The continuous generalization of geographic information poses a huge challenge to the classic geographic information analysis modes. Networked knowledge services will gradually become a new mode for geographic information applications, facilitating to transform the form of geographic computing into social computing. Geographic knowledge services need to connect people, institutions, natural environments, geographical entities, geographical units and social events, so as to promote knowledge assisted data intelligence and computational intelligence. Facing the urgent need for spatiotemporal knowledge acquisition, formal expression and analysis, this paper firstly introduces the concepts and characteristics of spatiotemporal knowledge graph. The spatiotemporal knowledge graph is a directed graph composed of geographic spatiotemporal distribution or geo-locational metaphors of knowledge that is a knowledge graph centered on spatiotemporal distribution characteristics. Secondly we proposes a research framework for spatiotemporal knowledge graph. The framework includes various levels from multimodal spatiotemporal big data to spatiotemporal knowledge services that contain ubiquitous spatiotemporal big data layer, spatiotemporal knowledge acquisition technique layer, spatiotemporal knowledge management layer, spatiotemporal knowledge graph layer, software/tools layer, and industrial application layer. Thirdly this paper introduces relevant research progress from text implied geographic information retrieval, heterogeneous geographic semantic web alignment, spatiotemporal knowledge formalization and representation learning. Combined with application practice, we then enumerate the construction and application approaches of domain oriented spatiotemporal knowledge graph. Finally, it discusses the key scientific issues and technical bottlenecks currently faced in the research of spatiotemporal knowledge graph. It is argued that in the era of large models, constructing explicit spatiotemporal knowledge graph and conducting knowledge reasoning to meet domain needs is still the only way for spatiotemporal knowledge services.

Geoscience Knowledge Graph (GKG) has strong capabilities of knowledge representation and semantic reasoning, thereby becoming a required infrastructure for the development of geoscience big data and geoscience artificial intelligence. However, existing studies on GKG were mainly conducted under the experimental scenarios. Because of a lack of research on the general framework of construction methods, sharing, and application of large-scale GKG for practical applications, it has not been used in practical applications in the geoscience field. For this reason, towards the needs of research and applications of geoscience big data and artificial intelligence for GKG, this paper first studied the construction techniques of large-scale GKG. Then, a general framework for covering the lifecycle of GKG including its construction, sharing, and application was proposed. Taking the big science program “Deep-Time Digital Earth (DDE)” as an example, the practice of developing GKG platform towards the practical application of DDE was carried out. Using this platform, this paper realized the construction of DDE large-scale GKG, the open sharing and application of built GKG, proving that the proposed framework can effectively support the construction, sharing, and application of large-scale GKG. This paper plays an important role in promoting the realization of the practical application value of GKG.

The new combat style places new requirements for battlefield environment service support. The intelligent service of battlefield environment urgently needs to improve knowledge based on the global multidimensional battlefield environment data. In view of the knowledge modeling problem of intelligent cognition of battlefield environment, this paper puts forward the classification method of battlefield environment knowledge and considers the battlefield environment knowledge graph as a new form of battlefield environment knowledge representation under the context of big data and artificial intelligence. To solve the fragmentation problem of triplet knowledge representation, a temporal hypergraph representation model of battlefield environment is constructed, a multi-level unified graph model combining entity knowledge, event knowledge, influence process knowledge, and service decision-making knowledge is realized, and all kinds of knowledge are represented as a unified knowledge hypergraph network with spatiotemporal and scene characteristics. Finally, the experimental verification is carried out based on the data of map, event, impact process, and combat impact effectiveness. The hypergraph network realizes the correlation of various battlefield environment knowledge from the semantic level, which can provide support for the further realization of intelligent reasoning and service decision-making based on hypergraph.

As a forward-looking and proactive policing mode, predictive policing has been a major innovation of modern policing reforms across the USA and European countries since it was proposed in 2008. As it does not involve the use of personal privacy data and can be integrated with police patrolling and precise crime prevention strategies, place -based spatial -temporal crime prediction has been a hot research topic and main component of policing practices. This research presents a systematic review of the progress of spatial-temporal crime prediction across the world since 2013 when the RAND Corporation released its special report on predictive policing. It contributes to the literature with the following five aspects: (1) summarizing the new trends in the field of spatiotemporal crime prediction studies in terms of the number of papers, research topics, leading scholars, and academic journals. The studies on spatial-temporal crime prediction have received extensive attention from various countries in recent years, and the research themes have shown a diversified trend. The most productive scholars are mainly from China and the USA, with the main focus on spatial-temporal crime prediction model development; (2) describing the new dynamics and progress of six basic components involved in the spatial-temporal crime prediction research, which are the prediction target, temporal scale, spatial scale, prediction method, performance evaluation measure, and practical evaluation. The four most widely studied types of crimes are theft, robbery, burglary, and motor vehicle theft. For burglary crime, the typical temporal unit for spatial-temporal prediction is 1-month; For the other three types of crime, the typical temporal unit is 1-day. For these four types of crime, the typical spatial unit is 200-meter grid. The top three models with the best prediction performance are random forest model, spatial-temporal neural network model, and Hawkes process model; (3) introducing several main commercial softwares for spatial-temporal crime prediction and global predictive policing practices; (4) investigating the relevant ethical issues and potential challenges that are embedded in each stage of practical applications, including data & algorithm biases, lack of transparency and countability mechanism; (5) prospecting future research directions in spatial-temporal crime prediction areas. This research provides a brief and panoramic image of the field of spatial-temporal crime prediction and can act as a reference for researchers and practitioners in relevant fields including crime geography, smart policing, and Policing Geographic Information System (PGIS).

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.

Convolutional neural networks have been widely used in the task of Remote Sensing Image Scene Classification (RSISC) and have achieved extraordinary performance. However, these excellent models have large volume and high computational cost, which cannot be deployed to resource-constrained edge devices. Moreover, in the RSISC task, the existing knowledge distillation method is directly applied to the compression model, ignoring the intra-class diversity and inter-class similarity of scene data. To this end, we propose a novel class-centric knowledge distillation method, which aims to obtain a compact, efficient, and accurate network model for RSISC. The proposed class-centric knowledge distillation framework for remote sensing image scene classification consists of two streams, teacher network flow and student network flow. Firstly, the remote sensing image scene classification dataset is sent into the teacher network pre-trained on a large-scale dataset to fine-tune the parameters. Then, the class-centric knowledge of the hidden layer is extracted from the adjusted teacher network and transferred to the student network based on the designed class center distillation loss, which is realized by constraining the distance of the distribution center of similar features extracted by the teacher and student network, so that the student network can learn the powerful feature extraction ability of the teacher network. The distillation process is combined with the truth tag supervision. Finally, the trained student network is used for scene prediction from remote sensing images alone. To evaluate the proposed method, we design a comparison experiment with eight advanced distillation methods on classical remote sensing image scene classification with different training ratios and different teacher-student architectures. Our results show that: compared to the best performance of other distillation methods, in the case of the teacher-student network belonging to the same series, the overall classification accuracy of our proposed method is increased by 1.429% and 2.74%, respectively, with a given training ratio of 80% and 60%; and in the case of teacher-student networks belonging to different series, the classification accuracy is increased by 0.238% and 0.476%, respectively, with the two given ratios. Additionally, supplementary experiments are also carried out on a small data set of RSC11 with few classes and few samples, a multi-scale data set of RSSCN7 with few classes and multiple books, and a large complex data set of AID with many classes of heterogeneous samples. The results show that the proposed method has good generalization ability. Trough the comparison experiments with similar techniques, it is found that the proposed method can maintain excellent performance in challenging categories through confusion matrix, and the proposed distillation loss function can better deal with noise through testing error curve. And visualization analysis also shows that the proposed method can effectively deal with the problems of intra-class diversity and inter-class similarity in remote sensing image scenes.

Multi-scale representation is one of the important research contents of geospatial data. This paper summarizes the research status of multi-scale representation of geospatial data from three aspects: geospatial data management, geospatial data scale transformation, and multi-scale representation of the map, and makes a systematic analysis and prospect of current research results. The main conclusions are as follows: ① In terms of multi-scale database and multi-scale spatial index of geospatial data management, three kinds of multi-scale database can provide better data support for multi-scale representation methods, and the hierarchical multi-scale index is the mainstream construction structure for the multi-scale database. However, at present, multi-scale database and multi-scale spatial index still have limited integration and matching ability of data at different levels, and the real-time consistency adjustment ability of data at different scales is also insufficient; ② In terms of the multi-scale transformation of geospatial data, automatic map generalization can be well combined with artificial intelligence technology. But due to the limitation of knowledge acquisition, there is still a long way to achieve automatic map generalization. The relevant achievements of intelligent automatic generalization research are mainly used to assist decision-making now, and the autonomous learning of comprehensive knowledge needs further research. Currently, most of the research is based on a discrete scale transformation model, which is incapable of continuous scale transformation. And due to the lack of a strong quality control mechanism, the results of automatic scaling have great uncertainty; ③ In terms of multi-scale representation of the map, map data types are multi-source, diverse, and flexible to use, and the multi-scale display is highly complex. Currently, the phenomena of hidden geographic information in map visualization need to be further explored. Finally, the future prospect of research on geospatial data presentation is proposed from the aspects of intelligent automatic generalization method, continuous multi-scale representation model, deep learning and cartographic synthesis, and multi-scale representation in the "new" era.

Traditional taxis and the e-hailing cars are two main transport vehicles for the public in current taxi market, which aim to satisfy the customized travel demand in daily lives of citizens in urban public transportation system. Due to the differences in service modes and commercial patterns, the two vehicles are appropriate for different target groups. Investigating the spatial and temporal characteristics of these two types of vehicle based on human travel flows can support the applications such as optimization of the urban public transportation and land use planning. The geographical flow space theory proposed recently provides a new theoretical perspective as well as a systematical analysis framework in studying the flow patterns of the travels by different types of vehicles. In this paper, we adopt this formulated theory framework to describe the travel flow. We select five typical flow patterns, namely random, clustering, aggregation, divergence, and community patterns, to reveal their spatial distribution characteristics and compare the differences in their travel patterns. The trajectory dataset of traditional taxis and the e-hailing cars in Xiamen City is employed to validate the effectiveness of the geographical flow space theory. We find that: (1) the travel flows of the two types of vehicles present significant non-random characteristics in flow space; (2) people tend to choose e-hailing cars for long distance travel, while prefer the traditional taxis for short and medium distance travels; (3) the two types of cars show different spatial distribution characteristics of the four typical flow patterns. The travels by e-hailing cars are more widely distributed and exhibit clustering patterns around the sub-centers at the suburban areas outside the core Xiamen Island and the east-southern software park area inside the Xiamen Island. Due to the travel demand driven model, the e-hailing cars satisfy the emerging high travel demand areas and tend to form community patterns. While the traditional cars are mainly distributed around the well-known city landmarks (e.g., Zengcuoan, Zhongshan road) on the Island; (4) approximately a quarter of the local areas have more than one typical flow patterns. Different types of cars exhibit different co-location flow patterns and spatial distribution characteristics. The mixed flow patterns derived from the geographical flow theory provide a more comprehensive perspective to better understand the travel flows, which can mitigate the misleading information from each isolated flow pattern. The above findings imply that the geographical flow theory can help to better understand the characteristics of the geographical flows and can be used to improve the applications based on related results.

With the deepening of global economic integration, maritime traffic congestion and ship accidents occur frequently. In order to supervise and analyze the marine ship activities, the traditional methods mainly use the ship positioning data for data mining without combining other marine multi-source data for the analysis of ship spatiotemporal activity process and behavior pattern, and thus lack deep knowledge mining. Therefore, this paper makes comprehensive use of multi-source data and constructs the ship activity knowledge map based on extracting the semantic information of trajectory, which provides an effective way for the transformation of trajectory spatiotemporal point sequence with low knowledge density to high-order semantic knowledge. Specifically, firstly, by analyzing the characteristics and constituent elements of ship activities, the ontology layer of ship activity knowledge map is designed based on the core idea of "process-event-behavior"; Then, the track semantic information is extracted by Stop/Move model, and the ship emergencies are extracted by DMCNN model to complete the filling of instance layer; Finally, the above model and method are verified by constructing a prototype system. The results show that the ship activity knowledge map constructed in this paper can support the knowledge representation of ship routine activities and emergencies, and realize spatiotemporal activity query and backtracking, so as to achieve the effect of semantic enhancement, which has a certain application value.

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.

With the development of Unmanned Aerial Vehicle (UAV) technology, it has been applied to various tasks in different fields. The prerequisite for a UAV to perform successful aerial tasks is accurate localization of its own position. Generally, traditional UAV navigation relies on the Global Navigation Satellite System (GNSS) for localization. However, this system has disadvantages such as instability and susceptibility to interference, leading to situations where UAV cannot use GNSS for positioning, known as GNSS-denied environments. This study focuses on the navigation and positioning of UAV in GNSS-denied environments and proposes a UAV visual retrieval and positioning method that comprehensively utilizes local and global deep learning features of known satellite orthophotos. Specifically, ConvNeXt is used as the backbone network, combined with generalized mean pooling, to form a retrieval feature extraction algorithm for extracting global features of satellite and UAV images. A triplet loss function considering the overlapping area between images is designed for the retrieval and positioning tasks, and a corresponding training data set is established to train the feature extraction algorithm. Then, the satellite images within a certain range are retrieved according to the extracted global features, and the preliminary retrieval results are obtained. In order to further improve the accuracy of the retrieved target images, the LoFTR algorithm based on deep learning local features is used for matching and reordering. Since the LoFTR algorithm has many mismatches, RANSAC is used to screen the matching results. Experiments using the test datasets we established demonstrate that the proposed method obtains an average accuracy of 90.9% and an average time cost of 2.22 seconds for retrieving satellite images in different seasons from fully overlapped UAV simulated images. The accuracy of the UAV real image test is 87.5%, which can meet the UAV positioning requirements.

China is one of the countries that are most severely affected by typhoons. The direct economic losses caused by typhoons amount to more than 10 billion yuan, and the affected population is more than one million each year in China. Typhoon disasters seriously threaten the social economy and natural environment of coastal areas. As a result, there is an immediate necessity to improve disaster emergency management and comprehensive disaster prevention and mitigation. With the concept of knowledge graph proposed by Google in 2012, it has gradually become a research hotspot in the field of artificial intelligence and played a role in applications such as information retrieval, question answering, and decision analysis. The information integration and representation capability of the knowledge graphs can provide effective support for dynamic monitoring and management decisions of typhoon disaster events. There are problems with the current typhoon disaster models in the representation of spatiotemporal processes. Most disaster knowledge graphs are analyzed for single elements of disaster events, and the research on ontological representation and analysis of disaster development process is still lacking. Firstly, we propose a typhoon disaster events knowledge representation model established from five levels: concept, object, state, characteristic, and relationship, by analyzing the components and dynamic characteristics from the typhoon disaster mechanism. Second, this model considers the multi-granularity of typhoon event information, and unifies the different feature information into each object. Besides, in order to highlight the evolutionary characteristics of typhoon events, the state is taken as the cross-section of the process in a specific spatiotemporal feature. The state is an action or record of an object occurring in time and space. The process is the procedure that properties, forms, and patterns undergo as it gradually changes over time. Finally, we construct a knowledge graph of typhoon disaster events using the 2021 severe typhoon In-Fa as a case study. The results show that the model not only highlights the characteristics of different objects portrayed in the event, but also expresses the spatiotemporal processes of typhoon disaster events through the state sequences of multiple objects. The knowledge graph can be applied as a primary knowledge source in the emergency decision management of typhoon disaster events, which can undoubtedly enable relevant decision-makers to better perceive the spatial and temporal development of typhoon disaster situations. In disaster assessment, based on the rich contents covered in the knowledge graph, it can cope with assessing various aspects such as human casualties, economic losses, and secondary disasters.

Rural Access Index (RAI) is an indicator (SDG 9.1.1) of the UN's Sustainable Development Goals (SDGs), and it measures the proportion of the rural population who live within 2 km of all-season roads. Currently, there is a lack of evaluation on RAI's spatial pattern in China and its influencing factors in existing studies. To fill this gap, our study proposes another indicator, Non-Served Rural Population (NSRP), and employs six open datasets including 1:250 000 road data, 1:1 000 000 county-level division data, 100 m population data, urban extent data, DEM data, and GDP data to evaluate both the RAI and NSRP indicators for 2852 counties in China. We also select two categories of variables (i.e., socio-economic and terrain variables) to analyze the spatial patterns of RAI and NSRP. Results show that: (1) The RAI and NSRP of China are 99.5% and 4.8 million, respectively. It means that 99.5% of rural population in China live within 2 km of all-season roads, and this value is much higher than that published by The World Bank. However, there still are 4.8 million rural population that live outside the 2 km of all-season roads; (2) The spatial patterns of both RAI and NSRP can be divided into two parts. That is, a relatively high RAI and low NSRP in the southeast of the “Hu Huanyong Line”, but on the contrary, a relatively low RAI and high NSRP in the northwest of the “Hu Huanyong Line”; (3) Both the RAI and NSRP are significantly correlated with socio-economic and terrain variables, and the correlation between RAI (or NSRP) and the terrain variable is the strongest, which indicates that the terrain may be a main factor that affecting the spatial patterns of these two indicators. This study first maps the spatial pattern of SDG 9.1.1 in China, which provides basic data, helpful information, and knowledge for improving road infrastructure in rural areas of China.

Accurate identification of visual factors affecting environmental safety perception provides important support for improving urban traffic environment and enhancing pedestrian travel safety. However, it is difficult to quantify environmental safety perception in complex scenes on a large scale in existing studies. Therefore, this study uses image semantic segmentation and object detection techniques to extract visual factors from streetscape images and constructs a road safety perception dataset by manual scoring in combination with deep learning methods. The influencing factors of environmental safety perception are also identified based on light gradient boosting machine algorithm and SHAP interpretation framework. In our study, the Anning District college cluster in Lanzhou City, a canyon city with a special road environment, is selected for the empirical study. Results show that: (1) The safety perception scores of colleges and commercial streets are high, while those of urban roads are generally low; (2) The image ratios of sky, sidewalk, road, and tree are the four factors that have the greatest influence on environmental safety perception, among which the image ratio of sky is linear, the image ratios of sidewalk and tree are similar to a logarithmic function, and the image ratio of road is similar to a quadratic function; (3) The proportion and number of visual factors have an interactive effect. A reasonable distribution of visual factors helps to create good spatial sightlines and suitable behavioral spaces, thus enhancing the perception of environmental safety.

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.

Wetland is of great significance to biodiversity and climate change, and it is also one of the basic living environments of human beings. In order to better understand and express wetland knowledge and the relationship between classifications, this paper proposes an ontology-based wetland knowledge graph construction method. Based on the land cover classification system of GlobeLand 30, this paper establishes the conceptual structure of wetland data and the rich semantic relationship between the elements around wetland type definition, spatial pattern, case distribution, and trend change. Firstly, based on the prior knowledge of wetlands, taking the wetland types in the GlobeLand 30 classification system as an example, we analyze the wetland domain knowledge around the wetland types, feature distribution, and other elements, extract the semantic relationship between knowledge, and construct the ontology database of wetland knowledge by combining top-down and bottom-up methods. The conceptual framework of wetland knowledge graph is formed through ontology modeling. Secondly, based on the wetland knowledge automatically extracted from the technical specification text and encyclopedia website, the extracted conceptual knowledge is stored in the model layer, and the data layer is constructed from bottom to top. The main contents include knowledge acquisition and knowledge fusion. According to the concepts contained in wetland knowledge, the relationship extraction of wetland knowledge is carried out, mainly including attribute relationship, spatial relationship, and temporal relationship. Using the wetland directory crawled from the wetland China website, the wetland entity name and knowledge are directly extracted from Baidu Encyclopedia by means of web crawler to form a triple. Finally, Through the above construction processes of wetland knowledge graph, the wetland related data with different structures are transformed into structured knowledge triple data, and the graph database Neo4j is used for semantic relationship storage with the "node relationship" storage model. Knowledge graph provides a new idea for the study of rich knowledge representation and storage in the field of land cover. It is a bridge between the basic geographic data of surface coverage and spatial knowledge service. It is of great significance to promote the sharing and reasoning analysis of surface coverage data. Taking the wetland land cover type as the research example, the knowledge graph constructed in this paper expands the conceptual description information of wetland entities, explores the wetland knowledge representation method by considering the temporal and spatial characteristics, and provides a new perspective and application demonstration for the expression of land cover knowledge.

Extreme temperature events occur frequently and pose a serious threat to human health. However, due to the variability of individual and environmental influences, the perception of temperature change and the trend of actual temperature change in different populations do not exactly coincide. A deep understanding of the human perception characteristics of temperature change plays an important role in improving the management, adaptation, and warning capabilities for coping with extreme weather. Traditional survey data are insufficient in sample size and coverage, moreover, lack of diverse individual samples. And medical simulation results are strongly influenced by the parameters of environmental variables and often differ from the real situation. In this study, we used Weibo data to characterize human perception, that is, individual descriptions of temperature based on subjective feelings. We analyzed the quantitative response relationships between human perception of temperature and temperature observation variables and used temperature tolerance and sensitivity to measure temperature perception characteristics. We investigated geographical changes in human perception characteristics of temperature and its local variations in different seasons and among different groups over 31 Chinese cities. We then used the generalized linear regression model to analyze the influencing factors of temperature perception. For example, climatic factors such as climatic zones, annual average temperature, and annual average precipitation, as well as social factors such as urban population and Gross Regional Product. Our results showed that the human perception of temperature exhibited regular, nationally conspicuous shifts along latitudinal gradients, the lower the latitude, the stronger the average heat tolerance and cold sensitivity. They showed a significant trend linearly toward horizontal increase from the northern regions to the southern areas at a rate of 0.42 and 0.51 per degree, respectively. In contrast, the average cold tolerance was weaker at a rate of 0.31. There were also significant differences in human perception of temperature in different seasons and among different groups. The abnormal temperature in the off-season was more likely to attract people's attention to temperature change, and teenagers and females were more sensitive to cold. The regional differences in temperature perception characteristics were strongly associated with climate regions. People in temperate regions showed greater heat tolerance than those in the tropics, while people in the tropics showed greater temperature sensitivity. Our findings could provide insights into the characterization and patterns of the human perception of local temperature and have potential for several issues in terms of planning, management, and decision-making related to Extreme temperature event.

Natural language is an effective tool for humans to describe things, with diversity and ease of dissemination, and can contain human spatial cognitive results. How to use natural language to describe geographic spatial scenes has always been an important research direction in spatial cognition and geographic information science, providing important application values in personalized unmanned tour guides, blind navigation, virtual space scene interpretation, and so on. The essence of natural language description of geographic spatial scenes is the process of transforming the two-dimensional vector of geographic space into a one-dimensional vector in word space. Traditional models perform well in handling spatial relationships, but are somewhat inadequate in natural language description: (1) spatial relationship description models are one-way descriptions of the environment by humans, without considering the impact of the environment on the description; (2) spatial scenes emphasize traversal-based descriptions of spatial relationships, where each set of spatial relationships is equally weighted, which is inconsistent with the varying attention paid by humans to geographic entities and spatial relationships in the environment; (3) the spatial relationship calculation of traditional models is a static description of a single scene, which is difficult to meet the requirement of dynamic description of continuous scenes in practical applications; (4) the natural language style of traditional models is mechanical, lacking necessary knowledge support. This article proposes a spatial scene natural language generation framework Map2Text (M2T) that integrates multiple knowledge graphs. The framework establishes knowledge graphs for spatial relationships, language generation style, and spatial attention, respectively, and realizes the fusion of multiple knowledge graphs and the generation of natural language descriptions of spatial scenes within a unified framework. The spatial scene description knowledge graph solves the pruning problem of traversing spatial relationships, and establishes the relationship between spatial scenes by building a spatial relationship graph, supporting continuous expression of spatial scenes; the natural language style knowledge graph establishes the relationship between spatial expression and language style, achieving diversified language styles that are appropriate for spatial natural language expression; the spatial attention knowledge graph captures the nuances of natural language spatial expression by establishing an attention matrix based on the interaction state between the subject and object of the spatial scene. An experimental prototype system designed based on the Beijing Forbidden City demonstrates that the system-generated results are close to human travel notes, with more complete content coverage and more diverse styles, verifying the effectiveness of the M2T framework and demonstrating the potential value of natural language description of spatial scenes.

The scientific and quantitative evaluation of urban vitality can provide an important basis for urban planning and urban coordinated development. Existing studies on urban vitality and urban planning both focus on the characteristics of people's activities, without considering the psychological feelings of urban residents. In view of the current situation that residents' emotions are easily ignored in research, this study selects Baidu heat map to measure the intensity of population agglomeration intensity and uses the emotional analysis results of micro-blog text data to measure emotional intensity. Using the TOPSIS model to calculate the comprehensive vitality of the city, a comprehensive vitality evaluation framework considering population agglomeration and emotional intensity is proposed. This study selects eight influencing factors from three dimensions: urban physical environment, economic environment, and ecological environment, including road accessibility, land use mix, the density of POI, building density, nighttime light intensity, salary level, housing price level, and vegetation coverage. The influence of the eight influencing factors on the spatial heterogeneity of urban vitality is further explored by the GeoDetector model. This study shows that: (1) The comprehensive vitality evaluation method integrating population agglomeration intensity and emotional intensity proposed in this study can better reflect the spatial differentiation pattern of urban vitality. The effectiveness of this proposed framework for evaluating urban comprehensive vitality is verified by the analysis results of the typical sampling regions; (2) Among the eight influencing factors, the density of POI has the greatest influence on urban comprehensive vitality, while the influence of vegetation coverage on urban comprehensive vitality is the weakest. However, the interaction between vegetation coverage and other factors has the most significant impact on the spatial heterogeneity of urban vitality. It shows that the vegetation coverage factor does not directly act on the spatial heterogeneity of urban vitality but indirectly affects the spatial differentiation of urban comprehensive vitality by coupling the road accessibility, density of POI, and building density.

Western Guangdong is one of the three major sugarcane producing areas in China. Sugarcane in western Guangdong is mainly distributed in Zhanjiang, with more than 2 million sugarcane farmers. In 2020, the sugarcane planting area in Zhanjiang reached 130 030 hectares. Mapping sugarcane plantation and analyzing its spatiotemporal characteristics in western Guangdong are of great values for making polices in sugarcane industry, optimizing the distribution of sugarcane plantation, and promoting production efficiency. Remote sensing technology provides an efficient way to acquire land cover information. In this study, the sugarcane plantation distribution information in 2000, 2008, and 2020 was acquired based on Landsat remote sensing data and statistics data in sugarcane planting areas. Following steps were implemented: preprocessing of Normalized Difference Vegetation Index (NDVI) time series, construction of reference NDVI of sugarcane, extraction of the amplitude and the maximum of NDVI time series, and identification of sugarcane using the Time Weighted Dynamic Time Warping (TWDTW) method. The TWDTW method calculated the distance between NDVI time series of unknown pixels and sugarcane pixels, and a distance threshold was set via the statistics data to acquire the sugarcane plantation distribution. Based on the extracted distribution of sugarcane plantation, the kernel density of sugarcane distribution was calculated to analyze the spatial clustering characteristics of sugarcane planting areas. Landscape pattern indexes such as the percentage of landscape, average patch area, patch density, and aggregation index were calculated to analyze the spatial distribution characteristics of sugarcane planting patches. The topographic characteristics of sugarcane planting areas were also analyzed based on DEM data. The results showed that: ① the TWDTW model could realize sugarcane identification with high accuracy by combing remote sensing time series data and statistics data. In 2000, 2008 and 2020, the average accuracy of sugarcane mapping reached 87.62%; ② Sugarcane was mainly distributed in Suixi, Leizhou, and Xuwen in western Guangdong. The distribution of sugarcane planting in Suixi and Leizhou presented a pattern of high-density aggregation in multi centers; ③ From 2000 to 2020, the average area of sugarcane patches increased, the patch density decreased, and the aggregation index increased in Suixi and Leizhou, which indicated that the layout of sugarcane plantation had been significantly adjusted in these areas, and sugarcane production showed a trend of intensive production; ④ In Suixi and Leizhou, most of sugarcane was planted in flat areas, showing a great potential to develop mechanized production.

The graph structure-based knowledge graph plays important roles not only in the description and reasoning of semantic network, but also in the structured abstraction and spatial reasoning of spatial entities. The relational information of spatial entities is recorded in edges in the knowledge graph. Through the edge-based knowledge graph computational reasoning such as path detection, sub graph alignment, pattern discovery, etc., it can play an important role in spatial scene cognition. Geographic knowledge graph is a knowledge system that formally describes geographic concepts, entities, and their interrelationships. It has both the connotation and characteristics of general knowledge and the specific spatiotemporal characteristics of geographic knowledge. It can connect semantic models with spatiotemporal models to describe semantic relations, spatial relations, and temporal relations, and has great application potential in the expression, understanding, acquisition, and reasoning of geographic knowledge. The existing research work of geographic knowledge graph is mostly focused on semantics, and the extraction and expression of semantic relations are very rich and comprehensive, which can support further functions such as semantic search and association analysis of geographic knowledge. However, the knowledge expression of geographic knowledge graph in spatiotemporal model is relatively lacking, and the existing spatial relationship is limited between elements, rarely involving the further distribution situation and spatial pattern in spatial cognition. Thus, the geographic knowledge graph needs to be strengthened in terms of spatial semantic knowledge. Based on the principle of knowledge graph construction, this paper takes the construction of geographic knowledge graph of buildings as an example to realize the grid-pattern recognition of buildings. Firstly, the buildings are abstracted into entities and expressed as nodes of the graph, and the spatial neighborhood relations between buildings is extracted based on geometric proximity analysis, so as to build the geographic knowledge graph of the building group. On this basis, combined with the domain knowledge of building pattern recognition, it further infers and constructs other spatial semantic relations, and improves the geographic knowledge graph. Then the grid-pattern of the buildings complex scene is expressed as the rules of the knowledge graph, which is based on NoSQL language for reasoning. The results show that this method can effectively extract the linear pattern of buildings and further deduce the grid-pattern, which demonstrates the important role of geographic knowledge graph in spatial reasoning and its good adaptability in domain problem research, and provides ideas for the application of geographic knowledge graph in the field of spatial cognition.

The development of financial network has profoundly changed the form of knowledge spillover between cities and further affected the level of urban economic growth. The research on the externality of financial network has gradually become a research hotspot in financial geography. With the assistance of the data of headquarters and branches of enterprises in China's financial industry from 2005 to 2020, this paper combines the methods of social network analysis and recursion thought to calculate the centrality of financial network to analyze its spatial and temporal distribution pattern. Meanwhile, we use the OLS model to analyze the influence mechanism of financial network centrality on urban economic growth in China. The study finds that: (1) From 2005 to 2020, the centrality of financial network showed a "core-edge" distribution pattern, but the spatial agglomeration degree of financial network was decreasing. In this paper, with the help of the Core/Periphery algorithm in UCINET software, cities are divided into core and peripheral cities according to the 2020 financial network，and finally 52 cities with core status, such as Beijing, Guangzhou, and Hangzhou, and 239 cities with peripheral status, such as Anshan, Binzhou, and Foshan, are identified. Cities in the eastern region play an important role in the allocation of financial network resources, forming a "core-periphery" pattern with Beijing, Shanghai, and Shenzhen as the core cities and the other cities as the periphery cities； (2) The development of financial network can not only alleviate financing constraints, but also affect urban economic growth by promoting knowledge spillovers under the influence of network externalities. Cities with larger network links and better accessibility have higher levels of economic growth, and the knowledge spillover effect is more dependent on network proximity than location advantage in "place space"; (3) The degree of knowledge spillover promoted by financial network centrality shows spatial heterogeneity, and the core city which plays the role of "knowledge gatekeeper" can obtain greater benefits from network links. Due to the lack of "knowledge gatekeepers", peripheral cities are unable to make full use of external resources, which exacerbates the risk of being at the low end of the value chain and finally leads to the economic growth level of core cities much higher than that of peripheral cities. In the future, we should attach great importance to the construction of financial network and give full play to the driving role of financial network in urban economic growth in China.

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.

In the era of big data, the spatio-temporal category, information content, and application scenarios of Geographic Information Systems(GIS) have expanded unprecedentedly. GIS needs to transform from the passive adaptation mode of exception processing into an active kernel-supported mode, forming a new generation of spatio-temporal information system. Given that the essence of GIS is an information system with cartographic data model as the core, this paper summarizes the research paradigm of GIS from three aspects: research objects, basic principles, and technical methods, and analyzes the new requirements of spatio-temporal information expansion on the GIS research paradigm. Secondly, by analyzing the cognitive model of Pan-Spatial Information System (PSIS) and the multi-granularity spatio-temporal object data model, the theoretical and technical routes of the PSIS based on spatio-temporal entities are concluded, and its practice and application in many fields are summarized. Then, it systematically analyzes the specific extension mode of PSIS in GIS research object, basic principles, and technical methods, respectively, and proposes the PSIS research paradigm. Finally, this paper summarizes the basic content of the PSIS research paradigm, compares the core content with the GIS research paradigm, and looks forward to the impacts and changes that the advanced research paradigm of GIS would bring.

Understanding the urban spatial pattern from the perspective of the “Production-Living -Ecological” function not only paves the way to the optimization of land spatial structure, but also reflects the internal functional form and combination mode of urban land. However, in the past, the recognition of urban “Production-Living -Ecological Spaces” (PLES) mainly relied on remote sensing images, Point of Interest (POI), and land use data, and there was a lack of three-dimensional information within a city. Street View Images (SVI) can reflect the characteristics of the streets in the city and capture large-scale and high-resolution objective measurements of the physical environment within a street from a close-up view. Therefore, based on the semantic features of the scene extracted from the SVI, this paper proposes a method of identifying PLES in the central urban area and analyzing the importance of different features of the PLES. Taking the Fourth Ring Road of Chengdu as the study case, the classification system of PLES is constructed based on POI data, and the proportion of PLES is calculated at each SVI sampling point. The eXtreme Gradient Boosting (XGBoost) algorithm is used to identify the urban PLES, and a comparative test of model accuracy is also carried out. The spatial distribution of PLES in the study area is analyzed from three scales, i.e., road network, 500-m grid, and traffic analysis zone. The SHapley Additive exPlanation (SHAP) method is introduced to identify the important features that contribute to PLES. The results are as follows: (1) The proposed method of identifying PLES based on SVI in this paper has a high accuracy. The R² of the model for identifying PLES reaches 0.6, indicating the feasibility of SVI for identifying PLES; (2) The spatial pattern of PLES reveals that the study area is dominated by production-living spaces, which are large in number and distributed in pieces in the study area. The number of units dominated by ecological space is small, and they are mainly distributed in large parks; (3) Among the semantic features of the seven types of scenes, street openness and motorization level have the greatest impact on the formation of the PLES. Based on PLES, this study uses SVI data to conduct a fine-scale analysis of land use in central urban areas and determine the types of urban land. This paper enriches the data and methods of PLES identification and provides a new tool for the optimization of urban spatial structure and development decision making.

Accurate and reliable short-term passenger flow prediction can support operations and decision-making of the URT system from multiple perspectives. In this paper, we propose a URT multi-step short-term passenger flow prediction model at the network level based on a Transformer-based LSTM network, Depth-wise Attention Block, and CNN network, named as Spatial-Temporal Integrated Prediction Model (STIPM). The STIPM comprises three branches. The first branch takes time-series inflow data as input, and a Transformer-based LSTM network is selected to extract the temporal correlations. The second one takes timestep-based OD data as input, and many spatial and temporal features are captured using Depth-wise Attention Blocks. Meanwhile, timestep-based OD data can better include inter-station relations and global information. The third branch takes Point of Interest data (POI) as input and CNN network is utilized for spatiotemporal features extraction, which can also become the bridge between spatial and temporal features. Moreover, the “Multi-input-multi-output Strategy” for multi-step prediction is used to obtain a longer prediction period and more detailed information under a relatively high forecasting accuracy. The STIPM is applied to two large-scale real-world datasets from the URT system, and the obtained prediction results are compared with ten baselines and four variants from itself, in which STIPM model achieves highest prediction accuracy indicated by RMSE, MAE, and WMAPE evaluations, which demonstrates the superiority and robustness of the STIPM.

Terrain music, the study of terrain feature lines, describes terrain undulation patterns in audible form. This paper takes terrain music as the starting point to simulate and quantify the morphology of terrain characteristic lines, and further discusses the spatial differentiation characteristics and laws of the terrain on the Loess Plateau. Based on the DEM data with a resolution of 30 m, 53 typical watersheds evenly distributed on the Loess Plateau in northern Shaanxi were selected as test sample areas, and the music theory knowledge, digital terrain analysis, and geostatistical theory were integrated. The watershed boundary profile was taken as the entry point to realize the digital expression of the land surface morphology. The Kriging method was used to construct a spatially differentiated map of terrain music index, so that the spatial distribution patterns and characteristics of the terrain could be further analyzed. On this basis, the spatial distribution of terrain music index on the Loess Plateau in northern Shaanxi and the comparative analysis with traditional indicators were further discussed. Results show that the terrain music index can quantitatively describe and reveal the spatial distribution characteristics of the terrain from multiple angles: ① The correlation coefficient between jump-in index and terrain undulation is -0.486, which quantitatively describes and reveals the spatial distribution characteristics of terrain from the degree of terrain undulation; ② The correlation coefficient between the grade progression index and slope is -0.328, which quantitatively describes and reveals the spatial distribution characteristics of terrain from the degree of slope of the terrain; ③ The correlation coefficient between the modal progression index and the profile curvature is -0.309, which quantitatively describes and reveals the spatial distribution characteristics of the terrain from the degree of terrain curvature. This study expands the research scope of digital terrain analysis and promotes the integration of music theory and geomorphology research, which further reveals that the application scope of terrain music related research methods in the field of geomorphology is different from that of traditional methods. This study examines the characteristics and internal mechanisms of spatial differentiation of terrain from the perspective of audibility, which deepens the understanding of development processes and internal mechanisms of terrain on the Loess Plateau.

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.

A reasonable spatialization of urban carbon emissions is an important prerequisite for formulating clear carbon emission reduction policies. However, previous studies relied heavily on the nighttime light data with coarse spatial resolution and did not consider the huge differences of carbon emissions between various industry sectors. Therefore, the corresponding results cannot accurately reflect the spatial distribution of carbon emissions. To solve the disadvantages of previous methods, this study proposed a more reasonable method for the spatialization of carbon emissions. Firstly, three statistical models were used to estimate the carbon emissions of various industry sectors for Guangzhou in 2019. Next, the spatial distribution of carbon emissions was simulated based on the combined use of Luojia1-01 nighttime light and urban functional zoning data. Based on the spatialization result, both the global and local spatial autocorrelation analyses were carried out to reveal the spatial characteristics of carbon emissions in Guangzhou. Finally, the random forest model was used to investigate the socio-economic driving factors behind the carbon emissions in Guangzhou. The results are summarized as follows: (1) Although the carbon emissions of Guangzhou increased slowly after 2011, the total emission volume still reached 83.12 million tons in 2019, in which the transportation sector played a dominant role; (2) Compared with the commonly-used ODIAC (1 km), EDGAR (10 km) carbon emission products and the carbon emission spatialization results based on NPP-VIIRS (500 m), the result generated by high resolution (130 m) nighttime light and urban functional zoning data can more accurately characterize the spatial differences of carbon emissions; (3) There was a significant positive global spatial autocorrelation of carbon emissions in Guangzhou, resulting in highly concentration areas of secondary and tertiary sectors; (4) The main influencing factors for the secondary sector's carbon emissions were public budget revenue, GDP of the secondary sector, public budget expenditure, and fixed asset investment. In comparison, the major contributors to the tertiary sector's emissions were retail sales of consumer goods, GDP of the tertiary sector, GDP per district, and population. In summary, this study carefully considers the differences in industry structure, and then utilizes the high-resolution nighttime light data to investigate the distribution pattern of carbon emissions. The results will be helpful for policy-makers to formulate reasonable carbon emission reduction and industrial optimization strategies.

With global warming, the frequency of extreme weather events and major meteorological disasters is increasing globally. It is important to study the relationship between climate change and the frequency of meteorological disasters for disaster prevention and mitigation in the context of climate change. In this paper, a method is proposed for automatic extraction of spatial and temporal events of meteorological disasters based on natural language processing technology. Because there is a huge amount of spatial and temporal information of meteorological disasters available in literature and web data. Specifically, (1) A coarse-to-fine method was proposed to build a training corpus of meteorological disaster annotations based on professional literature. Firstly, a unified meteorological disaster knowledge system oriented to textual events is constructed to address the problems of ambiguity and incompatibility of different literature materials. Then a coarse annotation method based on chapter structure was constructed, and a Labeled LDA model-based and a fine-grained annotated corpus screening method based on TF-IDF and N-gram models were developed for long texts (modern texts) and short texts (literary texts), respectively, solving the problem of rapid corpus construction; (2) A method for automatic classification of spatiotemporal events of meteorological disasters based on the BERT-CNN model, which integrates contextual semantic features and local semantic features at multiple granularities, was developed for the integrated processing of short and long texts; (3) Using this method, the spatiotemporal events of meteorological disasters were automatically extracted from the textual and web data, and their macro F1 values reached 89.09% and 80.06%, respectively. The spatiotemporal distributions of major events of meteorological disasters were highly correlated with professional statistics; (4) Based on the above results, the spatiotemporal evolution of disasters in various historical periods in China was also reconstructed. We found that the overall volume of disaster data in each period showed a gradual increasing trend, with heavy rainfall disasters, floods, and droughts being the main types of disasters in China. Our method enables both the automatic extraction of long text events from the web and the automatic detection of short text events from literatures, providing a new technique for application of text data to meteorological disaster research and monitoring.