Existing research on crude oil trade networks has largely focused on their static structural characteristics. However, systematic quantitative assessments of network stability, as well as examinations of the relationship between structural characteristics and stability, remain relatively limited. Based on United Nations Commodity Trade Statistics from 2000 to 2023, this study constructs an international crude oil trade network. By integrating complex network analysis with spatiotemporal methods, the study examines the network's evolutionary patterns, evaluates its stability from both topological and flow dimensions using Jaccard similarity and weighted similarity indicators, and applies Spearman's rank correlation to explore the associations between structural characteristics and stability. The results indicate that the following: (1) the international crude oil trade network exhibits a hierarchical core-periphery structure, with overall trade linkages between countries becoming increasingly tight; (2) key inflection points in network stability are correlated with major international events, and these correlations manifest differently across the dimensions of trade structure and trade flows; and (3) modularity is negatively correlated with topological stability and positively correlated with flow stability, while degree assortativity shows no significant association with either topological stability or flow stability, revealing that although the core-periphery structure enhances the resilience of trade scale, it may simultaneously weaken the flexibility of partnerships.

Urban commercial restructuring, driven by the closure of traditional supermarkets and the expansion of new-format superstores, creates a large-scale spatial reallocation challenge requiring scientific location-allocation methods. Traditional heuristic algorithms such as Genetic Algorithm (GA) struggle with discrete spatial optimization under 400+ candidate sites and complex geographic mask constraints: they converge slowly and easily fall into local optima. This study proposes a Deep Reinforcement Learning (DRL) framework named GeoPPO (Geospatial Proximal Policy Optimization) to address this gap. Using Xi’an’s retail restructuring as a case setting—427 candidate locations and multidimensional geographic features—the approach models spatial constraints via a gridded environment encoded as a five-channel state tensor. Key innovations include a dynamic action-constraint mechanism that masks invalid actions based on boundary rules and competition avoidance, and a curriculum learning strategy that enables stable convergence. The framework fills the need for methods that handle hard spatial constraints in large-scale location-allocation. Tests demonstrate rapid convergence within 1,000 epochs, achieving 75% average demand coverage—2.7% and 5.5% higher than GA and Particle Swarm Optimization (PSO), respectively. Ablation experiments confirm that Vanilla PPO without dynamic action masking fails to produce feasible solutions. The framework offers a feasible technical path for handling highly dynamic urban facility spatial configuration with geographic mask constraints.

The population-wide lifecourse cohort in Chibi (PowerCC) is the first city-wide, whole-population lifecourse cohort study in China, established to facilitate the precise prediction of disease risks at the individual level and cost-effective resource allocation at the societal level. It employs a data integration platform that, using ID numbers via application programming interfaces, links all sources/systems of dynamic health-related information of all residents in Chibi City (Hubei Province) and synchronizes the database on a regular basis. PowerCC contains basic health profiles, hospital records and health check-up records of all residents from healthcare facilities, follow-up information of those with hypertension/diabetes and a geriatric survey among all aged ≥55 years. As of the end of 2024, the 484,249 residents aged from birth to 105 years (51.61% being male) were included in PowerCC. Here we describe the rationale, design, data sources and maintenance of PowerCC, as well as disease prevalence, health status of all residents, utilization and costs of healthcare resources, and living conditions and needs of the elderly in Chibi. By providing a complete set of electronic health records for each individual, PowerCC enables the coordination of multiple stakeholders for precision health management and the researchers to conduct lifecourse research with unbiased samples. PowerCC is a city-wide, whole-population lifecourse cohort in China that uses a unified, ID-linked platform to integrate longitudinal electronic health records, including hospital data, routine health checks, chronic disease follow-up and geriatric surveys, for nearly half a million residents of Chibi from birth to old age.

High-resolution gridded population data are crucial for various fields. Estimating heterogeneous urban populations presents challenges due to nonlinear relationships between influential factors and population density, which vary spatially across grids within different land-use parcels. This study developed a Contextualized Geographically Weighted Neural Network (CGWNN) model to estimate population density on 100 x 100m grid cells in Beijing, China, using multi-source data. This model integrated the artificial neural network with geographically weighted regression to account for nonlinear associations that are similar across proximate grids. By incorporating parcel-level land uses as variable weights, it also considered contextually varying associations across proximate grids located in different land-use parcels. Our CGWNN model achieved superior accuracy (R2 = 0.85) compared to other models that ignored the aforementioned associations and widely used population datasets. The top three important variables were the distances to the nearest school, restaurant, and auto service, all negatively associated with population density. Additionally, the intensity of artificial light at night (ALAN) exhibited both positive and negative associations with population density in different regions, suggesting that the increased ALAN did not necessarily indicate higher population density in urban areas. Our modeling approach shows promise for accurate population estimation, which could be extended to larger areas, benefiting various fields.

As a crucial spatial constraint, directional relationships play an essential role in advanced spatial queries, spatial reasoning, image analysis, spatial indexing, and a variety of other applications. This paper concentrates on spatial cognitive tendencies and multiscale formal frameworks of directional associations within diverse contexts. We develop a multiscale pyramid cardinal direction model to fulfill the expression requirements in various application scenarios. The pyramid model integrates and extends existing models, thereby constructing a multiscale directional model that is suitable for spatial objects of different geometric types and varying expression accuracy demands. Firstly, it extends the direction-relation model of reference point by increasing the division from the basic directional tiles to segmentation directional tiles, thus enhancing the accuracy of qualitative directional description. Based on the reference point model, two layers of models for extended objects are further constructed, namely the nontopological overall matrix model and the topological local matrix model. The overall matrix model evolves the directional relations matrix to the segmentation directional matrix. It regards the reference line/polygon as a whole and constructs directional tiles with two levels of expressiveness. The local matrix model, based on topological references, conducts topological partitioning and directional tile partition for the minimum bounding rectangle region, addressing the expression of directional relations under complex topological relations. Simultaneously, the pyramid model constructs two types of models: qualitative and statistical matrices, catering to the needs of spatial similarity evaluation. Notably, the new model establishes flexible conversion channels between different scale models, enabling the model to enhance expression precision while ensuring computational speed and efficiency. The experimental results validate the higher accuracy of the new model and its feasibility across various scale application scenarios.

The strategic allocation of advertising billboards has become a critical aspect of urban planning and resource management. While previous studies have explored site selection based on road network and population data, they have often overlooked the diminishing marginal returns of overlapping coverage and neglected to efficiently process large-scale urban datasets. To address these challenges, this study proposes two complementary optimization methods: an enhanced greedy algorithm based on geometric modeling and spatial acceleration techniques, and a reinforcement learning approach using Proximal Policy Optimization (PPO). The enhanced greedy algorithm incorporates population-weighted road coverage modeling, employs a geometric series to capture diminishing returns from overlapping coverage, and integrates spatial indexing and parallel computing to significantly improve scalability and solution quality in large urban networks. Meanwhile, the PPO-based method models billboard site selection as a sequential decision-making process in a dynamic environment, where agents adaptively learn optimal deployment strategies through reward signals, balancing coverage gains and redundancy penalties and effectively handling complex multi-step optimization tasks. Experiments conducted on Wuhan’s road network demonstrate that both methods effectively optimize population-weighted billboard coverage under budget constraints while enhancing spatial distribution balance. Quantitatively, the enhanced greedy algorithm improves coverage effectiveness by 18.6% compared to the baseline, while the PPO-based method further improves it by 4.3% with enhanced spatial equity. The proposed framework provides a robust and scalable decision-support tool for urban advertising infrastructure planning and resource allocation.

Data acquisition and preprocessing is a core course on digital intelligence at Wuhan University that is designed to cultivate students’ understanding of data sources and improve preprocessing methods. The course aims at fostering digital thinking and literacy and enhancing intelligent computing skills. This study examined digital intelligence education and reform practices integrated into the data acquisition and preprocessing course, which covered web data, social sensing data, remote sensing data, sensor network data, unmanned aerial vehicle data, and 3D data. Moreover, the study explored the development and implementation of the course’s teaching platform, which was based on the open geospatial engine.

Prosperous waterway economics require rigorous safety measures. Unmanned aerial vehicle (UAV) offers massive images of inland waterways, within which navigation mark detection plays a critical role in ensuring waterway safety. This paper proposes a deep learning-based method for detecting navigation marks in UAV images. Firstly, a dataset of inland waterway navigation marks is constructed from UAV aerial images, which includes data collection, image enhancement, sample creation, and sample annotation. Secondly, a deep learning network model is developed, which uses ResNet-50 as the backbone, incorporates Coordinate Attention and Large-Scale Selective Kernel Attention mechanisms, integrates a Feature Pyramid Network (FPN) for feature enhancement, and uses Distance Intersection over Union (DIoU) as the loss function. Thirdly, the model is trained and evaluated on the constructed dataset, followed by precision assessment and post-processing. This paper explore a deep learning network model for small object detection in UAV images and establish a comprehensive workflow for detecting inland waterway navigation marks, thereby providing technical support for waterway safety.

Existing qualitative direction-relation matrix models employ rigid classification schemes, limiting their ability to differentiate directional relationships between multiple targets within the same directional tile. This paper proposes two quantitative matrix models for qualitative direction-relation with differing levels of precision. Based on directional tile partitioning derived from qualitative direction-relation models, the new models achieve quantitative expression of qualitative directionality through two distinct descriptive parameters: order and coordinate. The order matrix utilizes angular and displacement measurements as sequential variables, capturing the directional sequence characteristics within the same directional tile. The coordinate matrix employs direction-relation coordinates as matrix elements, integrating directional and distance relationships to identify the distribution of targets at varying distances along the same line of sight. These two novel models operate at distinct scales and achieve soft classification of directional relationships, substantially enhancing descriptive precision. Furthermore, they serve as foundational quantitative frameworks for the qualitative direction-relation models, establishing a bridge between quantitative and qualitative models. Experimental assessment confirms that the new models substantially improve directional relationship precision through their quantitative elements while supporting various application domains.

Urban villages, as a typical phenomenon in the process of urbanization, play a significant role in urban planning and sustainable development. However, their high-density structures and complex boundaries pose significant challenges for extraction tasks based on remote sensing imagery. To address these challenges, this paper proposes a Multi-domain Enhancement and Boundary Awareness Network (MEBANet) for urban village extraction. MEBANet consists of three core blocks: 1) The spatial-frequency-channel feature extraction block (SFCB), which simultaneously enhances feature representation in the spatial, frequency, and channel domains; 2) The multi-scale boundary awareness block (MBAB), which leverages dense atrous spatial pyramid pooling (DenseASPP) and multi-directional sobel operator convolution to strengthen the perception of complex boundaries; and 3) The deep supervision block (DSB), which accelerates model convergence through multi-level supervision signals. Experiments were conducted on three publicly available datasets from Beijing, Xi'an, and Shenzhen. The results demonstrate that MEBANet outperforms existing methods in terms of precision, recall, F1-score, and IoU. Additionally, cross-dataset transfer experiments validate the robustness and generalization capability of MEBANet. Ablation studies further confirm the effectiveness of each block. This study provides a high-accuracy and automated solution for urban village extraction from high-resolution remote sensing imagery, offering valuable insights for urban planning and management.

The COVID-19 pandemic has impacted all sectors of society, with effects that have been acutely experienced at the local, national, regional, and global levels. This study examined the heterogeneous impacts of and vulnerability to COVID-19 for promoting urban sustainability and resilience. We performed a scoping review on the basis of the relevant literature from the Web of Science and PubMed, and a national survey conducted among a total of 5,376 participants in early 2020. The survey adopted a repeated cross-sectional design to study changes in residents’ risk perception of COVID-19 across the three stages (21–23 January, 27–28 February, and 24–27 March), using a snowball sampling method to recruit 2,144, 2,021, and 1,211 participants, respectively. This study revealed that the spatial, social, economic, and health impacts of COVID-19 have not been distributed evenly among populations, with specific individuals and communities more vulnerable than others. Among the determinants of these inequalities are socioeconomic status, housing arrangements, and working requirements, which influence the extent to which people can safely adhere to stay-at-home and social distancing policies and how they perceive risks. Additionally, racial/ethnic minorities face differing risks, in part because of socioeconomic factors but also because some groups experience higher shares of comorbidities. Moreover, overall, these risk factors are the healthcare systems meant to shield individuals and communities from pandemic impacts, which, however, have become increasingly taxed due to the sudden influx of patients and the resultant shortages of resources – including crucial personal protective equipment to minimize interpersonal transmission. Understanding the heterogeneous impacts of and vulnerability to COVID-19 could inform the design of environmentally sustainable and socially resilient cities, making them better equipped to encounter future epidemics. This study would help us identify more effective and equitable solutions to the ongoing challenges of the pandemic, promoting sustainability and resilience at multiple societal levels.

Recent geopolitical crises have reshaped global shipping patterns, profoundly impacting related carbon emissions. Here, we utilize automatic identification system data from March 2021 to February 2024 and the ship traffic emission assessment model to investigate changes in carbon dioxide emissions from shipping in the Black Sea region before and during the Russia-Ukraine war. We find that shipping carbon dioxide emissions in Ukraine's Black Sea exclusive economic zone decreased by an average of 17.88% annually, while those in Romania's and Turkey's Black Sea exclusive economic zones increased by 36.30% and 16.08% annually, respectively. At the voyage level, shipping carbon dioxide emissions from maritime trade between Russia and the European Union obviously decreased, while those from maritime trade with certain Asian and Middle Eastern countries have obviously risen. The findings uncover the challenges to the climate change goal in the global shipping sector due to regional geopolitical crises.

Spatial heterogeneity or nonstationarity in spatial data and relationships has elicited increasing attention in the field of spatial statistics.To explore this fundamental phenomenon,researchers have extensively developed place-or location-specific methods and local statistical techniques that assume data relationships to be spatially variant.In line with the principle of spatial dependence depicted by the first law of geography,the Geographically Weighted(GW)regression technique was proposed to incorporate spatial weights into location-wise regression model calibrations to highlight spatial heterogeneities in data relationships by outputting spatially varying coefficient estimates.With this distance-decaying schema for calculating spatial weights,a series of GW models has been proposed for fine-scaled spatial analysis in descriptive,explanatory,interpretive,and predictive scenarios,including GW descriptive statistics,basic GW regression and extensions,GW discriminant analysis,GW principal component analysis,GW machine learning,and GW artificial neural network.These GW models form a continually evolving technical framework for identifying spatially nonstationary features or patterns in various disciplines or fields,including geography,social science,biology,public health,and environment science. In this study,we systematically sorted the theoretical and technical frameworks of GW models.First,we summarized the essence and rules for applying the family of GW models,including catering for spatially heterogeneous or nonstationary features and relationships in geographic variables and outputting location-dependent metrics or estimates by calculating the spatial weight matrix and the distance-decaying principle of spatial dependence presented by Tobler's first law of geography.With regard to the common and fundamental parts of GW models,we conducted hypothesis tests on spatial heterogeneity or nonstationarity,provided a general definition of distance metrics in geography,calculated spatial weights,and performed bandwidth optimization. With regard to descriptive,explanatory,interpretive,and predictive scenarios,the potential usages of each GW model were discussed from four analysis perspectives.We recommend the use of univariate GW descriptive statistics,such as GW average,GW quantile,GW standard deviation,and GW skewness,to help users grasp the spatially heterogeneous distribution of a geographic variable.For exploratory data analysis with multivariate spatial data,the GW correlation coefficient and GW principal component analysis are recommended.GW regression and its rich extensions,especially multiscale GW regression,are powerful tools in interpretive analysis and have been widely applied.When data relationships are studied comprehensively,accurate predictions are usually obtained in data analytics.The usages of GW regression and geographically and temporally weighted regression in predictions are straightforward,and the prediction accuracy is further improved when artificial intelligence technologies,such as GW machine learning,GW artificial neural network,and geographically neural network weighted regression,are incorporated. The increasing popularity of GW models has resulted in the development of several software packages,standalone programs,and toolkits,including the R package GWmodel and GWmodelS,which are new,free,user-friendly,high-performance standalone software that incorporate spatial data management and mapping tools and GW model functions.However,further improvement is needed before GW models can become all-around,quantitative,analytical frameworks for spatial heterogeneity because of drawbacks in theoretical foundation,technical completeness,complementarity,and evolution to spatiotemporal dimensions.

With the support of spatial-temporal data analysis technologies and network science, the International Trade Network (ITN) research has made significant progress, demonstrating broad application prospects in mining market evolution and predicting trade dynamics. Based on all ITN research cases from 2003 to 2023, this paper presents a research framework for ITN analysis, reviewing its advancements in data collection, visualization, topology analysis, structure prediction, and correlation analysis, where the spatial-temporal data analysis technologies have provided crucial methodologies and insights. A multilevel scenario construction theory for complex networks is proposed, highlighting the great significance of spatial regression models and system dynamics models in identifying global mechanisms; the unique value of temporal network analysis under the support of time-series information is discussed. Given the existing limitations, the development of more granular and reliable datasets utilizing big data technologies, as well as the construction of richer spatial-temporal scenarios, are considered as future research agendas.

Individual mobility prediction forecasts traveling activities of an individual traveler, and has wide applications in location-based services, public health, and transportation planning. Whereas, it remains challenging due to the complexity and uncertainty of human mobility. Existing methods mainly consider spatiotemporal contexts in current traveling, but overlook those in historical trips, as well as relationships between traversed road intersections. These issues hinder the model from effectively capturing complex mobility patterns. To fill this gap, we propose a novel method that incorporates current traveling features and historical activity chain to predict the coordinates of traveling destination. Specifically, (1) we construct current traveling features by extracting real-time moving states, and represent spatiotemporal correlations between traversed road intersections using word embedding; (2) we learn travel intentions as a probability vector for each historical trip, and combine it with spatiotemporal features to construct historical activity chain; (3) we construct an individual mobility prediction model using Long Short-Term Memory (LSTM) network and spatiotemporal scoring mechanism, to capture short-term and long-term dependencies in current trip and historical activity chain, respectively. Experiments on 21,890 trajectories over the whole Year 2019 of 20 representatives selected from 1916 private car travelers in Shenzhen City, reveal the effectiveness of our model. It outperforms four baselines, Random Forest (RF), Distant Neighboring Dependencies (DND), Location Semantics and Location Importance (LSI)-LSTM, as well as Intersection Transfer Preference and Current Movement Mode (ITP-CMM), by approximately 10%-15% improvement in accuracy. In addition, we further explore the impact of historical activity chain length, and destination visiting frequency on prediction, as well as the relationship between predictability and eight mobility pattern features. This study benefits potential applications such as personalized location-based service recommendations and targeted advertising, and also provides implications for understanding human mobility.

Timely and accurate mapping of urban functional zones (UFZs) is crucial to urban planning and management. Although existing methods for identifying urban functions have made remarkable progress, they still suffer from limitations, such as high sample dependency, insufficient semantic relationship representation, and poor interpretability due to being data-driven models. To bridge this gap between these methods and the way humans identify functional areas, a new framework that couples domain knowledge and remote sensing images was proposed for the mapping of UFZs. First, to model the concepts, attributes, and spatial and semantic relationships of urban functional objects, a UFZ knowledge graph (UFZ-KG) was constructed to assist in the mapping of UFZs. Then, the contrastive language-image pretraining model was adopted to encode jointly the semantic features of UFZ-KG and the visual features of UFZ images. In this model, a nonlinear embedding module was designed to achieve semantic alignment of these two different modal features in shared space. The effectiveness of the proposed method was verified in three test areas in Shenzhen, China. Results demonstrate that the proposed method of coupling UFZ-KG with satellite images significantly enhances the UFZ classification accuracy compared to the method that solely relies on image features. Furthermore, it exhibits good generalization performance.

In light of rapid economic and urban growth, the proliferation of structures including transmission towers, signal poles, and wind generators has become evident. Consequently, precise object detection of these structures emerges as a pivotal approach to enhance infrastructure management. This technique establishes a robust foundation for achieving elevated efficiency, precision, optimized energy management, and heightened safety monitoring. This article introduces a novel model for detecting structure based on channel and large-scale selective kernel (CLSK) model using high-resolution images. The method is rooted in a two-stage target detection network, enabling simultaneous identification of both primary structures and their associated shadows. The incorporation of deformable convolutions augments the model's ability to extract intricate features. Moreover, the introduction of the innovative LSK attention module, along with the CLSK attention module, enhances the optimization of features gleaned from the network's core architecture. Simultaneously, the complete intersection over union loss function refines the network's focus by considering parameters such as center point distance and aspect ratio in addition to the conventional overlapping area. This comprehensive approach facilitates improved feedback on detection outcomes. Empirical evaluation of the proposed network underscores its superior performance when juxtaposed with both conventional network models and the rotating detection box network.

The international migration network, comprising the movements of people between countries, is one of the most important global systems of interaction, which can reflect the complex international relations of economics, cultures, and politics and has huge impacts on global sustainability. However, the conventional gravity model cannot model its complicated interactions accurately. In this article, we propose a novel reverse gravity model using genetic algorithm to reconstruct the complicated interaction patterns with high accuracy. To verify the feasibility of our method, it was applied to a series of international migration networks. We found that the derived node attractions were highly correlated with socioeconomic factors and network metrics, and the calculated node positions outperformed the geometric centers from the perspective of human migration that related to economy and demography. Our approach could be a preferred choice to investigate the spatial–temporal interactive patterns in geographical space, facilitating comprehension of the mechanisms underlying their generation and evolution.