Understanding urban functional regions (UFRs) is essential for spatial planning and governance. Existing approaches typically rely on static points of interest (POI) or mobility data to delineate functional zones, but they often fail to capture the dynamic coupling between physical space and human activities and overlook population attributes, which are a fundamental parameter underpinning both spatial units in urban planning and human activities. To address this limitation, we propose a Dual-Information Entropy Model (DIEM) that explicitly synthesizes the structural signals of POI distribution and the dynamic usage intensity of Wi-Fi mobility records. By further incorporating population portrait data, the proposed framework moves beyond static functional classification toward comprehensive, human-centric profiling of urban regions. Applied to Beijing's Fourth Ring Road, DIEM significantly outperforms baseline zoning strategies, achieving an Overall Accuracy of 0.896 and a Kappa coefficient of 0.885. More importantly, the results reveal two key patterns: UFRs display temporal elasticity, shifting from concentrated production-oriented structures on workdays to fragmented consumption and life-oriented patterns on holidays; and population dynamics exhibit systematic restructuring, with clear variations in age, gender, and educational attainment across functional regions. These findings highlight the value of incorporating demographic dimensions into urban functional analysis and provide new insights for adaptive, human-centered urban planning.

Night-time light (NTL) data, exemplified by the Black Marble dataset, has shown significant application potential across multiple domains due to the rich information that they provide on nocturnal light emissions. However, the VNP46A2 product, which is limited by considerable challenges stemming from extensive missing values. This problem is resolved through gap-filling methods, but existing approaches mostly disregard the spatiotemporal relationships and interactions in NTL measurements, thereby constraining efforts to treat temporal abruptness of NTL data, and ineffectively addressing the issue of numerous missing values. To overcome these deficiencies, we developed a gap-filling method based on graph neural networks (GNNs) considering spatiotemporal anisotropic geometric relationships. The method includes a graph construction algorithm from spatiotemporal cubes and a GNN model capturing spatiotemporal anisotropy. Its applicability is further enhanced by the fact that its application requires no prior knowledge. Experiments demonstrated the model's high accuracy (R2 = 0.95 on the test set) and strong generalization. The gap-filled NTL data closely matches actual data in terms of morphology, intensity, and spatial continuity, outperforming other four different methods in consistency and dynamism. Ablation studies confirm the model's rational design with no computational redundancy. This approach provided a novel solution for remote sensing data imputation, supporting urban studies while expanding the application prospects of daily NTL products.

Precise discrimination of basalt tectonic settings serves as a crucial methodological approach for providing insights into Earth's history. To address the limitations of traditional discrimination methods, which include high subjectivity due to reliance on expert experience and restricted precision resulting from simplistic comparative analysis of geochemical elements, we developed an innovative discrimination model-the Element Matrix and Series Parallel Network (EMSPN). The model enhances the capacity of tectonic setting discrimination by integrating the correlation characteristics between geochemical elements and the sequential features of element reactivity, thereby obtaining more comprehensive lithogenetic information. Based on >39,000 geochemical analyses of basalts from 9 typical tectonic settings after the Archaean period, we conducted application demonstrations through preprocessing operations, including feature engineering, missing value imputation, and category balancing. The proposed model demonstrated superior performance across multiple evaluation methods, achieving an overall discrimination accuracy of 88 %. This study compared the proposed model with four traditional machine learning models as baseline methods, and the results showed that the model outperformed other traditional machine learning models in overall discrimination accuracy across 9 tectonic settings. Additionally, in ablation experiments, by systematically removing key components of the EMSPN, the results validated the model design's rationality and confirmed each module's importance in information extraction and feature learning. Using the SHapley Additive exPlanations (SHAP) method, we analyzed and discussed the importance of different elements in discrimination results and the geochemical characteristics across various tectonic settings. When applied to controversial Archaean basalt samples, the results confirm the conclusions from traditional geochemical analysis methods, demonstrating the model's geological reliability and practical significance. This research provides a reliable technical approach for the field of lithogeochemistry and retrieves geodynamic information through tectonic setting discrimination, contributing to more accurate reconstruction of Earth's tectonic history.

Discovering spatially associated objects involves measuring objects’ similarities and retrieving associated objects. The integration of spatial topology and network models for discovering associated objects remains largely unexplored. Here, the concept of a maximum topological accessibility path was developed to quantify objects’ similarity attenuation. Considering the topological accessibility and spatial feature similarity of network nodes, an approach named the Weighted Similarity measure method considering Topological Accessibility (WSTA) is proposed to measure object association. The WSTA can capture both spatial interaction patterns and topological relationships in complex urban environments, thereby improving the accuracy of spatially associated object discovery. The proposed approach is validated using real-world point-of-interest (POI) datasets from Beijing city. The results suggest that integrating topological relationship approaches yields significant accuracy improvements in existing baseline methods, thereby enriching geospatial data retrieval in the era of big geospatial data.

The spatial attention mechanism has been widely employed in the semantic segmentation of remote sensing images due to its exceptional capacity for modeling long-range dependencies. However, the analysis performance of remote sensing images can be reduced owing to their large intra-class variance and complex spatial structures. The vanilla spatial attention mechanism relies on the dense affine operations and a fixed scanning mechanism, which often introduces a large amount of redundant contextual semantic information and lacks consideration of cross-directional semantic connections. This paper proposes a new Cross-scan Semantic Cluster Network (CSCN) with integrated Semantic Filtering Contextual Cluster (SFCC) and Cross-scan Scene Coupling Attention (CSCA) modules to address these limitations. Specifically, the SFCC is designed to filter redundant information; feature tokens are clustered into semantically related regions, effectively identifying local features and reducing the impact of intra-class variance. CSCA effectively addresses the challenges of complex spatial geographic backgrounds by decomposing scene information into object distributions and global representations, using scene coupling and cross-scanning mechanisms and computing attention from different directions. Combining SFCC and CSCA, CSCN not only effectively segments various geographic spatial objects in complex scenes but also has low model complexity. The experimental results on three benchmark datasets demonstrate the outstanding performance of the attention model generated using this approach.

Long-tailed distribution is a common issue in remote sensing image classification (RSIC), and many datasets suffer from severe class imbalance. This imbalance often causes the classifier to focus on the head classes with more samples, neglecting the tail classes. As a result, the precision of the tail classes is reduced, which in turn affects the generalization ability of the classifier. To address this problem, a hybrid network based on cross-space learning and perception-driven mechanism (CLPM) is proposed to improve the classification accuracy of samples from the tail classes. The CLPM network consists of three components. The cross-space representation learning branch is designed to enhance the representation capability of tail-class samples by integrating multiscale and multiregion spatial features. In parallel, the adaptive perception classification branch dynamically adjusts the receptive fields to improve generalization across different resolutions and challenging scenarios. In addition, the CLPM innovatively applies the von Mises-Fisher (vMF) distribution to remote sensing images for high-dimensional interclass feature modeling. Building on this, a vMF-based contrastive loss function is proposed. This approach effectively coordinates the learning processes of head and tail classes while enhancing the precision of feature representation. The effectiveness of CLPM is validated on datasets with varying balance ratios, including SIRI-WHU, CLRS, and NWPU-RESISC45. Results show that CLPM significantly improves tail classes accuracy while maintaining high recognition rates for head and middle classes. Compared with the existing methods, CLPM has significant advantages in the overall recognition accuracy, the long-tailed problem, and diversity adaptation.

Deep learning based subway passenger flow prediction was widely employed to promote prediction accuracy, which is crucial for subway management and commercial infrastructure planning. However, the existing work ignored the semantic similarity inherent in the subway stations function, which can extract passengers and enhance prediction accuracy. In this work, a Semantic-Augmented Spatio-temporal Graph Convolutional Network (SASTGCN) model was proposed, which considered semantic similarity, spatiotemporal correlations and spatial heterogeneity to realize the passenger inflow and outflow prediction. The station function was derived from travel characteristics of passengers by data-driven method. The spatiotemporal block including Topology Adaptive Graph Convolutional Network (TAGCN) and ConvNeXt, constructed adaptive spatial topology, depthwise separable convolution and expanded receptive fields to capture spatiotemporal correlations and spatial heterogeneity. The SASTGCN model was validated with the card swiping data in Shanghai, the prediction ability and error analysis results demonstrated the performance outperform nine baseline methods, and the accuracy was improved by approximately 21%. The proposed model can provide inspiration for the follow-up research of passenger flow prediction, traffic pattern recognition and dynamic scheduling.

With urbanisation and population growth, understanding spatial interactions in cities is increasingly vital for urban management. In recent decades, spatial interactions could be predicted accurately with the support of large GPS data, but anonymous trajectory data lacks semantic details, limiting predictions and behaviour understanding. To address this, we proposed a Semantic-Integrated Mobility Trajectory Model (SMTM), integrating social media check-in data, remote sensing imagery, and taxi trajectory data capable of accurately predict travel flow. Specifically, Convolutional Neural Networks (CNN) and Long Short Term Memory (LSTM) extract demographic insights, Graph Convolutional Networks (GCN) and Gate Recurrent Units (GRU) are incorporated to predict spatial interaction intensity. We conducted two case studies in New York City, U.S., and Ningbo, China, using taxi trips (over three million trips in New York and nearly one million trips in Ningbo) and social media check-in data (around 60,000 records for each city). Results demonstrate excellent performance over baselines. Furthermore, the integration of travel trajectories and census data revealed diverse travel preferences at various scales, including intra-region, inter-region, and inter-urban. The SMTM model contributes to optimising the design of public spaces and personalised recommendations.

The precise time series prediction method is the key technology for the monitoring and management of ground deformation. Current prediction methods mostly rely on independent sampling points for prediction, limiting the effective utilization of spatial features by the model, thereby affecting the overall spatial prediction accuracy, and it also restricts the prediction efficiency of the model. In response to the above-mentioned issues in previous research, this study proposes a Time Distributed Fully Connected (TDFC) Recurrent Neural Networks (RNNs) framework that integrates Temporal Convolutional Attention Mechanism (TCAM) for joint prediction of sampling points in time series Interferometric Synthetic Aperture Radar (InSAR) surface deformation data. Firstly, based on Sentinel-1A imagery over the Beijing Plain, the time series surface deformation data from May 2017 to April 2020 are obtained utilizing the Small Baseline Subset InSAR (SBAS-InSAR) technology. After data processing and production into a dataset, based on the TDFC-RNNs framework integrated with TCAM, five different RNN structures were used as prediction modules to construct time series prediction models for InSAR surface deformation. To investigate the effectiveness of the TCAM module on prediction performance, ablation experiments were conducted specifically targeting it. Furthermore, to explore the relative optimality choice of prediction modules under the current dataset and the compatibility of this framework with non-RNN structures, various other sequence models were selected as prediction modules. The predictive performance of the models constructed by this framework was compared in two aspects with benchmark methods, ablation models, and other exploratory models. This included evaluating the predictive results of the test set using various metrics and analyzing the trends in numerical characteristics of the predicted results for the next 60 time steps (720 days). The comprehensive comparison results indicate that the model constructed by this framework outperforms other methods or models in terms of overall performance across various evaluation metrics. At the same time, the future predicted results exhibit more reliable numerical characteristics, aligning well with the developmental trends of surface deformation. This suggests that the above-mentioned models demonstrate favorable predictive capabilities for time series InSAR surface deformation. Such results can be instrumental in intuitively assessing the overall situation of surface deformation in the study area, promptly identifying risks, and swiftly implementing measures to address potential hazards.

Understanding spatial interactions in urban environments has become critical in the context of spatio-temporal big data. However, Spatial–temporal big data often exhibit non-uniformity, necessitating the imputation of spatial interaction relationships derived from the analysis of such data. Previous studies often used simplified grid-based or TAZ approaches that ignore the complex interactions for spatial interaction imputation, leading to limitations in accuracy. In this paper, we proposed a two-layer spatial interaction imputation framework (SIF) for accurate multi-scale spatial interaction imputation. To our knowledge, this is the first time that we impute spatial interactions in multi-scale urban areas. In the first layer, it utilised a hierarchical spatial units division algorithm inspired by Shannon’s information entropy to hierarchically classify study area using point of interest (POI) data; In the second layer, it integrates the classified areas and travel flow data into a spatial interaction graph convolutional network (SI-GCN) for spatial interaction imputation. Two case studies were conducted in Beijing, China and New York City, USA, using over eight million taxi data and one million bike-sharing data. The results showed the superior performance of SIF compared to baseline models. The results also analysed the travel behaviours in both Cities, as well as the impact of social, economic and environmental factors on passengers’ spatial choices when travelling.

Spatial interaction research is particularly important for geographical analyses, as it plays a crucial role in extracting travel patterns. However, previous studies on spatial interactions have not adequately considered regional population variations over time, resulting in insufficiently precise travel predictions. Moreover, the threshold of spatial correlations is difficult to determine. Existing studies have assumed fully connected spatial correlation matrices, which is not realistic. To address these limitations, we proposed the Self-paced Gaussian-Based Graph Convolutional Network (SG-GCN) to automatically estimate the threshold of spatial correlations for travel flow predictions. It incorporates a temporal dimension into spatial relationship matrices to enhance the accuracy of vehicle flow predictions. In particular, Gaussian-based GCN identifies patterns in a time series of regional flows, enabling more precise capturing of spatial relationships while fusing node and edge features. Building on this model, self-paced contrastive learning automatically sets thresholds to determine the presence or absence of spatial relationships. The model's performance was verified through two empirical case studies conducted in New York City, USA, and Ningbo, China, using 2.8 million bicycle-sharing records and 1.25 million taxi trip records, respectively. The proposed model helps delineate mobility patterns in cities of varying scales and with different modes of transportation.

Prediction of high-risk areas for urban crime is of great significance for maintaining public safety and sustainable development. However, existing approaches are deficient in spatiotemporal sensitivity and perceptivity, which make it difficult to extract the spatiotemporal dependency from uneven and sparsely distributed data. To address this problem, the novel multi-scale neural network models, namely ST-HGNet and ST-HGNet(a) with attention, were proposed. It is dedicated to further exploring spatiotemporal patterns and improving hotspot location prediction accuracy for sparse types of crimes. First, multi-scale conception and attention mechanisms were introduced to address the receptive field range fixed problem. It enhanced representation of captured information by exposing spatial "scale" dimension and assigning weight relationships. Then, novel multi-scale hierarchical gating architecture was designed that has two forms of whether to add attention or not, to enhance the sensitivity of features and the perception of sparse features by filtering the valid information at different scales. Ultimately, the periodic temporal components were used to capture different time-trend dependencies. The proposed model adopted well-known Chicago assault crime dataset as a case study. Compared with five common benchmark models, the results show that the ST-HGNet model outperformed other baseline models and achieved higher prediction accuracy at multiple level spatial resolution. In particular, ST-HGNet(a) with self-attention achieved the greatest improvement at 1000 m, with a mean hit rate of more than 84%.

As the spatial structure of cities becomes increasingly complex and sustainable development goals are promoted, society places higher demands on the management and planning of cities. As the basic unit of urban analysis, the combination pattern and scale shape of urban spatial units are crucial for rational management and planning of cities. However, existing urban analysis management systems often adopt a prefabricated fixed cell division method, which is difficult to meet the needs of high precision and multi-scale analysis of urban information. Therefore, this paper proposes an interactive dynamic partitioning technology, and designs a multi-scale dynamic partitioning system for urban spatial units (SUPS), in order to meet the diverse needs of urban management and planning. The system consists of a data management module, a spatial unit module, an integration module and a visualization module. The system not only realises the multi-scale dynamic partitioning of spatial units in the form of interactive operation, but also obtains more detailed identification results by applying the multi-scale spatial units to the identification of urban functional areas, verifying the effectiveness and feasibility of the interactive multi-scale dynamic partitioning of spatial units, and providing a new technical support for fine urban management.

Traffic flow forecasting is crucial to Intelligent Transportation Systems (ITS), particularly for route planning and traffic management. Spatiotemporal graph neural networks have been widely used for this purpose, where a global graph structure is mainly used, but local graph features are ignored. Multi-scale spatiotemporal features—the combined application of global and local graph features—can help effectively discover the underlying spatiotemporal patterns. This study proposed a multi-scale adaptive spatiotemporal forecasting model called Adaptive SpatioTemporal InceptionNet (AST-InceptionNet). To enrich the captured features and extract multi-scale spatiotemporal ones, the inception part is applied to combine local spatiotemporal features with several global ones. Additionally, we developed a fully adaptive graph convolution method, including topologically adaptive graph convolution and an adaptive adjacency matrix. It can autonomously and dynamically learn spatial heterogeneity and enable the proposed model to work with unknown adjacency relations. The proficiency of AST-InceptionNet was validated using four publicly available real-world traffic flow datasets. The experiments demonstrate a satisfactory performance from the proposed model, outperforming existing state-of-the-art methods by up to approximately 12%.

时空伴随模式是具有时空伴随关系的视频对象组合.为了从海量视频数据中快速发现符合查询条件的时空伴随模式,提出一种基于三重剪枝匹配策略的时空伴随模式发现算法——MPA.首先,利用已有的视频对象识别和跟踪模型对视频对象进行结构化提取;然后,对提取的连续帧中大量重复出现的视频对象进行压缩存储并构建索引;最后,设计基于前缀树的时空伴随模式发现算法,以快速发现符合查询条件的时空伴随模式.在真实数据集和合成数据集上的实验结果表明,与暴力搜索算法(BFA)相比,所提算法的效率提高了30%左右,且数据量越大,效率提高越明显.因此,所提算法能够快速发现海量视频数据中满足查询条件的时空伴随模式.

In the last decade, the event knowledge graph field has received significant attention from both academic and industry communities, leading to the proliferated publication of numerous scientific papers in diverse journals, countries, and disciplines. However, a comprehensive and systematic survey of the recent literature in this area to obtain how the development of event knowledge graph evolves over time is lacking. To address this gap, we performed scientometric analyses utilizing the CiteSpace software of version 6.2.R4 package to extract and analyze data from the Web of Science database, including information about authors, journals, countries, and keywords. We then constructed four networks, including the author co-citation network, journal co-citation network, collaborative country network, and keyword co-occurrence network. Analyzing these networks allowed us to identify core authors, research hotspots, landmark journals, and national collaborations, as well as emerging trends by assessing the central nodes and nodes with strong citation bursts. Our contribution mainly lies in providing a scientometric way to quantitatively capture the research patterns in the last decade in the event knowledge graph field. Our work provides not only a structured view of the state-of-the-art literature but also insights into future trends in the event knowledge graph field, aiding researchers in conducting further research in this area.

Assessing jobs-housing balance (JHB) is crucial for the optimization of urban spatial pattern and transportation planning. However, due to the limitations of traditional data and the inability to integrate evaluation indicators, the evaluation results may be bias, conflicting with common sense. Considering interaction of multiple factors, a Job-housing balance measurement model (JHBM-SEM) was proposed to accurately evaluate the degree of JHB in a certain area. To address the problem of multi-indicator fusion, the structural equation model is used to incorporate the advantages, limitations and complementary relationships of each evaluation indicator into the evaluation process. A function relationship is defined between factor loadings, path coefficients, and variable scores to construct the measurement model and obtain comprehensive evaluation results. In addition, by integrating multi-source spatiotemporal big data mainly based on mobile signaling data, the paper can effectively mine the current status of job-housing balance in cities, and solve problems such as low precision and granularity of traditional data. The model was validated using Shanghai as an example, and the results show that compared with classical methods, the model's results are more consistent with the real situation of regional jobhousing patterns. It can identify the pseudo-balance phenomenon in underdeveloped areas of the suburbs and make reasonable evaluations, and the intermediate process can explain the direction of the imbalance factors in the region.

Geoparks contain various geological relics and peculiar geological landscapes, which have good ornamental value and are non-renewable precious wealth. Today, with the deterioration of the natural environment and the impact of human activities, the geopark has been destroyed to a certain extent, but the current research methods on the geopark are still mostly traditional propaganda methods with a single method. This study takes the geoparks in Southwest China as the research object, establishes a geopark management system, realizes the display, query, statistical rendering, distribution analysis and impact factor analysis of geoparks in the region, not only intuitively reflects the distribution of geoparks, The GIS analysis method is also introduced to explore the regularity of their distribution and the factors affecting the distribution, so as to provide reference for the protection, planning and construction of subsequent geoparks.

The prediction of parking occupancy is of great importance to urban planning. As the number of cars increases and parking resources become limited, the lack of parking supply has become a challenge for urban design. Previous works ignore the correlation between car parks when predicting parking occupancy, which limits the accuracy of the prediction. To address this issue, this study proposes a Temporal-GCN-based correlated parking prediction model (CPPM) to forecast the temporal occupancy of car parks. In particular, the model utilises Convolutional Neural Networks (CNN) and Bayesian probabilities to extract street view similarities in car parks, as well as their spatial correlations, cosine similarity is used to calculate the activity type similarity, and Graph Convolutional Networks (GCN) and Gate Recurrent Units (GRU) are integrated to predict spatio-temporal car park occupancy, taking into account both temporal parking records, similarities in car parks, and their spatial correlations. We conducted two case studies in Ningbo and Beijing, China, integrating over 10 million parking sensing records and corresponding street view images of parking lots to predict parking occupancy. The results show that our model has outstanding performance over the baselines and can be extended for various types of car parks in cities of different sizes and different levels of development. The results also reveal the parking preferences of the citizens of Ningbo and Beijing, which is valuable for a quantitative understanding of commuters' parking patterns and behaviour and can be used as a guide for urban planning and management.

City portrait is a social impression generated by the interaction between the public and the city, which can help us better understand and perceive the nature and characteristics of the city, and thus provide strong support for the development and governance of the city. However, most existing studies extract thematic semantic labels globally, but ignore the order of the tags and the degree of their contribution in the topic, which affects the city portrait extraction results. In addition, existing studies also lack the analysis of the impact of grid areas as the study scale on city portraits. In this paper, we propose a new approach to accurately identify city labels based on multi-source data grid fusion using a topic feature word extraction model (Weight-LdaVecNet) with fused topic word embedding and network structure analysis with feature word weight constraints. On this basis, we construct a multi-level city portrait description framework using hierarchical cluster analysis, extract tag clusters, and obtain a similarity matrix by combining topic feature tags and region feature tags using similarity analysis to construct a multi-level city region portrait, with a view to achieving a fine-grained construction of a multi-level city portrait. The experimental results show that, compared with the traditional LDA model, our method indicates that the identified city labels with similar thematic semantics have strong aggregation, thus proving the effectiveness of our proposed method. In addition, in the overall multi-level city portrait, we find that Beijing has a strong attractiveness in terms of cultural features. However, the regional distribution of cultural characteristics dimensions is not uniform in the multilevel city-region portrait, and better rational allocation and planning of cultural resources are needed to better meet people's needs.