The new smart city is an inevitable requirement for the development of urban digitalization to intelligence and further to wisdom, and is an important part of achieving high-quality development. This paper first introduces the background and basic concept of smart city, and analyzes the relationship and difference between the three stages of digital city, smart city and new smart city. Digital cities use computer networks, spatial information and virtual reality to digitize urban information, and focus on building information infrastructure. Smart cities, on the other hand, use spatio-temporal big data, cloud computing, and the Internet of Things to integrate systems across urban life, emphasizing intelligent management through a unified digital platform. New smart cities combine technologies such as digital twins, blockchain, and the meta-universe for citywide integration, and employ AI-based intelligent lifeforms for decision-making, blending real and virtual elements for advanced city management. This paper then explores the construction of new smart cities, focusing on high-quality urban development driven by technology and societal needs. It highlights the transition from digital to smart cities, emphasizing the role of information infrastructure and intelligent technology in this evolution. The paper discusses key technologies such as 3D urban modeling, digital twins, and the metaverse, and details their impact on urban planning and governance. It also examines how smart cities contribute to economic growth, meet national needs, and ensure public health and safety. The integration of technologies such as AI, IoT, and blockchain is shown to be critical to creating connected, efficient, and sustainable urban environments. The paper concludes by assessing the role of smart cities in measuring economic development, demonstrating their potential as a benchmark for national progress. Finally, based on the latest advances in AI technology, this paper analyzes and systematically looks forward to the key role AI can play in building new smart cities. AI's ability to analyze massive amounts of data, improve decision-making, and integrate various urban systems all provide important support for realizing the vision of a truly smart city ecosystem. With the synergy of "AI + IoT", "AI + Big Data", "AI + Big Models", and "AI + High Computing Power", the new smart cities are expected to achieve an unparalleled level of urban intelligence and ultimately a high quality of sustainable, efficient, and people-centered urban development.

The assurance of a consistent supply of daily necessities in megacities is pivotal in fortifying community supply resilience. It is axiomatic that a community system is not an insular entity; rather, it intricately intertwines with various elements of urban systems. As a foundational unit of urban governance, the urban community is instrumental in facilitating a congruent nexus between supply and demand, thereby augmenting urban resilience. This study proposes an exploratory evaluation method for the urban community supply support and resilience based on complex network theory, attempting to achieve a breakthrough in the underlying theoretical framework of resilience assessment from "single system assessment" to "multi-system correlation assessment". Taking the six districts in the central city of Guangzhou as an example, we build a supply-demand network based on citizens' spatio-temporal behaviors using multi-source data such as mobile phone signaling data and other data. The attacking strategies of network are based on five community resilience indicators. Besides, the cascade failure mechanism is introduced to evaluate the network resilience, and the entropy-weighted method is employed to obtain resilience evaluation results. The influence mechanism of community resilience on the supply system is further analyzed by studying the factors affecting community node failure at different stages of supply network. The findings are as follows: (1) The proposed evaluation model of the community supply support and resilience can effectively simulate urban community supply-demand networks and evaluate the resilience of communities. Low-resilience communities are mainly categorized into three spatial types: old blocks, urban villages, and suburban blocks; (2) Through the analysis of network resilience under five different attack strategies, it is found that the dominant influencing factors are different, with the population density being the primary factor; (3) There exists a complex bidirectional relationship between community resilience and supply security, including the obvious vulnerability of low-resilience communities. And the community self-organization ability, the supply facility layout, and the linkage scheduling between supply points all affect the overall community resilience.

Being able to penetrate clouds and fog, Synthetic Aperture Radar (SAR) imagery has been widely used in flood mapping and flood detection regardless of time and weather condition. Improving the accuracy of flood maps retrieved from SAR images is of both scientific and practical significance. However, errors in SAR-derived flood maps can come from SAR image measuring principles, image acquisition and pre-processing system, water detection algorithms, and the remarkable temporal dynamics of the flooding process. The aim of this paper is to provide an extensive literature review of flood detection using SAR images (about 108 peer reviewed journal papers), including SAR data sources, flood detection methods, application of auxiliary information, accuracy evaluation, and challenges and opportunities for future research. Based on the articles reporting flood detection methods, it is found that the threshold segmentation methods such as the OTSU and KI algorithms are computationally fast and have been most widely used. The classification methods (e.g., the support vector machine and K-means clustering algorithms) have the flexibility to account for both subjectivity and objectivity, and the change detection method using the difference and ratio algorithms can effectively suppress over-detection and image geometric errors. Additionally, combining SAR images with four major types of auxiliary data to increase flood detection accuracy has become a hot topic in the past decades. Specifically, terrain information such as Digital Elevation Model (DEM), Height Above Nearest Drainage (HAND), and topographic slope can effectively reduce the impacts of shadows and exclude non-flooded areas. SAR image textural and multispectral optical information (e.g., Landsat data and aerial photos) can enhance the recognition ability of water features. Land cover/use data facilitate removing non-water features that are similar to water features, and hydrological data can help excluding permanent water bodies from temporary flood areas. From the perspectives of SAR image types, image preprocessing, detection algorithms, and accuracy assessment, major challenges are further discussed including insufficient understanding of the complexity of SAR backscattering information, limited progress in improving the signal-to-noise ratio during image pre-processing, lack of versatile flood detection algorithms, and low availability of high-quality verification data. While opportunities for future SAR-based flood detection research include combination of auxiliary information in detection algorithms, use of multiple rather than single threshold for water detection, and transition from deterministic toward probabilistic flood mapping.

Image geo-localization is a technique that obtains the geographic location information of an image through a series of methods, so as to establish a mapping relationship with the real geographic space. This technique is important for further image information mining and has potential application value in cyberspace surveying and mapping, intelligence acquisition, user outdoor positioning, and augmented reality. Despite the tremendous progress in the field of computer vision, high-precision automatic geo-localization of images still needs to be addressed due to the involvement of multiple fields such as image feature extraction, large-scale data retrieval, large-scale point cloud processing, deep learning, geographic information feature extraction, geometric modeling and reasoning, semantic scene understanding, context-based reasoning, and multiple data fusion. This paper reviews the progress of image geo-localization research, mainly including image geo-localization methods, image geo-localization datasets, image geo-localization evaluation methods, and summary and prospect of image geo-localization. Firstly, image geolocation methods are classified into three categories, i.e., image retrieval, 2D-3D matching, and cross-modal retrieval, according to the relevance of the research content. Secondly, the datasets and evaluation methods used for image geo-localization research are categorized and summarized. The geo-localization datasets include image datasets, cross-view datasets, Structure from Motion (SfM) datasets, and multimodal datasets, etc. The image geo-localization evaluation metrics include Top-k candidates, localization error, position and orientation error per video frame, and accuracy/recall. Finally, the current status of image geo-localization research is analyzed, and the future research directions of image geo-localization are outlined in terms of global geo-localization, natural area geo-localization, multi-method fusion for geo-localization, Point of Interest (POI) data-based geo-localization, and pre-selected location refinement.

Geographic Information Science (GIS) is not only the demand for the development of the discipline itself, but also the technical method to support the exploration of the frontiers of geography, earth system science and future geography, and the supporting technology to serve the national strategy and social development. In view of the intrinsic law of the development of geographic information science, the extrinsic drive of the development of related disciplines, and the pull of new technologies such as Artificial Intelligence (AI), this paper firstly analyses the development process of GIS and explores its development law from six dimensions, such as description content, expression dimension, expression mode, analysis method and service mode, etc.; then, on the basis of interpreting the original intention and goal of the development of geography, a geography discipline system oriented to the "physical-humanistic-informational" triadic world is proposed, the research object of information geography is discussed, and a conceptual model integrating the seven elements of information and seven dimensions of geographic descriptions is put forward; then, the development trend of geographic information science is analysed from three aspects, including geography from the perspective of information science, information geography from the perspective of geography, and geo-linguistics from the perspective of linguistics, information geography from the perspective of geography, and geolinguistics from the perspective of linguistics, the development trend of geographic information discipline is analysed. Finally, the paper summarises the possible directions and points of development of GIS, geography in the information age, geo-scenario, and geo-big model. We hope that our work can contribute to enriching the understanding of geographic information disciplines, promoting the development of geographic information related sciences, and enhancing the ability of the discipline to support national development needs and serve society.

With the development of science and technology, cyberspace has been deeply integrated with people's daily lives and represents a new spatial form of human activities. The cyberspace correlates to the real world, but on the other hand it also differs from it. Cyberspace has distinct geographical characteristics, and the spatial-temporal relationship in geograph remains an indispensable element in cyberspace. Therefore, it is of great significance to apply geographical thinking to the cognition of cyberspace in order to describe the situation of cyberspace and maintain cybersecurity. In this paper, we review the emergence and development of cyberspace, analyze the basic structure and characteristics of cyberspace, and examine the geographical properties of cyberspace based on different views of cyberspace. From the perspective of the three laws of geography, this paper discusses how to use geographical thinking and Geographic Information Science (GIS) methods to describe cyberspace, and takes the visualization of cyberspace, the construction of geographic knowledge graph of cyberspace, and the intelligent analysis of cyberspace behavior as examples to illustrate how to apply geographical thinking to the analysis and research of cyberspace. Exploring the geographical properties of cyberspace and applying geographical techniques to cyberspace protection can provide new insights into the comprehensive governance of cybersecurity, thus improving the cognitive level and governance capabilities of cyberspace in the new era.

Geometric and semantic integration of 3D building models are important infrastructure data for smart city, they are conducive for promoting the refined management and intelligent application of building facilities. However, most of the existing point cloud-based modeling methods focus on the reconstruction of geometric models with simple roof structure, and semantic and topological relations are ignored. Moreover, these methods are sensitive to noise, which are difficult to assure topological consistency and geometric accuracy. To solve these problems, this paper proposes a 3D primitive fitting algorithm for automatically reconstructing building models with complex roof structure from point clouds. Firstly, a 3D building primitive library is designed, including various 3D building primitives with simple and complex roof types. Secondly, an individual building point cloud input is segmented into multiple planes using RANSAC algorithm. The Roof Topology Graph (RTG) is then generated according to the relationship of roof planes, and the roof type of point cloud is subsequently recognized by comparison of RTG between point cloud and building primitives. Thirdly, the reconstruction is formulated as an optimization problem that minimizes the Point-to-Mesh Distance (PMD) between the point cloud and the candidate meshed building primitive. The sequential quadratic programming optimization algorithm with necessary constraints is adopted to perform holistically primitive fitting, so as to estimate the shape and position parameters of a 3D primitive. Finally, the parameterized model is automatically converted into City Geography Markup Language (CityGML) building model based on the prior 3D building primitive. The generated CityGML LoD2 (second level of detail) models are different from mesh models created by conventional building modeling methods, which are represented with geometric, semantic, and topological information. To evaluate the quality and performance of the proposed approach, airborne lidar and photogrammetric building point clouds with different roof structures are collected from public datasets for test. Several building models with complex roof types are successfully reconstructed by using this approach, and the average PMD of five models is 0.17 m. The proposed algorithm is also compared with three other methods. Experimental results indicate that the proposed method achieves the best geometric accuracy, because the average PMD of each model is less than that of other methods. Moreover, this automatic primitive fitting method is efficient, and it is also robust to noise and local data missing. This study demonstrates that the resulting building models can well fit the input point cloud with topologic integrity and rich semantic. This method provides great potential for accurate and rapid reconstruction of geometric-semantic coherent building models with complex roof condition.

Geological and mineral resource survey and scientific research in "geology, geophysics, geochemistry, and remote sensing " have established a large amount of geological and mineral survey data, which contain rich knowledge related to mineralization and distribution of gold mine, such as the metallogenic and tectonic setting, geological environment of occurrence, geological characteristics of mineral mine, genesis and metallogenic model of mine, and so on. The transformation from massive mineral related data to effective metallogenic knowledge has become one of the most important breakthroughs to improve the accuracy of geological prospecting. To solve this problem, through the in-depth analysis of knowledge representation, information extraction, and knowledge fusion in knowledge engineering, this paper explores the knowledge graph construction method of gold mine based on ontology. Firstly, referring to industry norms, gold mine knowledge base, and reference material of geological and mineral resource exploration, the metallogenic model of gold mine is sorted out, and the gold mine concept, gold mine entity, gold mine relationship, gold mine geological attribute, and gold mine metallogenic attribute are determined. In addition, the schema layer of gold mine knowledge graph is constructed by using the top-down ontology knowledge representation method, which represents the conceptual model and logical basis of gold mine knowledge graph. Secondly, based on structured, semi-structured, and unstructured multi-source heterogeneous geological data, the deep learning model is used to realize gold mine knowledge extraction, semantic analysis, and knowledge fusion, which enriches the data layer of gold mine knowledge graph and provides data support for gold mine knowledge graph. The gold mine knowledge graph is constructed in a bottom-up way, and the gold mine knowledge triplet is stored by Neo4j graph database, in which nodes represent gold mine concept, gold mine entity, and gold mine attribute value, while edges represent relation and attribute. Finally, the gold mine knowledge management system is developed based on the graph database. It can be applied to the management of gold mine data, acquisition of knowledge, visualization representation of gold mine knowledge graph, inquiry of knowledge, management and presentation of knowledge base, and other functions well, so as to lay a foundation for the intelligent analysis and mining of geological big data. This study develops a geological prospecting method driven by data and knowledge, and provides a reference for identifying, controlling, and managing mineral resources, which can improve the prospecting accuracy in geological exploration.

With the development of big data and artificial intelligence, the scope of digital earth modeling has extended to full-time holography beyond the earth surface. However, the current data model of digital earth still remains in the data modelling of earth tile or grid subdivision. This model severely limits the application of scenario-based and intelligent digital earth development. This paper proposes the concept of digital holographic earth and a corresponding data organization model of earth data cube. By using global multi-level grid reference system to describe and express multi-scale space and using two or three-dimensional grid cells to describe spatial positions, the traditional spatiotemporal description of "longitude, latitude, elevation, and time" is transformed to a new spatiotemporal description system of "time granularity, time coverage, grid position, and grid scale". The proposed model is characterized by the dimensions of "time-space-scale-attribute" based on spatiotemporal big data in the digital earth. The model encapsulates vectors, rasters, grids, time series arrays, and 3D models into an unified system. This unified system ensures that any data value of a specific earth data cube is aligned perfectly in time, space, and scale, which solves the problem of multi-dimensional or spatiotemporal dynamic fusion of big earth data. Finally, this paper develops a deep-time and spatiotemporal dynamic visualization simulation system to verify the data model based on the requirements of the Deep-time Digital Earth International Science Program.

Real-time identification of urban hotspot areas can improve the response ability of city managers on emergencies. With the development of the Internet of Things and communication technology, the starting and ending information of taxi trips can be uploaded to the data center in real-time, forming a massive and continuous data stream of pick-up and drop-off events. Taxi is a welcoming means of transportation, and have characteristics of all-weather operation, full regional coverage, and high spatial-temporal resolution, so its pick-up and drop-off data stream can be used as a high-quality data source for real-time identification of urban hotspots. However, the hotspots area identification methods aimed at historical data sets have a high delay and can’t meet the real-time requirement. At the same time, the existing clustering algorithm based on distributed streaming processing technology is difficult to meet all the requirements including low aggregation cost, good scalability, and supporting arbitrary shape cluster recognition when facing pick-up and drop-off streams. Based on the distributed stream processing technology, an urban hotspot area identification method suitable for taxi pick-up and drop-off data stream is designed in this study. By mapping the real-time pick-up and drop-off records to grid monitoring units, we can obtain the heat value of each monitoring unit for each time window, filter the monitoring units which have higher heat values than a specified threshold as hot units, and finally gather the hot units of same time window into hotspot areas. To avoid the performance bottleneck of the aggregation operator in distributed region identification, a multi-stage distributed hot area aggregating method is designed. The method is implemented on Apache Flink, and the pick-up and drop-off data stream is simulated with the historical taxi trip records from Wuhan and New York City. The results show that: (1) The spatial distribution and status of hotspots differ from time to time, which is related to citizens' activities at different times; (2) Using smaller monitoring units can get finer spatial positions of each hotspot area; (3) Our method can accurately identify the hotspot areas using different parameter pair of monitoring unit sizes and hotspot thresholds; (4) The method has excellent throughput which increases with the computing parallelism and reaches 90k/s with parallelism at 8. The proposed method can correctly capture the spatial distribution of urban hotspot areas of each period in real-time and has good performance and scalability.

While rapid urbanization endows people with a modern life, it also brings many urban diseases such as traffic congestion and uneven distribution of resources. Taxi is one of the main transportation methods for urban residents. Taxi data effectively record the spatial and temporal information of residents' travel and can be widely used for residents' travel characteristics mining. Analyzing residents' travel characteristics is an important way to solve and alleviate the increasingly prominent urban problems. At present, rich research results have been achieved in mining residents' travel characteristics using taxi OD flow data. Cluster analysis, which is based on taxi OD flow data, represents one of the primary methods for uncovering the travel characteristics of residents. But most of the studies ignore the semantic information of OD flow. Urban POI data is an important data support for semantic extraction of OD flow, and semantic information can be extracted by studying the relationship between OD flow and POI. To address the problem of insufficient consideration of semantic information in spatiotemporal clustering algorithms, a method for extracting semantics of OD flow based on Global Vectors (GloVe) model and density based spatiotemporal semantic clustering algorithm (STS DBSC AN, Spatial Temporal Semantic DBSCAN) is proposed in this paper. Firstly, OD flow semantics are extracted by combining POI visiting probability and GloVe model, the GloVe model not only fully considers the local geographic context information of POIs, but also takes into account its global statistical information in the corpus. Based on this, a spatiotemporal semantic similarity measurement rule for OD flow is proposed, which comprehensively considers temporal, spatial, and semantic information. Then, the DBSCAN clustering algorithm is improved according to the spatiotemporal semantic similarity measurement rule, and the spatiotemporal semantic clustering of OD flow data is realized. Finally, analysis of travel characteristics of residents in Xiamen island based on OD flow semantics and spatiotemporal semantic clustering, and a total of seven types of residents' travel semantics are extracted. Results show that: 1) Residents' travel semantics are influenced by the time factor, and the main residents’ travel semantics are different in different time periods; 2) residents' travel hotspots are mainly distributed in the central developed area of Xiamen Island; 3) seven typical residents' travel patterns are extracted from four main residents' travel semantics through spatiotemporal semantic clustering analysis. The results demonstrate that OD flow semantic and the spatiotemporal semantic clustering method can effectively mine the travel characteristics of urban residents.

Nowadays, cities have emerged as one of the core elements for the sustainable development of human society. This also aligns well with the United Nations Sustainable Development Goals on sustainable cities. The pivotal role of cities is also demonstrated by the rapid development of big data and artificial intelligence technologies. There have been more and more studies dedicated to the realm of data-driven urban sustainability, in which the complex processes of urban sustainable development, encompassing social, economic, and ecological dimensions, are monitored, interpreted, and evaluated through massive urban data from multiple sources. However, a common limitation is that most existing studies concentrate on individual application scenarios and singular data sources and ignore the intricate interconnections among diverse urban data sources and multiple urban elements, making it challenging to explore findings across diverse urban sustainability contexts. Therefore, to address this critical gap, in this paper, we propose a novel approach for urban sustainable development driven by Urban Business Area/Region Knowledge Graph (UKG). This approach incudes two fundamental steps: the construction of a comprehensive ontology for the UKG based on massive multi-source urban data, and the subsequent synthesis of knowledge guided by this ontology to create the UKG. The construction of the UKG ontology captures important elements in cities as well as their complex interconnections, e.g., people, locations, and organizations, and their relationships in terms of spatiality, function, and association. This ontological architecture lays the foundation for the subsequent knowledge fusion, ultimately leading to the construction of UKG. The practical applications of UKG in driving urban sustainability are manifold, ranging from real-time status monitoring and nuanced interpretation of urban phenomena to the holistic evaluation of decisions made for urban sustainability. To verify the effectiveness and efficiency of the proposed approach, the paper introduces a novel cross-modality contrastive learning framework that incorporates semantic knowledge for urban sustainability. The proposed framework includes a semantic encoder and a visual encoder to capture information from UKG and urban images (satellite images and street view images), respectively. Based on the assumption that the semantic representation of UKG entities should be close to their corresponding image representations, the proposed framework successfully incorporate semantic knowledge into visual encoder, which further enhances the predictive capabilities of urban socioeconomic indicators derived from urban images. Through empirical validation, this study demonstrates the real-world applicability and generalizability of the UKG framework for urban sustainability.

Most of the precipitation datasets in Central Asia have problems such as data missing, geographical bias and outliers, low resolution, and so on. The normal prediction results obtained by most machine learning methods are usually hard to interpret, not only due to the uncertainties from input information but also due to the complicated global geographical environments as well as the underlying local geographical conditions. In this paper, to overcome this problem, we proposed a novel downscaling precipitation model to adjust and optimize the precipitation computation results from Conditional Generative Adversarial Networks (CGAN) using an inverse distance weighting method based on the prior information of geographical differences of local digital terrain model and multiple weather stations. In this study, the Amu Darya River Basin was selected as the research area due to its various geographical environment and complicated topographic and geographical conditions. First, the input Climate Research Units (CRU) precipitation data with 55 km resolution were spatially corrected based on the topographic map using the spatial deformation model. The spatial deformation model was extended from spatial transformation network methods. Second, we input the corrected CRU precipitation data, temperature, wind speed, humidity equivalent data, and remote sensing data to the CGAN computing framework for high-resolution precipitation reconstruction. The experiment adopted the cross-validation method, taking 80% of the data as the training set, and the remaining 20% as the verification set. The test set contained 20 raster maps of annual precipitation from 2000 to 2019. The model was built based on pytorch 1.10.0, the batch size was 16, and the learning rate was 0.000 3. The epoch was 8 000 iterations in the Adam optimizer for gradient descent. Finally, the precipitation data of meteorological stations were used as the true values for analyzing the geographical differences of inverse distance weights and the accuracy of the corrected precipitation grid data. The results show that the proposed method can improve the resolution and accuracy of precipitation data，especially for the complex terrain and mountainous area. And Experiments on the Amu Darya in Central Asia show that the Root Mean Square Error (RMSE) of the downscaling result within the watershed was 15.96 mm, the Mean Absolute Error (MAE) was 11.82 mm, the R² value was 0.83, and the deviation was 0.08. This study provides a robust, accurate method for improving the spatial resolution of precipitation data in complex geographical areas.

Extraction of ship routes and analysis of traffic flow are the basis of route design, maritime management, and trade analysis. Based on the massive ship trajectory data, existing ship route extraction methods still have limitations in terms of adaptability to large sea areas, model complexity, and consistency with real maritime traffic routes. In this study, we propose a ship trajectory extraction model and traffic flow analysis based on massive ship Automatic Identification System (AIS) data. Firstly, the ship's navigation trajectory is abstracted as the combination of a ship's stay points (stop points) and movement points (waypoints). Stop points represent the characteristic of a ship's stop trajectory at the port, and the waypoint represents the ship's moving trajectory characteristic, e.g., the sailing speed or sailing angle changes significantly. The navigation trajectory abstraction model denoted as "departure port (stop point)→movement (waypoint)→destination port (stop point)" of a ship is constructed, enabling the division of ship navigation trajectory. Secondly, based on the abstract model of ship navigation trajectory, further clustering of stop points and waypoints of the massive ship navigation trajectory based on graph theory is implemented to extract route points (stop points and waypoints) of ships. Finally, a route point connection matrix is established to realize ship route extraction in the form of ship traffic map, which provides a new method for ship route extraction and traffic flow analysis. Taking the Silk Road area in the South China Sea as the study area, the historical AIS data for the entire year of 2017 are used to analyze the traffic flow characteristics and ship routes of typical merchant ships (i.e., container ships, bulk carriers, and oil tankers). The results show that the extracted ship routes are highly consistent with the maritime traffic in high-density areas and can reflect the real maritime traffic routes. Compared with the existing shipping route data, the details of extracted routes are enriched, and the structure is more comprehensive. In addition, compared with the existing shipping route extraction methods, the proposed method has two following advantages. First, the shipping routes extracted by the proposed method have greater richness. The proposed method not only extracts the shipping routes but also identifies the characteristic points during ship navigation, i.e., the stopping points and the waypoints of the ship route, which provides important knowledge support for route design and navigation safety. Second, the extracted routes can be easily applied to analyze the maritime traffic network. Since the extracted routes are in the form of point-to-point starting from the port, it is easy to construct a maritime traffic network, allowing for potential transportation network analysis. This study contributes decision-making support for ship route planning, traffic flow analysis, navigation safety, etc.

The research on car-following behavior aims to explore the impact of the leading vehicle's movement on the following vehicle's driving state on a one-way road. By establishing corresponding car-following models for simulation studies, it can reveal the underlying mechanism of traffic congestion, traffic flow oscillation, and other traffic phenomena, which is helpful for evaluating the stability, road capacity, and operational efficiency of traffic flow. Due to differences in driving experience, personality, and other characteristics, drivers may exhibit different car-following characteristics. Moreover, under the same conditions, the car-following behavior of different drivers may differ, and the car-following behavior of the same driver may also vary at different times. However, traditional car-following models often assume that drivers' driving behavior is homogeneous and rarely consider differences in driving styles among passing vehicles, which is inconsistent with actual situations. Therefore, this paper first extracts four driving behaviors of passing vehicles on the road (lane changing, starting, braking, and smooth driving), develops a Weight-based Adaptive Data Stream Gravity Clustering (WAStream) algorithm based on weights, and conducts clustering analysis on the time-series data of different driving behavior characteristics. Then, according to the driving style scoring model, the aggressiveness of different driving behaviors of drivers is quantified, the effective classification of driving styles of passing vehicles is achieved, and the overall driving behavior characteristics of different style driver groups are obtained. Next, by analyzing the car-following data of drivers with different styles, a speed expectation function for different style vehicles is constructed. Furthermore, the proposed car-following model considers the impact of speed and acceleration differences between the leading vehicle and multiple front vehicles in the driver's field of vision, which considers the driver's driving style. Finally, based on the NGSIM vehicle trajectory data, the key parameters of the car-following model considering the driver's driving style are calibrated using genetic algorithms, and the model's validation and numerical simulation analysis are achieved. The experimental results show that compared with the classical FVD model, the proposed car-following model can better fit the car-following data, and the MAE, MAPE, and RMSE are reduced by 1.511 m/s², 6.122%, and 1.064 m/s², respectively. At the same time, the model can effectively reduce the delay of vehicles in car-following behavior, construct traffic flow scenarios closer to reality, and improve the stability of traffic flow. The car-following model proposed in this study can provide effective decision-making information for transportation planning and management departments and provide model references for micro-traffic simulation studies.

Scientists still cannot fully understand and explain many complex physical phenomena and dynamic systems, which cannot be described by deterministic mathematic equations and be analyzed and predicted through compact physical mechanistic models. With the ever-increasing of observational data, data-driven machine learning methods can effectively describe many complex non-linear phenomena. Nevertheless, pure data-driven models still have shortcomings in representation, interpretation, generalization capabilities, and sample efficiency. Conventional machine learning methods are confronted with challenges brought by spatiotemporal heterogeneity and sample sparsity. Recently, Physics-Informed Machine Learning (PIML) can effectively leverage observation data to describe and analyze dynamical systems when physical principles are uncertain. PIML has gain wide attention and been extensively applied in physics, computer science, biology, medical science, and geosciences. In recent years, artificial intelligence and machine learning technologies have been widely applied in geography, especially in GIScience and remote sensing, attracting wide research interests of geographers. This line of research is termed GeoAI and has become a cutting-edge research frontier in geography. PIML methods integrate the ideas of model-driven and data-driven methods, introducing new research paradigms for GeoAI and improving the description and prediction of complex geographical phenomena. This survey first summarizes recent progress in this domain from the perspectives of the representation of physical priors and the integration of physical priors in machine learning methods. Physical prior refers to existing independent knowledge that is already available before building machine learning models. This survey reviews the representation of physical priors from the aspects of augmented data and customized features, physical laws and constraints, governing equations as well as geometric properties. We also review how physical priors are integrated into various machine learning models, including constraint modeling, auxiliary task design as well as model training and inference. Based on the PIML survey framework, we explore the relationships between spatiotemporal priors and other physical priors, before briefly reviewing and summarizing typical case studies of spatiotemporal prior-informed GeoAI research. We also discuss the research agenda and future prospects of spatiotemporal prior representation and the spatiotemporal prior-informed GeoAI in the context of geo-machine learning and GeoAI frontiers. In light of fast progress of PIML, we contend that GeoAI studies that are well informed by spatiotemporal priors can gradually establish a generic geographical representation, analysis, prediction, and interpretation framework, which not only helps handle many classical problems in GIScience but also addresses future profound challenges of human being by encouraging geographers to explore more research opportunities when collaborating with researchers from other disciplines.

The 15-minute community-life circle is defined as an ideal geographical setup where most human needs are located within a 15-minutes travel distance. This concept represents a new trend for green, low-carbon, and sustainable urban development. However, there are challenges in building 15-minutes community life circles effectively, efficiently, and equality, such as how many service facilities are required, where to locate the facilities, and how to promote service efficiency and equality for urban residents. In this paper, a novel facility location model, DC-CFLP, is proposed for facility site selection within the 15-minute community-life circle and addressing the aforementioned facility planning challenges. First, we use a maximum service radius, a recommended service radius, a minimum percentage of demand covered by facilities within the recommended service radius, and an optional maximum number of facilities to extend the single-source facility location problem (SSCFLP). Second, the constraints on the facility capacity, such as maximum service radius and minimum percentage, are formulated as soft constraints, which are addressed through penalties in the objective function. The proposed model is tested in Zhengdong New District, Zhengzhou, China. Based on the geographic condition of the region and its detailed urban planning maps for the year of 2035, three different scenarios are designed for locating the community convenience service centers, each with three sets of planning parameters. In this case study, we solve nine model instances using a metaheuristic algorithm. The planning results show that our proposed model can efficiently select facility locations that satisfy planning criteria, including balancing service demand and supply, minimizing cost service and travel costs, achieving a minimum percentage of demand covered by facilities within the recommended service radius, and reducing spatial inequality of service, while considering service cost, accessibility, and equity. Based on the model results, several planning recommendations are provided for the study area. Moreover, to demonstrate the superiority of the proposed model, we conduct comparison experiments with the SSCFLP, the Capacitated P-Median Problem (CPMP), and the DC-CFLP. These experiments show that the facility location selection using SSCFLP is the most efficient, the CPMP results are largely dependent on the number of facilities, and the DC-CFLP results archive a better balance between service quality, cost, and equality. In conclusion, our study demonstrates that our proposed model is a planning-parameter-driven, efficiency-equality balanced model, and highly flexible for the site selection of public facilities.

The term "equality " refers to the fairness of rights or resource distribution among social group members, which is crucial for traffic planning. The accessibility of public transport reflects whether residents of corresponding geographical analysis unit have reasonable access to public transports given the size of their population. Public taxi service (including both ride-hailing taxi and traditional taxi) is the primary means to meet urban residents’ personalized daily demand for public transport. Exploring the equality of public taxi services can provide support for optimizing personalized travel service in urban public travel. In this study, based on the taxi trajectory and dynamic population data of Xiamen, we used Gini coefficient and Theil index to calculate the equality of taxi service for three types of taxi service, i.e., cruise only, ride-hailing only, and mixed receiving taxi service. Then we analyzed the contribution of urban functional areas to equality of tax service and extracted areas with potential inequity. The results show that the proposed method can quantify the inequality of different taxi service and its changes under the context of COVID-19, based on the reclassification of taxis service. Specifically, (1) after the COVID-19 outbreak, the number of vehicles providing ride-hailing service decreased by 18.8% in Xiamen, with a 10% increase in service inequality relative to the dynamic population, while the number of taxis using cruising only to pick up orders remained relatively stable, and the inequality was also at a high level constantly; (2) In Xiamen city the overall inequality of ride-hailing only service was 66% that of cruise only service. The use of online car hailing platform improved the fairness of personalized public travel services for urban residents; (3) the equality of taxi service differed significantly among different types of urban functional areas. For cruising only service, 57.49% of the overall inequality was contributed by commercial land use in Xiamen. For ride-hailing only service, industrial and tourism land contributed 35.07% and 19.32% of the inequality, respectively. After the COVID-19 outbreak, the contribution of tourism land to the inequality of online shopping service increased significantly, by 81.67% compared to the pre-epidemic period; (4) Xiamen City contains two parts: inside-island and outside-island. The number of potentially inequitable service areas was much larger outside-island than inside-island. Areas with a low level of passenger service but a high level dynamic population are typically located in the island's natural parks, while areas with a high level of passenger service but a low level dynamic population are located beyond the island's natural parks; (5) Compared with the results based on the dynamic population, the inequality based on the static population assessment was overestimated by up to 89.25%. The research results of this paper demonstrate that the theoretical framework and analysis method can systematically reveal the inequality characteristics of public taxi service, providing guiding principle in urban traffic optimization.

Crime prediction is a prerequisite for crime prevention. Forecasting crime efficiently and accurately is of great significance for improving urban management and public safety. At present, it is difficult for most of the existing studies to obtain accurate crime prediction, because they usually utilize a single machine learning or deep learning model, ignoring the spatiotemporal dependence of the crime. In this paper, we propose a spatiotemporal prediction model GAERNN based on deep learning techniques. Firstly, the GAE model is used to capture the spatial distribution characteristics of crime cases. Secondly, the features with spatial dependencies are input into the GRU model after serialization to further extract the temporal features of crime sequences. Then, the spatial and temporal prediction results of theft crime are obtained by the fully connected layer processing. Finally, we select MLP and GCN to carry out contrastive experiments by using several indicators, such as RMSE and MSE, to verify the performance of our model. The results show that our model is significantly superior to other benchmark models in spatiotemporal prediction, and it can be used to prevent and control theft crime effectively.

Under the background of high-density urban areas and aging population in China, it is not only necessary but also urgent to strengthen the research on the design and construction of urban pocket parks. This paper uses CiteSpace, literature review, technical analysis and some other methods to conduct cluster analysis and comprehensive literature analysis on the study of urban pocket parks in China from 2000 to 2022. The results indicate that the current research hotspots in this field are pocket parks, roadside green space, landscaping, vest-pocket park, public space, landscape architecture, micro green spaces, street green land, design strategy, planning and design, etc. The research progress of pocket parks is divided into three stages: basic research (2000—2006), steady progress (2007—2018), and rapid development (2019—2022). In the basic research stage, the paper mainly studies the basic theories of street green space and vest-pocket park, which are the predecessor of the concept of pocket park, such as the development status at home and abroad, humanized design, and behavioral psychology, which lays a good foundation for the research of pocket park in China. In the stage of steady progress, the concept of pocket park is clearly proposed, the connotation of pocket park is interpreted, and the basic strategy of pocket park planning and landscape design is summarized. In the stage of rapid development, the research perspective turns to more micro aspects such as urban renewal, spatial layout of pocket park in the context of park city, optimization strategy, accessibility, fairness, interactivity, and comprehensive evaluation, etc. The research focus includes basic research, planning and design research, and evaluation research. The basic research has systematically sorted out and summarized the concept and connotation, construction scale, construction types, and usage functions of pocket parks. The planning and design research has extracted design strategies related to pocket parks from aspects such as spatial layout, landscape design, and elderly-oriented design. The evaluation research has evaluated the current situation of pocket parks from three aspects: social benefits, landscape benefits, and spatial structure. The development directions of urban pocket park research in our country in the future include: research on collaborative group layout of multiple pocket parks and optimization of internal spatial layout of a single pocket park, optimization of landscape facility layout, and plant configuration and optimization; research on the adaptability of pocket parks to the elderly, children, accessibility, and humanization according to the behavioral characteristics and psychological needs of residents, based on the theoretical foundations of environmental behavior and environmental psychology; systematically study on the coupling relationship between pocket parks and the natural environmental effects in the area by comprehensively applying architectural environmental theory, Remote Sensing (RS) technology, and Geographic Information System(GIS) technology; normative research on design guidelines, construction, operation and maintenance standard paradigms of pocket parks; research on digitization of pocket parks design and intelligent operation and maintenance management, as well as evaluation system, evaluation method and statistical analysis of pocket parks on this basis.

Trajectory clustering is a hot research topic in the field of spatial data mining, which is of great significance to many applications such as urban traffic control, road network construction and update. Trajectory clustering involves grouping similar trajectories into clusters where trajectory similarity measurement and clustering parameter setting are two core issues in the process of clustering. However, due to the complex morphological and structural characteristics of trajectories, the existing trajectory similarity measures are sensitive to noise or do not fully consider the consistency of trajectory motion direction. In addition, most clustering algorithms still need to manually set parameters, and the quality of clustering results is affected by the subjective experience of users. To address the above problems, this paper proposes an adaptive trajectory clustering algorithm. The proposed algorithm has two main components: a new trajectory similarity measure called Directed Segment-Path Distance (DSPD) and an improved hierarchical clustering algorithm based on the concept of central trajectory. The DSPD metric is a fusion of the spatial proximity and motion direction features of trajectories, providing a robust similarity measure. The enhanced hierarchical clustering algorithm extends the Ward hierarchical clustering algorithm by defining central trajectories and use the DSPD metric as the trajectory similarity measure. In addition, the proposed algorithm also utilizes the clustering characteristic curve to determine the optimal clustering parameters automatically. This eliminates the need for manual parameter tuning and reduces the subjectivity of clustering results. To evaluate the effectiveness of the proposed algorithm, experiments were conducted on both the simulated datasets and real-world trajectories of Wuhan. We first compared the effect of the DSPD with other commonly used trajectory similarity measures (i.e., Hausdorff distance, Fréchet distance, DTW distance, and LCSS distance) using the same clustering algorithm on the 11 sets of simulated datasets. The evaluation was based on the Adjusted Rand Index (ARI). Then we conducted another comparative analysis to access the effectiveness of the improved clustering algorithm in contrast to an average link-based hierarchical clustering algorithm. Finally, to verify the practicability of the proposed algorithm, we applied it to the process of road network updating. The experimental results show that the proposed DSPD measure outperforms alternative distance metrics on the ARI evaluation indicator. It can effectively distinguish moving trajectory clusters in different directions while considering the spatial proximity of trajectories, thus enhancing the accuracy and effect of the trajectory clustering. Furthermore, the proposed algorithm can significantly reduce the subjectivity of clustering results and provide suggestions for practical applications such as urban road network extraction and update.

Many large cities have been actively promoting the policy of "replacing oil with gas" for taxis. Taxis are converted from traditional gasoline consumption to Compressed Natural Gas (CNG) to achieve energy conservation and emission reduction goals. To accurately evaluate the carbon dioxide (CO₂) emission reduction benefits of CNG taxis, taking Wuhan as an example, a vehicle microscopic CO₂ emission model based on deep learning method and trajectory data was proposed to investigate the spatial-temporal characteristics of CO₂ emissions of taxis under different fuel scenarios. Considering the driving feature sequence and fuel type of vehicles, the Portable Emission Measurement System (PEMS) was used to collect vehicle CO₂ emission data in the road test experiment, then we constructed a vehicle microscopic CO₂ emission model by the BiLSTM algorithm and further verified its accuracy. Based on the proposed CO₂ emission model and the trajectory data of 15 752 Wuhan taxis, the CO₂ emissions throughout the entire lifecycle of urban taxis by 92# gasoline and CNG were estimated respectively to quantify the CO₂ emission reduction benefits of CNG taxis. The results show that the proposed model had a higher accuracy than common regression algorithms such as SVR and LSTM, and the predictions matched well with real vehicle CO₂ emission changes, meeting the accuracy for a large-scale estimation of urban taxi CO₂ emissions. In addition, the accuracy of taxi CO₂ emission estimation based on deep learning methods was also higher than that of physical microscopic models such as IVE and CMEM. Especially, when using CNG as vehicle fuel, the physical models had significant computational errors due to not involving technical parameters. The empirical results show that, taxi CO₂ emissions using CNG were reduced by 22.05% during the PTW process and by 49.45% during the WTP process, compared to emissions using 92 # gasoline. Our results reveal both the temporal and spatial patterns of taxi CO₂ emission as well as the CO₂ emission reduction benefits of CNG taxis. The outperformance of deep learning methods over other methods for estimating vehicle CO₂ emissions provides new ideas for large-scale and high-precision estimation of vehicle emissions. The CO₂ emission reduction benefits of using CNG as fuel in taxis are significant, which provides a reference for the government to formulate relevant energy-saving and CO₂ emission reduction policies.

Based on the Point of Interest (POI) big data of the catering industry and related service industries in Guangzhou in 2021, this study analyzes the spatial distribution characteristics, influencing factors, and the spatial spillover effects of the overall and subdivided catering industry in Guangzhou based on the methods of HDBSCAN clustering, Collaborative Location Quotient, and Spatial Durbin Error Model. The study mainly explores the overall and local spatial relationships between the catering industry and surrounding service industries. The results show that: 1) Different catering density areas show variations in the spatial distribution of the catering industry in Guangzhou. The catering industry in high-density areas is characterized by a muti-central agglomeration pattern, while the catering industry in low-density areas is characterized by central agglomeration with surrounding radiation. The local distribution of restaurants are related to population features, such as population density, population education level, and so on; 2) There are variations in the spatial correlation between the catering industry and its surrounding service industries across different catering density areas. Areas with high catering density have the strongest spatial correlation, while areas with moderate catering density have the weakest spatial correlation; 3) the influence of surrounding service industries on different types of catering industry also varies. In general, the spatial correlation strength from strong to weak is as follows: fast restaurants, dinner restaurants, snack bars, and cold beverage shops. The local spatial differences are similar but the spatial difference of dining restaurants is the most obvious; 4) The estimation results of the Spatial Durbin Error Model at the street-town scale show that transportation facilities services, shopping services, and population size have the most direct impact on the POI number of local catering industries, with obvious spatial spillover effects. Both the population size and surrounding service industries are the main factors that influence the spatial distribution of fast food restaurants, while dinner restaurants, snack bars, beverage shops, and other catering industries are easily affected by transportation facilities and shopping services. In general, from the perspective of spatial correlation, this study deepens the research on the location theory of service industries. It also provides references for the study of commercial geography and the optimization and adjustment of the spatial pattern of the catering industry in big cities.

Freshwater is an essential landscape element in sustaining environment and socio-economic system in the Northwest China. Under the compounding impacts of climate change and human activities, the temporospatial patterns of freshwater in Northwest China (NWC) is undergoing substantial changes, which in turn is affecting socio-economic development and environment conservation in the region. This paper investigates the spatial and temporal patterns of freshwater in Northwest China in response to a changing climate based on a high-resolution global surface water dataset (JRC Monthly History v1.3) for the period 2000 to 2020. Seasonally, freshwater area within NWC is found increased rapidly from June to September, then dropped gradually from October with the reduction of available water. Interannually, the area of freshwater in NWC increased from 3.48×10⁴ km² to 4.82×10⁴ km² at a rate of 682.64 km²/a during 2000 to 2020. Spatially, the freshwater area expanded substantially along the Tarim River and in the western Qinghai Province. The expanding freshwater mainly occurs around perennial rivers or lakes such as the Tarim River, the Hotan River, Lake Taijinar, Lake Dabson and Qinghai Lake. Changes in freshwater area is found considerably affected by the changing climate in NWC. Based on the high-resolution climate reanalysis dataset (CMFD), it is found that the arid or semi-arid zone in the western NWC was experiencing a warm-wetting trend in climate, resulting notable expansion of freshwater. The increasing rate of freshwater area is the highest in the warm-wetting regions (with approximately 466.14 km²/a) followed by wetting regions. Joint distribution analysis of freshwater area and dominant climate factors shows freshwater area correlated positively to temperature and precipitation. The expansion of freshwater in Tarim River basin, northern Xinjiang and Qinghai province is more closely related to the increase in temperature and precipitation, with correlation coefficients greater than 0.4. The changes of freshwater area in NWC have contributed to strengthening the hydrological connectivity within the region, which could be conducive to regional environment conservation and socio-economic development.

The single machine learning-based landslide susceptibility prediction model has different focuses of features and a weak classification ability, and also the accuracy of traditional random sampling of non-landslide is low. To solve these problems, this study optimized Non-Landslide Samples (NLS) based on the information value model and utilized Stacking heterogeneous ensemble models to evaluate the landslide susceptibility of Fengjie County in the Three Gorges Reservoir. Firstly, 16 evaluation indexes were extracted based on multiple sources of topographic, geologic, and remote sensing data, including elevation, slope, aspect, profile curvature, plan curvature, lithology, distance to fault, topographic wetness index, stream power index, distance to river, normalized difference vegetation index, distance to road, and land use, and the correlation analysis was carried out to exclude high correlation indicators and construct the landslide susceptibility evaluation criteria system. Then, the NLS index was proposed based on the information value model to divide the non-landslide samples into two categories: information values less than or equal to 0, and greater than 0. Finally, the logistic regression model was used to compare the non-landslide samples under different NLS conditions, and the NLS index was used to obtain optimized non-landslide samples, which forms the training set with the same number of landslide samples. Finally, Random Forest (RF), Light Gradient Boosting Machine (LGBM), Gradient Boosting Decision Tree (GBDT), and homogeneous (Boosting-RF, Boosting-LGBM, Boosting-GBDT) and heterogeneous (Stacking) ensemble methods based on these three models were compared for susceptibility evaluation. The results show that non-landslide sampling using NLS can produce non-landslide samples of high quality and generalization ability, which in turn improves the learning ability of the model and the accuracy of susceptibility evaluation. The Stacking heterogeneous ensemble model has the best accuracy of 0.941, which is better than the Boosting homogeneous ensemble models (an accuracy of 0.902, 0.897, 0.870, respectively) and other single models (an accuracy of 0.882, 0.864, 0.855, respectively). These results indicate that the Stacking heterogeneous ensemble algorithm is capable of extracting landslide and non-landslide features from various spatial angles, realizing the complementary advantages and disadvantages of the models, significantly improving the performance of machine learning, and obtaining better predictions, and thus is a reliable landslide susceptibility evaluation model. This study contributes to a better understanding of the landslide activity, improves the reliability of regional landslide hazard risk assessment, and provides support for carrying out reasonable land use planning, disaster prevention, and mitigation strategies.

Spatiotemporal crime prediction often employs quantitative techniques such as Geographic Information Systems (GIS), geo-statistics, and big data analysis to predict the time and risk area (or location) of crime events that are more likely to occur in the future. In the era of big data, how to dynamically optimize the deployment of limited police forces and successfully improve the effectiveness of crime prevention based on data-driven crime predictions is a research focus in the field of global predictive policing. It is also a main practical direction for law enforcement agencies worldwide to implement modern proactive policing models. Traditional crime geography and spatiotemporal crime prediction methods mainly use police precincts or grids as the basic spatial analysis unit, and the analysis results are not conducive to guiding refined patrol force planning and deployment. The graph neural network based on deep learning can be combined with the topological structure of the road network at the micro scale, enabling precise crime prediction at the street scale. However, existing approaches rarely consider the impact of road weights in model prediction. In this paper, a Road Weighted Spatiotemporal Graph Convolutional Network (RW-STGCN) is constructed for street crime prediction by introducing road network accessibility and distance attenuation factors, and the model is evaluated using street theft crime data of Chicago. The results show that: (1) Compared to the spatiotemporal graph convolutional networks without considering road weights, the hit rate of the RW-STGCN increases by more than 6.5% across various road network coverage ratios (1%, 5%, 10%, and 20%), and the increase becomes more significant as the coverage ratio decreases, with a maximum increase exceeding 50%. This indicates the effectiveness and superiority of the RW-STGCN for smaller units; (2) Model ablation experiments show that the hit rate of the RW-STGCN considering road weights increases by 13.5% compared to the model result without considering road weights, and the model considering both road weights has a more significant improvement in prediction performance than the model considering only a single factor of distance attenuation weight or road network access weight, with a maximum increase of 12.9% in hit rate. This suggests that deep learning methods combined with geographic features can effectively improve the accuracy of crime prediction. The RW-STGCN is helpful for street crime prediction and can provide auxiliary decision support for law enforcement agencies to conduct scientific patrol planning and police force deployment based on road networks. In addition, it is also useful for the study of road-related urban computing problems.

As Artificial Intelligence Generated Content(AIGC) rapidly advances, various disciplines are shifting toward AI-driven scientific research. GeoAI technology, which focuses on geographic spatial intelligence, has the potential to outperform traditional methods in solving cartographic tasks. This shift presents both new opportunities and challenges for cartography. Despite some progress in integrating AI into cartographic research, limitations in computational power and other factors have hindered significant success in the past. As we enter the era of intelligence, both humans and machines will play critical roles in map creation and interpretation. Through artificial intelligence algorithms, maps can be produced quickly, at low cost, and on a large scale. However, there are also issues such as the instability of the quality of map works. The generation of map content has gone through the stages of expert-generated content and user-generated content and is developing towards the stage of artificial intelligence-generated content. In the traditional map-making phase, professional maps are produced by cartographic experts. While the quality of these maps is assured, the number of experts is limited. Consequently, the production cycle is long, the cost is high, the quantity of map products is limited, and they have not been produced on a large scale. At the current stage, generative artificial intelligence can produce map content in three forms: text-to-map (txt2map), map-to-text explanation (map2txt), and map style transfer (map2map). People can already use ChatGPT to generate maps by entering a piece of text, produce a textual explanation of a map by uploading an image of the map to ChatGPT, and even achieve map style transfer from images using Generative Adversarial Networks (GANs). The integration of artificial intelligence with the map transmission model has derived an intelligent map transmission model. It includes four stages: (1) Intelligent acquisition of mapping information: Sampling and collecting information about the real-world geographical environment through artificial intelligence methods, which is then processed and filtered into structured information for mapping; (2) Intelligent mapping: The process of intelligently generating maps through the use of colors, symbols, grading, and other representational methods based on mapping information; (3) Intelligent map reading: The process by which readers use artificial intelligence methods, combined with map language, domain knowledge, and personal understanding, to recognize the real world; (4) Intelligent interpretation of map information: Using artificial intelligence to interpret maps, thereby gaining cognition and understanding of the real world. Although progress has been made, research on using intelligent methods to address cartographic challenges is still in its early stages. Challenges include the lack of comprehensive training datasets, limited model algorithm generalization, and interpretability. These areas offer promising directions for future development.

The road boundary extraction from the vehicle-borne LiDAR point cloud can be easily affected by the occlusion of vehicles and pedestrians in urban environment. These occlusion phenomena will cause two problems: one is the generation of pseudo-boundary points, and the other is the discontinuity of boundary lines. We find that the elevation standard deviation constraint can effectively deal with the problems caused by occlusion. First, data pre-processing is carried out, including point cloud subdivision, cloth simulation filtering, and scanline storage. Second, a continuous double window is established based on scanlines. The bidirectional moving window method is adopted to construct elevation difference constraint, angle value constraint, and elevation standard deviation constraint to obtain candidate road points. Then, based on the continuity of road boundary, the DBSCAN algorithm in density clustering is used to generate relatively continuous and accurate road boundary points. Finally, the cumulative curvature value and distance of the boundary breakpoint region are calculated to determine whether a location is a junction. The boundary breakpoint is not considered connected if it is a junction; otherwise, it is regarded as a breakpoint caused by vehicle or pedestrian occlusion. The quadratic polynomial curve is used to smooth the boundary points, and the mathematical parameter model of the boundary is obtained. The experimental results show that the accuracy of road boundary extraction can exceed 80% in an urban environment with more occlusion.

OpenStreetMap (OSM) road network is an open-source dataset that is dedicated to providing people with a globe-free digital map resource, and it has been widely used in spatial analysis and applications such as route planning and vehicle navigation services. Meanwhile, in order to regulate traffic order and reduce heavy traffic congestion, the constraints of turning rules are generally implemented at intersections in urban areas. These constraints should be respected in the applications based on OSM road network. However, OSM road network lacks turning relationships at intersections, preventing its services from route planning and vehicle navigation. For this reason, to endow OSM road network structure with turning relationships, this study presents an intersection turning detection method based on map matching and string mapping, which takes advantage of crowdsourcing GNSS trajectory data in terms of its dynamic connection information at traffic intersections. Firstly, a structure detection method for OSM intersections is designed based on a top-down quadtree splitting idea, then the intersections with different sizes and complex and various shapes are reduced to the connection points. On this basis, the improved Hidden Markov Model (HMM) map matching algorithm is introduced to project low-frequency and high-noise trajectories onto OSM road segments. This algorithm considers the direction consistency between roads and trajectories, as well as the effective drift distance between two adjacent trajectory points, can identify trajectory sequences with semantic anomalies during the driving process. Secondly, to simplify turning relationship detection, a character encoding technology facing the intersection-related road segments is presented to map the trajectories crossing through intersections to the directional strings in turning process. The information enhancement method regarding the empty characters based on optimal path analysis is further designed to enhance turning trajectory support for short road segments. This approach helps restore the driving route information for low-frequency trajectories. Finally, the different turn modes of trajectories at the target intersection are mined by directly targeting the trajectory directional strings based on a string matching method, thus this study realizes turning information enhancement for OSM intersections referencing to the "consensus knowledge" of crowdsourcing trajectories. The complicated turning relationship identification for OSM intersections is transformed into the simple string matching. The experiment based on crowdsourcing trajectory data in Shanghai shows that the proposed method can detect turning relationships for OSM intersections with a precision rate of 90%, a recall rate of over 98%, and an F1-score of over 94%.

The converting evolution of cascading disaster scenario refers to that in the process of disaster scenario evolution, the disaster bearing bodies transform into new disaster hazards, forming a disaster chain. Rainstorm can easily cause serious secondary disasters such as waterlogging, debris flow and flood, and the combination of these secondary disasters will make the city more vulnerable. However, existing research on rainstorm cascading scenario deduction lacks the analysis of specific scenario evolution situations such as multi disaster combination, scenario element converting, and human-induced emergencies. Meanwhile, traditional research often relies on the probability inference based on existing scenario evolution networks, without providing a construction method for scenario evolution networks, making it difficult to adapt to the knowledge requirements of actual scenario situation converting deduction. To address the scenario converting evolution problems of urban rainstorm cascading disasters, this paper proposes a scenario converting deduction method for rainstorm cascading disaster response based on multi-source spatial data and probability analysis tools. First, based on local and non-local historical emergency cases, the scenario elements involved in the rainstorm cascading disaster scenarios and their potential converting paths are identified. Next, with the support of Baidu Encyclopedia and Wikipedia network knowledge resources, relevant scenario element features and their associations are extracted, and a Group Lasso machine learning method is adopted to achieve feature selection of involved scenario elements. Then, considering the multi-stage and complex scenario correlation in the process of cascading scenario evolution, a dynamic Bayesian network model for scenario converting deduction is constructed. Finally, a Markov chain Monte Carlo method is used to solve the Bayesian network and generate the converting probabilities. The proposed method is applied to the rainstorm response practice of Wuhan High-tech Zone. The use case results show that the proposed method can combine historical cases and network data to achieve rapid and effective generation of key scenario elements and their features, helping to improve the reliability of scenario converting deduction. At the same time, the proposed method supports the scenario converting deduction of small-scale disaster-bearing bodies such as geographic grids, which helps to provide more accurate rainstorm emergency decision-making support and provide good performance in visual analysis. The uncertainty analysis of the proposed method shows that the precision of original probabilities of key scenario element features and the size of generated geographic grids significantly affect the scenario converting deduction results. These findings provide important information for the local area and are expected to help the rainstorm disaster management of other jurisdictions.