Search Results (215)

Reliable short-term prediction of bus travel time on signalized urban arterials is essential for improving service reliability and may provide a useful forecasting basis for prediction-informed transit signal priority (TSP) and arterial coordination applications. However, bus operations on urban arterials are highly variable due to stop dwell times, signal delays, and interactions with mixed traffic, leading to nonlinear and nonstationary travel time patterns with strong spatiotemporal dependence. This study proposes a hybrid KNN–ConvLSTM framework for short-term arterial bus travel time prediction using real-world field data. A K-nearest neighbors (KNNs) module is first employed to retrieve historical operation sequences that are most similar to the current corridor state, thereby reducing interference from mismatched traffic regimes and improving robustness. Smart-card (IC card) transaction data are incorporated as demand-related features to represent passenger activity and its impact on dwell time and travel time variability. The selected sequences are then organized into a corridor-ordered spatiotemporal representation and further refined by lightweight temporal enhancement operations, including relevance gating, multi-scale aggregation, adaptive feature fusion, and residual enhancement, before being fed into the convolutional long short-term memory (ConvLSTM) predictor. The proposed approach is evaluated using weekday service-hour data extracted from 30 days of real-world bus operation records collected from a typical urban arterial corridor in Changchun, China, and is compared with several benchmark models, including ARIMA, KNN, LSTM, CNN, ConvLSTM, Transformer, and DCRNN. The results indicate that the proposed KNN–ConvLSTM framework achieves an MAE of 40.1 s, an RMSE of 55.8 s, a SMAPE of 10.7%, and an R² of 0.878, outperforming all benchmark models. Specifically, compared with the Transformer baseline, the proposed framework reduces MAE by 1.5%, RMSE by 5.1%, and SMAPE by 7.0%, while increasing R² by 0.014. Compared with the DCRNN baseline, it reduces MAE by 10.7%, RMSE by 1.9%, and SMAPE by 2.7%, while increasing R² by 0.008. These findings demonstrate that similarity-aware retrieval combined with spatiotemporal deep learning can substantially enhance short-term bus travel time prediction on signalized urban arterials. More accurate short-term forecasts may support prediction-informed transit signal priority and arterial coordination by providing more reliable downstream arrival-time estimates. However, the generalizability of the reported results is still constrained by the relatively short 30-day observation period and the single-corridor case setting, and the operational and environmental effects of downstream applications remain to be validated through dedicated closed-loop control evaluation in future work. 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

With urbanization transforming from scale expansion to high-quality development and the increasing prominence of the ecological environment constraints of drainage basins, systematically identifying the mechanism of action of non-point source pollution from a high-quality development perspective is significant for coordinating urban development and environmental protection. Based on remote sensing data on atmospheric pollution and multi-source spatial big data such as nighttime light (NTL), LandScan population, point of interest (POI), and land use data from 2013 to 2025, this study applies methods including deposition flux analysis, deep learning fusion, bivariate spatial autocorrelation, and geographically weighted regression (GWR) to empirically analyze the spatiotemporal evolution characteristics, spatial correlation, and local impacts of high-quality urban development on non-point source pollution in the Chenghai drainage basin. We find that, firstly, non-point source pollution and high-quality urban development in the Chenghai drainage basin both present significant stage-specific and spatial heterogeneity. In other words, the two are not mutually independent spatial elements in space; instead, they are closely and significantly correlated, with their correlation types showing obvious spatial agglomeration characteristics. Secondly, the impact of high-quality urban development on non-point source pollution evolves in stages. It gradually shifts from a whole-region, homogeneous, strongly positive driving force to spatial differentiation. Specifically, from 2013 to 2017, the whole-region regression coefficients are generally greater than 0.5, meaning that urban development represents a strong, whole-region driving force promoting pollution. However, after 2017, this impact evolves into a stable spatial differentiation pattern. It mainly shows that the northern urban core area, where coefficients are greater than 0.5, maintains a continuous strong positive driving force. Meanwhile, the peripheral area, where coefficients are generally lower than 0, creates a negative inhibition effect. Based on the above rules, further analysis shows that the impact of high-quality urban development on non-point source pollution is absolutely not a simple linear relationship. Instead, it is a result of the coupling effect of multiple factors, including development stage, spatial location, and governance level. Therefore, to positively affect the ecological environment through high-quality development, model transformation and precise governance are essential. The findings of this study deepen our understanding of the transformation of urban development models and the response mechanism of non-point source pollution. They also provide a scientific basis and decision support for promoting the coordinated governance of high-quality urban development and non-point source pollution by region and stage in plateau lake drainage basins, as well as for improving the sustainable development of drainage basins. Full article

Accurate precipitation nowcasting plays an important role in disaster prevention and hydrometeorological applications, yet it remains highly challenging due to the complex spatiotemporal variability and multi-scale structural characteristics of precipitation systems. Existing deep learning methods are largely data-driven and often struggle to effectively exploit multi-source observations or learn physically meaningful representations. To address these limitations, this study proposes a Multi-Scale Frequency–Temporal Network (MS-FTNet) for precipitation nowcasting. The framework leverages Fourier transform-based frequency-domain modeling to achieve an interpretable multi-scale decomposition of precipitation dynamics. Specifically, low-frequency components capture large-scale stratiform patterns and their temporal evolution, while high-frequency components represent localized convective structures and abrupt variations. Building on this, a Global Feature Collaboration (GFC) module integrates global frequency-domain representations with multi-scale convolutional features, and an Adaptive Temporal Fusion (ATF) module enhances temporal dependency modeling. Experiments on the SEVIR dataset demonstrate that MS-FTNet consistently outperforms representative baseline models in terms of MSE, CSI, and LPIPS, particularly for heavy precipitation events and longer forecast lead times. Full article

Unsupervised video anomaly detection (VAD) methods learn from normal data to identify anomalies by capturing pattern deviations. However, they often struggle to model multi-scale features and distinguish between normal and abnormal instances. To address these limitations, we propose a Multi-scale U-shaped Adaptive Clustering Learning (MS-UACL) framework. Built on the U-Net architecture, we redesign it as a 3D-encoder/2D-decoder autoencoder. In the encoder, we introduce a Dual-scale Feature Cascading Module (IDCN), which adopts a pseudo-branch fusion mechanism to systematically model multi-scale spatiotemporal features, thereby enhancing the model’s representational capability. To further enhance the distinction between normal and anomalous patterns, we propose an MLP-based Adaptive Clustering Algorithm (MLP-ACA). Specifically, MLP-ACA employs an initial mapping mechanism to align cluster centers with the underlying normal data distribution, facilitating more accurate feature reconstruction. Additionally, we introduce an adaptive clustering update strategy that optimizes cluster centers by tuning solely the parameters of the MLP. This enables the cluster centers to autonomously converge toward optimal feature representations, thereby accelerating clustering convergence and enhancing pattern separability. Extensive experiments on three benchmark datasets demonstrate that the proposed MS-UACL framework outperforms most existing methods on small- and medium-scale datasets. Full article

Land use changes within urban agglomerations exhibit significant spatiotemporal heterogeneity and regional diversity. In urban agglomeration land simulation, traditional models often struggle to systematically capture these variations. We introduce the GCTP, a novel framework that integrates guided Geographical zoning, Convolutional Neural Networks (CNN)-Transformer, and the Patch-generating Land Use Simulation (PLUS) model. Initially, guided K-means clustering was employed for geographic zoning to characterize regional spatial non-stationarity. Then, a CNN-Transformer network leveraged self-attention mechanisms to capture multi-scale spatial correlations, obtaining pixel-level development probabilities. Finally, these probabilities were fused with PLUS- Land Expansion Analysis Strategy (LEAS) outputs to drive PLUS- Cellular Automata with multi-type Random Seeds (CARS) for patch-level simulation. The results demonstrate the following: (1) The embedding of guided zoning enabled the model to achieve an Overall Accuracy (OA) of 0.941, effectively mitigating global simulation bias. (2) The optimal simulation performance occurred at a fusion weight of 0.81, yielding a Kappa of 0.8917 and an Figure of Merit (FoM) of 0.3830, significantly exceeding a single model. (3) The 2030 simulation indicates that the GCTP model effectively reduces isolated pixels at urban fringes. The GCTP generates neighborhood patterns with high spatial compactness and geographic consistency. This study highlights the significant advantages of integrating long-range spatial perception with geographical heterogeneity constraints in the land expansion simulation of urban agglomerations. The findings support more precise territorial spatial planning practices. Full article

High-precision wind power prediction improves grid stability and reduces curtailment losses. Existing methods face three limitations: static graphs cannot capture dynamic spatial correlations under weather changes, time series models miss multi-scale temporal features, and frequency-domain analyses lack physical constraints. We propose: (1) a dynamic distance correlation weighted graph that adaptively combines geographic and power correlations for weather–terrain coupling; (2) a spatio-temporal-frequency fusion framework integrating graph networks, bidirectional GRUs, and a patchwise sparse time–frequency module; (3) a turbine power curve-constrained frequency mixer for physical consistency. On the SDWPF dataset, our model achieves MAE reductions of 37.47–43.32% and RMSE reductions of 37.93–42.70% versus baselines, outperforming state-of-the-art methods. The approach demonstrates superior performance in complex spatio-temporal scenarios. Full article

Background: The recognition of autism spectrum disorder (ASD) has been a challenge due to the heterogeneity in symptoms and complex variations in brain function. Resting-state functional magnetic resonance imaging (rs-fMRI) has become instrumental in studying these disorders by accessing underlying abnormal neural activity and connectivity. Recently, deep learning approaches have shifted the analysis of brain networks by capturing spatiotemporal information from fMRI sequences. Nonetheless, most existing studies are limited by relying on a single representational scale, typically restricting analysis to either voxel-level spatiotemporal patterns or static connectivity matrices. Additionally, the dynamic reconfiguration of functional coupling and its variations across different anatomical parcellations are often ignored, which obscures neurobiologically meaningful dynamics. Methods: In this regard, we propose a multi-atlas dynamic connectivity transformer fused with 4D spatiotemporal modeling for ASD recognition (MADCT-4D). Specifically, the framework comprises two complementary branches. The 4D spatiotemporal branch encodes raw rs-fMRI volumes to learn hierarchical representations of evolving neural activity, while the dynamic-connectivity branch models time-resolved functional connectivity sequences constructed from multiple atlases, enabling the network to capture dynamic reconfiguration at the connectome level under different parcellation granularities. Moreover, we perform late fusion by combining the branch-specific decision scores with a learnable gate, allowing the model to adaptively weight voxel-level dynamics and multi-atlas connectivity evidence for each subject. Results: Extensive experiments on the publicly available ABIDE dataset demonstrate that the proposed method achieves 90.2% accuracy for ASD recognition, outperforming multiple competitive baselines. Conclusions: The proposed framework yields interpretable biomarkers based on learned dynamic connectivity patterns that are consistent with altered functional coupling in ASD. Full article

Infrared moving maritime vessel segmentation is a crucial image processing task for maritime security, which is a challenging problem due to the complex backgrounds and targets with varying sizes. To address these issues, we propose an end-to-end segmentation network based on a multi-scale spatiotemporal vision transformer (ST-VT) for segmenting the moving maritime vessels in the infrared image sequence. Specifically, in the feature extraction module, we introduce a multi-scale feature encoding structure that combines a multi-scale backbone and Feature Pyramid Network technology. Then, the multi-scale deformable encoder structure and a cross-scale fusion module with the pixel decoder are proposed to generate the multi-scale spatiotemporal features. Subsequently, we employ the improved attention blocks that are the core blocks of the coarse-to-fine framework (across scales) of the prompt decoder to obtain the prompts. Finally, a multi-scale mask decoder is applied to achieve the final target segmentation. The experiments are conducted on the benchmark dataset IPATCH and our labeled dataset LAS-MassMIND. The results demonstrate that the proposed method achieves state-of-the-art performance, especially within complex backgrounds and targets of varying sizes. Full article

Spatiotemporal fusion aims to generate remote sensing images with both high spatial and high temporal resolution by integrating multi-source observations. However, significant spectral inconsistencies often arise when fusing images acquired at different spatial scales, which severely degrade the radiometric fidelity and temporal reliability of the fused results. Most existing methods focus on enhancing spatial details or temporal consistency, while the cross-scale spectral discrepancy between coarse- and fine-resolution images has not been sufficiently addressed. To tackle this issue, we propose a cross-scale spectral calibration framework for spatiotemporal fusion (XSC-Net), which explicitly models and corrects spectral responses across different spatial scales. The proposed method introduces a spatial feature refinement block to enhance spatially discriminative structures and a hierarchical spectral refinement block to adaptively calibrate channel-wise spectral representations. By jointly exploiting spatial and spectral correlations, the proposed framework effectively suppresses spectral distortion while preserving fine spatial details. Extensive experiments on the public CIA and LGC datasets indicate that XSC-Net compares favorably with state-of-the-art methods, demonstrating superior performance over established baselines. Furthermore, ablation studies verify the efficacy and contribution of the proposed architectural components. Full article

Video action recognition faces persistent challenges in balancing accuracy with computational efficiency. While state space models, such as Mamba, have emerged with linear complexity advantages, they exhibit inefficiency in capturing critical spatiotemporal dependencies within video data. To address this core limitation, this paper proposes ETMamba, an enhanced architecture built upon the Mamba baseline. The ETMamba achieve performance breakthroughs via three core innovation modules: (1) the Spatiotemporal Feature Preservation module retains complete original spatiotemporal correlations before data flattening, solving the problem of spatiotemporal feature loss; (2) the Efficient Bidirectional Sharing strategy accurately models bidirectional temporal dependencies, enhancing key temporal dynamic information; and (3) the Spatiotemporal Collaborative Modulation mechanism combines global temporal and local spatial information to achieve collaborative capture of long-short term dependencies and fine-grained features. We conduct experiments on multiple benchmark datasets, achieving recognition accuracies of 88.3%, 74.6%, 75.7%, and 98.1% on Kinetics-400, Something-Something V2, HMDB-51, and Breakfast datasets, respectively, while maintaining low to medium computational complexity. Full article

Zenith Tropospheric Delay (ZTD) and its associated atmospheric water vapor information constitute essential environmental variables for Earth observation (EO)-based atmospheric monitoring and environmental variable retrieval. High-quality ZTD products are therefore of great importance for the post-processing, refinement, and reconstruction of atmospheric environmental variables at regional scales. Among existing observation techniques, Global Navigation Satellite System (GNSS) measurements provide high-precision ZTD estimates and have become an important means for retrieving tropospheric delay and water vapor. However, the sparse and uneven spatial distribution of GNSS stations limits their direct applicability for continuous environmental monitoring. Reanalysis-based products, such as ERA5 provided by the European Centre for Medium-Range Weather Forecasts (ECMWF), offer EO big data with excellent spatiotemporal continuity but suffer from pronounced systematic biases compared to precision GNSS retrievals, restricting their direct use in high-accuracy regional applications. To address these limitations, this study proposes a Residual Correction Kriging method for ZTD (RK ZTD) that integrates GNSS ZTD and ERA5 ZTD grids through a multi-source data fusion framework. High-precision GNSS ZTD is treated as reference data, and the differences between GNSS ZTD and ERA5 ZTD at modeling stations are defined as residuals to characterize the systematic bias in ERA5 ZTD grids. A Kriging interpolation algorithm is then employed to model the spatial distribution of these residuals and generate residual correction grids. By superimposing the interpolated residual grids onto the ERA5 ZTD grids, a refined and high-precision regional ZTD product is reconstructed. Experiments were conducted using observations collected in 2023 from 36 GNSS stations in the Netherlands, including 10 modeling stations and 26 independent validation stations, together with concurrent ERA5-derived ZTD grids. The results demonstrate that the proposed RK ZTD model provides spatially robust and high-precision ZTD products across the study region. The RK ZTD achieves a Root Mean Square Error (RMSE) of 5.70 mm, representing improvements of 58.4% and 35.4% compared with the original ERA5 ZTD (13.69 mm) and the GNSS-Kriging ZTD (8.82 mm), respectively. Moreover, the absolute bias is reduced to 0.41 mm, in contrast to 5.15 mm for the ERA5 ZTD, indicating that systematic biases are effectively mitigated. Spatial and seasonal analyses further confirm that the proposed method maintains stable performance across all seasons and significantly alleviates interpolation inaccuracies caused by sparse GNSS stations, even under extreme weather conditions such as Storm Ciarán, proving its value for advanced Earth environmental science applications. Full article

Load forecasting for Integrated Energy Systems (IESs) is critical to enabling multi-energy coordinated optimization and low-carbon scheduling. Facing multi-load types and multi-site high-dimensional heterogeneous data, there remains a global learning challenge stemming from insufficient representation of spatiotemporal coupling features. In response to the multi-source heterogeneous characteristics of IES loads, this paper designs a Spatiotemporal Topology Encoder that maps load data into a tensorized multi-energy spatiotemporal topological representation via fuzzy classification and multi-scale ranking. In parallel, we construct a MultiScale Hybrid Convolver to extract multi-scale, multi-level global spatiotemporal features of multi-energy load representations. We further develop a Temporal Segmentation Transformer and a Steady-State Exponentially Gated Memory Unit, and design a jointly optimized forecasting model that enforces global dynamic correlations and local, steady-state preservation. Altogether, we propose a multi-scale spatiotemporal fusion and steady-state memory-driven load forecasting method for integrated energy systems (MSTF-SMDN). Extensive experiments on a public real-world dataset from Arizona State University demonstrate the superiority of the proposed approach: compared to the strongest baseline, MSTF-SMDN reduces cooling load RMSE by 16.09%, heating load RMSE by 12.97%, and electric load RMSE by 6.14%, while achieving R² values of 0.99435, 0.98701, and 0.96722, respectively, confirming its feasibility, efficiency, and promising potential for multi-energy load forecasting in IES. Full article

Soil salinization severely threatens agricultural sustainability in saline–alkali regions, and high-throughput, efficient screening of salt-tolerant rice varieties is critical to mitigating this threat. Traditional evaluation methods are constrained by low throughput, limited spatiotemporal resolution, and the lack of standardized indicators. To address these gaps, this study established a multi-scale spectral phenotyping framework integrating ground-based hyperspectral, UAV-borne multispectral, and Sentinel-2 satellite remote sensing data for high-throughput screening of salt-tolerant rice. Field experiments were conducted with 12 rice lines at five key growth stages in Ningxia, China, with synchronous ground spectral measurements and UAV image acquisition on the same day for each stage. Five feature selection methods were employed to screen salt stress-sensitive hyperspectral bands, with classification accuracy validated via a Support Vector Machine (SVM) model. The results showed that: (1) rice spectral characteristics varied dynamically across growth stages, and first-order differential transformation effectively amplified subtle spectral variations in stress-sensitive regions; (2) the Minimum Redundancy–Maximum Relevance (mRMR) method outperformed other methods, achieving 100% classification accuracy at key growth stages, with sensitive bands dominated by red edge bands (58.33%); (3) the constructed Salt Stress Index (SIR) showed strong correlations with classical vegetation indices and rice yield, and could clearly distinguish salt-tolerant and salt-sensitive rice varieties, with stable performance against field environmental noise; and (4) band matching between UAV and Sentinel-2 data enabled multi-scale data fusion and regional-scale salt stress monitoring. This framework realizes the transformation from qualitative spectral description to quantitative salt tolerance evaluation, providing standardized technical support for salt-tolerant rice breeding and precision management of saline–alkali lands. Full article

Video Anomaly Detection aims to identify video segments containing abnormal events. However, detecting anomalies relies more heavily on temporal modeling, particularly when anomalies exhibit only subtle deviations from normal events. However, most existing methods inadequately model the heterogeneity in spatiotemporal relationships, especially the dynamic interactions between human pose and video appearance. To address this, we propose GSMTNet, a dual-stream heterogeneous unsupervised network integrating gated spatio-temporal graph convolution and multi-scale temporal learning. First, we introduce a dynamic graph structure learning module, which leverages gated spatio-temporal graph convolutions with manifold transformations to model latent spatial relationships via human pose graphs. This is coupled with a normalizing flow-based density estimation module to model the probability distribution of normal samples in a latent space. Second, we design a hybrid dilated temporal module that employs multi-scale temporal feature learning to simultaneously capture long- and short-term dependencies, thereby enhancing the separability between normal patterns and potential deviations. Finally, we propose a dual-stream fusion module to hierarchically integrate features learned from pose graphs and raw video sequences, followed by a prediction head that computes anomaly scores from the fused features. Extensive experiments demonstrate state-of-the-art performance, achieving 86.81% AUC on ShanghaiTech and 70.43% on UBnormal, outperforming existing methods in rare anomaly scenarios. Full article