks analyze encrypted network traffic to exploit side-channel features such as packet sizes, inter-packet timings, and burst patterns, enabling adversaries to infer users’ browsing activities and posing persistent privacy threats even under encryption protocols like TLS. Existing WF defenses primarily rely on static perturbations of coarse statistical features, which fail to reproduce the multi-scale spatio-temporal dynamics of website traffic and are increasingly ineffective against modern deep learning-based classifiers. To address this challenge, we propose WFD-EST, a website fingerprinting defense framework that dynamically emulates spatio-temporal traffic characteristics for fine-grained obfuscation. WFD-EST constructs a multi-scale traffic representation that captures both packet-level dynamics and burst-level correlations. A diffusion-based generator, guided by a fine-tuned large-scale discriminator, synthesizes realistic target traffic templates that preserve structural consistency while reflecting temporal diversity. Based on these templates, a burst-aware manipulation module performs packet padding, insertion, and delay operations to align source flows with target spatio-temporal patterns, generating traffic indistinguishable from real target flows. Evaluations on a real-world dataset comprising 15,000 encrypted samples from three representative websites show that WFD-EST consistently outperforms two state-of-the-art defenses, reducing classification F1 scores by 0.082–0.144 while lowering bandwidth and time overheads by at least 0.086 and 0.054, respectively. Full article

Reliable operation of proton exchange membrane fuel cells (PEMFCs) is crucial for their widespread commercialization, and accurate fault diagnosis is the key to ensuring their long-term stable operation. However, traditional fault diagnosis methods not only lack sufficient interpretability, making it difficult for users to trust their diagnostic decisions, but also one-dimensional (1D) feature extraction methods highly rely on manual experience to design and extract features, which are easily affected by noise. This paper proposes a new interpretable fault diagnosis algorithm that integrates Gramian angular field (GAF) transform, convolutional neural network (CNN), and gradient-weighted class activation mapping (Grad-CAM) for enhanced fault diagnosis and analysis of proton exchange membrane fuel cells. The algorithm is systematically validated using experimental data to classify three critical health states: normal operation, membrane drying, and hydrogen leakage. The method first converts the 1D sensor signal into a two-dimensional GAF image to capture the temporal dependency and converts the diagnostic problem into an image recognition task. Then, the customized CNN architecture extracts hierarchical spatiotemporal features for fault classification, while Grad-CAM provides visual explanations by highlighting the most influential regions in the input signal. The results show that the diagnostic accuracy of the proposed model reaches 99.8%, which is 4.18%, 9.43% and 2.46% higher than other baseline models (SVM, LSTM, and CNN), respectively. Furthermore, the explainability analysis using Grad-CAM effectively mitigates the “black box” problem by generating visual heatmaps that pinpoint the key feature regions the model relies on to distinguish different health states. This validates the model’s decision-making rationality and significantly enhances the transparency and trustworthiness of the diagnostic process. Full article

Steady-State Visual Evoked Potentials (SSVEPs) offer a robust basis for brain–computer interface (BCI) systems due to their high signal-to-noise ratio, minimal user training requirements, and suitability for real-time decoding. In this work, we propose MultiHeadEEGModelCLS, a novel Transformer-based architecture that integrates context-aware representation learning into SSVEP decoding. The model employs a dual-stream spatio-temporal encoder to process both the input EEG trial and a contextual signal (e.g., template or reference trial), enhanced by a learnable classification ([CLS]) token. Through self-attention and cross-attention mechanisms, the model aligns trial-level representations with contextual cues. The architecture supports multi-task learning via signal reconstruction and context-informed classification heads. Evaluation on benchmark datasets (Speller and BETA) demonstrates state-of-the-art performance, particularly under limited data and short time window scenarios, achieving higher classification accuracy and information transfer rates (ITR) compared to existing deep learning methods such as the multi-branch CNN (ConvDNN). Our method achieved an ITR of 283 bits/min and 222 bits/min for the Speller and BETA datasets, and a ConvDNN of 238 bits/min and 181 bits/min. These results highlight the effectiveness of contextual modeling in enhancing the robustness and efficiency of SSVEP-based BCIs. Full article

Distributed acoustic sensing (DAS) systems enable real-time monitoring of physical events across extended areas using optical fiber that detects vibrations through changes in backscattered light patterns. In perimeter security applications, these systems must accurately distinguish between legitimate activities and potential security threats by analyzing complex spatio-temporal data patterns. However, the high dimensionality and noise content of raw DAS data presents significant challenges for effective feature extraction and event classification, particularly when computational efficiency is required for real-time deployment. Traditional approaches or current machine learning methods often struggle with the balance between information preservation and computational complexity. This study addresses the critical need for efficient and accurate feature extraction methods that can identify informative signal components while maintaining real-time processing capabilities in DAS-based security systems. Here we show that wavelet packet decomposition (WPD) combined with a cascaded machine learning approach achieves 98% classification accuracy while reducing computational load through intelligent channel selection and preliminary filtering. Our modified peak signal-to-noise ratio metric successfully identifies the most informative frequency bands, which we validate through comprehensive neural network experiments across all possible WPD channels. The integration of principal component analysis with logistic regression as a preprocessing filter eliminates a substantial portion of non-target events while maintaining high recall level, significantly improving upon methods that processed all available data. These findings establish WPD as a powerful preprocessing technique for distributed sensing applications, with immediate applications in critical infrastructure protection. The demonstrated gains in computational efficiency and accuracy improvements suggest broad applicability to other pattern recognition challenges in large-scale sensor networks, seismic monitoring, and structural health monitoring systems, where real-time processing of high-dimensional acoustic data is essential. Full article