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.

Owing to the rapid advent of urbanization and the increasing demand for medical services by residents, the pressure on medical services in densely populated areas is surging. The analysis of the accessibility of medical service facilities is of primordial importance. In this study, the medical data was garnered from the Fuzhou Municipal Health Commission, and the crawler technology was used to yield the number of residential households to estimate the population. By use of the Baidu map to obtain the real time road condition information of the peak and non-peak time periods, the access time under the optimal route from the community residential districts to the hospital based on the real-time road condition was calculated, and the time zones of medical services were drawn. The accessibility of general hospitals in the main urban area of Fuzhou was analyzed using the two-step mobile (Ga-2SFCA) search method boosted by the Gaussian distance attenuation function, considering factors such as the travel mode, searching time threshold, and travel peak hours. The results yielded show that: (1) By integrating Baidu Map API into Ga-2SFCA model, multivariate and fine-grained analysis of accessibility was implemented, leading to the accurate measurement of urban medical service supply and demand; (2) The time cost of public transportation at different periods was less affected by traffic congestion, and reaching tertiary hospitals was faster. Under the premise of advocating green transportation, this mode of public transportation was recommended for medical treatment; (3) Under different conditions, the accessibility of medical facilities depended on the space of residential differentiation characteristics significantly, on the whole presenting a "single center" and "diminishing layer coil" distribution. High accessibility of residential areas was mainly distributed in urban core areas, and the lower level of accessibility settlement distribution was in the peripheral urban areas. However, other factors can also influence accessibility, such as the time threshold. The accessibility level of medical services markedly differed with the transportation mode, and the accessibility of medical services was significantly higher along the subway. The choice of off-peak travel time can effectively improve the level of medical service; (4) Due to the layout of urban expressways, the spatial distribution of medical accessibility in driving mode was consistent with that of roads, presenting a "loop level" pattern. However, the spatial distribution of accessibility under the public transport mode was affected by the urban bus microcirculation system, displaying the trait of "axial expansion." The method used in this paper provides a new scientific method for refined measurement and analysis of the accessibility of medical service facilities.

Territorial spatial planning is the spatial blueprint of high-quality social and economic development. With the rapid development of geo-information science and technology, geo-information science and tech- nology has changed the way of territorial spatial planning. Its powerful capability in data acquisition, analysis, prediction, and management provides support in data, method, and platform for territorial spatial planning, thus enabling territorial spatial planning to be more scientific, operable, and forward-looking. Based on literature review, summary, and comparative analysis, this study analyzes the technical requirements of territorial spatial planning compilation, implementation, supervision, public participation, and intelligent transformation, and systematically expounded the application of geo-information science and technology in territorial spatial planning. This study expounds the contributions of geo-information science on China's territorial spatial planning from the following three aspects: (1) Geospatial data, remote sensing data, and socio-economic big data provide data basis for territorial spatial planning; (2) Geographic Information System (GIS) analysis method, geographic simulation method, and artificial intelligence method provide method support for territorial spatial planning; (3) The application of GIS platform, cloud computing, and urban intelligent platform promotes the intelligent transformation of territorial spatial planning. This study also points out shortages of different technologies. However, there are still some problems that need to be further explored: (1) The generation of socio-economic big data and its application scenarios in territorial spatial planning are concentrated in urban space; (2) Both traditional and modern technologies in territorial spatial planning have advantages and disadvantages. These technologies need to be effectively integrated to prepare more scientific territorial spatial planning; (3) The construction of territorial spatial planning platform has not been organically combined with the construction of City Information Modeling (CIM) and other intelligent society platforms, there is a huge space for mining in the future. According to the maturity of its application in territorial spatial planning, these technologies can be divided into mature technology and promising technology. With the promulgation of territorial spatial planning at all levels and types and the initial establishment of Chinese territorial spatial planning system in 2021, attention should be paid to the application of intelligent planning methods in agricultural space and ecological space, technical system construction of intelligent territorial spatial planning, and the improvement of territorial spatial planning intellectualization.

The national land survey is a major component of evaluating national conditions and strength. Its main purpose is to master the detailed national land use status and natural resource changes. It is of great significance to cultivated land protection and sustainable social and economic development. With the development of remote sensing technology, investigating the status, quantity, and distribution of land resources has always been the focus of remote sensing applications. This article reviews the application of remote sensing in national land survey over the past four decades. Until now, remote sensing technology has shown broad prospects in national land survey. However, the remote sensing information extraction in national land survey still mainly relies on visual interpretation and is not automated enough. In recent years, the remote sensing data tend to have the characteristics of high-resolution, large-scale, multi-temporal, and multi-sensor. However, the existing automated information extraction technology does not fully integrate those characteristics, hindering the application in national land survey. This article first introduces the relevant progress in national land survey from four aspects: feature extraction using very-high-resolution images, samples acquisition from large-scale images, transfer learning in multi-temporal/multi-sensors images, and multi-source heterogeneous data fusion. Then, four challenges in the existing remote sensing information extraction technology in the national land survey are summarized: ① Image feature is the key to image classification. There are questions on how to define and select features. In addition, high-resolution images put forward higher requirements for advanced feature extraction; ② Remote sensing data in the national land survey are usually large in scale, and there are inter-class imbalance and intra-class diversity. Therefore, it is a challenge to obtain sufficient, balanced, and diverse sample sets from such complex data set; ③ Generally, the efficiency of sample collection cannot catch up with the accumulation speed of remote sensing data, thus the labeled samples are relatively small compared with the data. For multi-sensor/multi-temporal imagery, how to realize land use classification in a low-cost and timely manner is a question worth considering; ④ There is a semantic gap between land cover and land use. Since remote sensing images mainly reflect land cover information, how to properly introduce semantic information to bridge the semantic gap and realize land use classification is a problem. Finally, the future development and application of remote sensing technology in national land survey are prospected, such as transformation from visual interpretation to artificial intelligence technology, accuracy and consistency assessment of remote sensing classification products in land survey, crowdsourcing methods for large-scale land use production, and update of large-scale land use data.

Modeling urban land use change is important for future regional planning and sustainable development. Previous FLUS-based studies are mostly based on larger grid scales. How to simulate the complex land use change processes in rapidly developing cities and explore the driving mechanisms of land use change still need further exploration. This paper constructs an urban land use pattern simulation framework coupled with FLUS and Markov and innovatively introduces house price to characterize socio-economic attributes. We take Shenzhen as the study area to simulate future urban land use spatial patterns under different development scenarios based on small grid scale (30 m) land use classification data and multi-source spatial variables such as basic geography data, road and river networks, and point-of-interest data. Finally, we analyze the land use change drivers using random forest models. The results show that the coupled FLUS and Markov method proposed in this paper has higher accuracy (FoM = 0.22) and simulate the land use change processes more accurately in rapidly developing cities, compared to traditional CA models (RFA-CA and Logistic-CA). The mapping results of multi-scenario land use patterns verify the importance of ecological control lines in the process of urban development, further illustrating the reference value of the proposed simulation framework for future urban planning layout. Hospital infrastructure, entertainment venues, and bus stop, road network density have a greater impact on urban development than natural factors (e.g., elevation, slope), while the distance to coastline limits land use change processes to some extent within Shenzhen. The model constructed in this study and the fine mapping results can provide a reference basis and theoretical foundation for related research on urban regional planning and spatial pattern simulation.

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.

SexyTea, as a local milk tea brand in China, combines traditional Chinese tea culture with fashion elements and incorporates a strong Chinese style, making it a must-drink milk tea drink for tourists who visit Changsha. Exploring its spatial distribution and evaluating the suitability of its store location is of great practical significance for optimizing store layout, promoting economic development, and improving tourism service level. This article is based on the API of AMAP to crawl the SexyTea POI in Changsha City, and the spatial pattern is analyzed using the average nearest neighbor index, geographic concentration index, unbalanced index, standard deviation ellipse, kernel density estimation, and other methods. We integrate multi-source heterogeneous spatial data to select a series of factors that affect its spatial distribution and use the random forest model to evaluate the suitability of the store layout. The analysis results show that: ① The spatial distribution of SexyTea in Changsha is agglomerated as a whole (ANN=0.558, G=40.283), clustered around the city's core business clusters, forming a spatial pattern of "one super-multi-core"; ② The average test accuracy after optimization of the random forest model is 92.18%, and the OOB test accuracy is 93.45%. The evaluation results can accurately reflect the suitability and spatial distribution heterogeneity of the SexyTea store in Changsha City; ③ SexyTea location suitability results show that the suitability probability in the core business clusters of Changsha City is generally high, and there is an obvious high-value agglomeration phenomenon, which is in line with Friedman's "center-periphery" theory. If the business clusters are stratified into centers of different levels, the service functions and scope of influence provided by them will be affected by the attenuation of spatial distance, and the spatial distribution conforms to the Tobler's First Law of Geography; ④ The ranking result of feature importance shows that competitive environment, transportation location, and socio-economic development have the greatest contribution to the model. This is complementary to the minimum difference criterion emphasizing agglomeration effect and traditional commercial location strategy emphasizing location selection. Therefore, such factors can be considered when selecting store locations. The methods and conclusions of this research that integrate multi-source spatial data and use data mining technology to solve the location problem can provide reference for the location and spatial layout of SexyTea stores.

In recent years, big data has been widely applied in traffic analysis. However, they are mostly used for data visualization and phenomenon description. There is a lack of big-data oriented transport modeling, which leads to limited application of big-data in transportation planning. In this study, we propose a Location-Space Dependent Indicator (LSDI) based on the time-space interaction between transportation and land use. Based on this indicator, the urban commuting distribution model is developed, which improves the traditional gravity model. Taking Beijing as a study case, the developed model is applied and verified using mobile phone signaling big data derived from the communication service of an operator in September 2017. Travel generation and distribution models are constructed and verified respectively. Our results show that: (1) For the travel generation model simulations, commuter population and resident population show a good linear relationship. This model generates a significant prediction with a goodness of fit of 0.84; (2) For the travel distribution model simulations, a comparison analysis is conducted between gravity model, radiation model, and modified model with LSDI. The gravity model corrected by real commuting data performs best in regression analysis with a goodness of fit of 0.94. But large errors occur in the probability density distribution. The radiation model performs normal in regression analysis with a goodness of fit of 0.37. It has a better accuracy in the probability density distribution. The modified gravity model with LSDI has the best overall performance. The underestimation phenomenon is optimized in the commuter population distribution with a highest goodness of fit (0.85). Our findings provide new insights in developing big-data oriented transport prediction models and contribute to promote the application of big data in transport planning.

In order to improve the efficiency of remote sensing monitoring of crop planting and expand applications of remote sensing data, a method of crop planting area extraction based on NDVI time series difference index is proposed. With the development of remote sensing and cloud computing technologies, Google Earth Engine, as a global-scale geospatial analysis cloud platform, overcomes the disadvantages of traditional single-machine computing and brings new opportunities for rapid remote sensing classification. In this study, taking Qi County in Henan province as the study area, the NDVI time series difference index of different crops is constructed according to the characteristics of time series NDVI curve of each crop to extract crop planting information and distinguish different crop types using multi-temporal Sentinel-2 images in 2019-2020 based on the Google Earth Engine platform. The extraction accuracy is verified and compared with other existing methods. The results show that the NDVI time series difference index is based on crop phenology information and developed using GEE's high-performance computing capability, which forms a framework for rapid crop planting information extraction and has obvious advantages over traditional local computing. The winter wheat and garlic planting areas in Qi County have obvious spatial variation. The winter wheat planting areas are mainly concentrated in the northwest and southern rural residential areas of the study area. While the garlic in Qi County is mainly concentrated in the central and northeastern part of the study area due to the needs of transportation. Compared with other methods using support vector machine and maximum likelihood, the overall accuracy of crop planting area extraction using the NDVI time series difference index reaches 83.72%, and the Kappa coefficient is 0.67. The overall accuracy and the Kappa coefficient are 10.02% and 0.21 respectively higher than the maximum likelihood method, and are 4.18% and 0.09 respectively higher than the support vector machine method, which indicates that our method can extract crop planting information with high efficiency and high accuracy. We develop an efficient and accurate monitoring method for regional crop planting information extraction and expand the application of remote sensing data in the agricultural field, which has significant value for future agricultural applications.

As the most typical public facility, public toilets reflect the civilized level and management service level of the city and are an important window for building a civilized image of the city. Current research focuses on the accessibility and coverage of public toilets, treats public toilets as spatial points without discrimination, and ignores the heterogeneity of public toilets in different urban functional areas. How to establish a comprehensive and accurate public toilet space evaluation system and analyze the comprehensive service capabilities of public toilets in different regions is obviously insufficient in the current research, which is not conducive to the deployment of public toilets and the advancement of the equalization of basic public services. The emergence of multi-source data provides a new perspective for the research of urban public facilities. Therefore, this paper proposes a rationality evaluation method of public toilet spatial layout based on POI big data from the perspective of urban functional area. We use Term Frequency-inverse Document Frequency (TF-IDF) information weighting technology combined with Point of Interest (POI) frequency density to identify urban functional areas, and integrate OpenStreetMap (OSM) road network density and WorldPop population data to construct a population travel vitality index and evaluate public toilet services in urban functional areas. Finally, the population and spatial coverage rate and the spatial imbalance index are calculated to determine the difference between streets and towns and the rationality of the layout of public toilets in streets and towns. Based on multi-source data, this method quantitatively analyzes the rationality of the allocation of public toilets in different functional areas and explores the differentiating factors of the space allocation of public toilets. This article takes Shanghai, one of the most urbanized cities in China, as an example for calculation. The study finds that: ① The number of toilets in different urban functional areas is different. The number of planned commercial service functional areas is the largest, but the public toilets in the commercial service functional area have the highest qualifications. "Industry-Commercial service" and "Green Space-Commercial service" and other commercial service-related joint functional areas are also at a high level of qualification. This is because a lot of commercial service organizations provide public toilet services to the outside, which has improved the service capacity of public toilets in the area; ② The public functional area has the lowest qualification rate, only 10.27%, which is related to the openness of this type of attached public toilet facilities; ③ The eligibility of public toilets in Shanghai’s streets and towns is generally reasonable, with an average space coverage rate of 67.31% and an average population coverage rate of 70.72%. The imbalance index between public toilet service and travel vitality distribution in streets and towns ranges significantly from 0 to 0.76, of which 147 have an imbalance index less than 0.4, accounting for 69.34%, indicating the comparison of the space allocation of public toilets between these streets and towns is reasonable. The rationality of the allocation of public toilets decreases significantly from the downtown area of Shanghai to the southwest, southeast, and Chongming Island, while there is no obvious attenuation to the northwest, showing a good contiguous service capacity. The results show that this method fully takes into account the issue of the heterogeneity of the functional areas of public toilets and the travel vitality of the population, and the spatial analysis is more accurate and has more practical value.

Named Entity Recognition (NER) is the basis of many researches in natural language processing. NER can be defined as a classification task. The aim of NER is to locate named entities from unstructured texts and classify them into different predefined categories. Compared with English, Chinese have the features of flexible formation and no exact boundaries. Because of the features of Chinese and the lack of high-quality Chinese named entity datasets, the recognition of Chinese named entities is more difficult than English named entities. Fine-grained entities are subdivisions of coarse-grained entities. The recognition of Chinese fine-grained named entities especially Chinese fine-grained geographic entities is even more difficult than that of Chinese named entities. It is a great hardship for Chinese geographic entity recognition to take both accuracy and recall rate into account. Therefore, improving the performance of Chinese fine-grained geographic entities recognition is quite necessary for us. In this paper we proposed two Chinese fine-grained geographic entity recognition models. These two models are based on joint lexical enhancement. Firstly, we injected the vocabulary into the experimental models. The vocabulary was considered as the 'knowledge' in the models. Then we explored the appropriate fine-grained named entity recognition method based on vocabulary enhancement. And we found two models, BERT-FLAT and LEBERT, that were suitable for fine-grained named entity recognition. Secondly, to further improve the performance of these two models in fine-grained geographical named entities recognition, we improved the above two models with lexical enhancement function in three aspects: pre-training model, adversarial training, and stochastic weight averaging. with these improvements, we developed two joint lexical enhancement models: RoBERTa-wwm-FLAT and LE-RoBERTta-wwm. Finally, we conducted an ablation experiment using these two joint lexical enhancement models. We explored the impacts of different improvement strategies on geographic entity recognition. The experiments based on the CLUENER dataset and one microblog dataset show that, firstly, compared with the models without lexical enhancement function, the models with lexical enhancement function have better performance on fine-grained named entities recognition, and the F1-score was improved by about 10%; Secondly, with the improvements of pre-training model, adversarial training, and stochastic weight averaging, the F1-score of the fine-grained geographic entity recognition task was improved by 0.36%~2.35%; Thirdly, compared with adversarial training and stochastic weight averaging, the pre-trained model had the greatest impact on the recognition accuracy of geographic entities.

The spread of infectious diseases is usually a highly nonlinear space-time diffusion process. Epidemiological models can not only be used to predict the epidemic trend, but also be used to systematically and scientifically study the transmission mechanism of the complex processes under different hypothetical intervention scenarios, which provide crucial analytical and planning tools for public health studies and policy-making. Since host behavior is one of the critical driven factors for the dynamics of infectious diseases, it is important to effectively integrate human spatiotemporal behavior into the epidemiological models for human-hosted infectious diseases. Due to the rapid development of human mobility research and applications aided by big trajectory data, many of the epidemiological models for Coronavirus Disease 2019 (COVID-19) have already coupled human mobility. By incorporating real trajectory data such as mobile phone location data at an individual or aggregated level, researchers are working towards the direction of accurately depicting the real world, so as to improve the effectiveness of the model in guiding actual epidemic prevention and control. The epidemic trend prediction, Non-pharmaceutical Interventions (NPIs) evaluation, vaccination strategy design, and transmission driven factors have been studied by the epidemiological models coupled with human mobility, which provides scientific decision-making aid for controlling epidemic in different countries and regions. In order to systematically understand this important progress of epidemiological models, this study collected and summarized relevant literatures. First, the interactions between the COVID-19 epidemic and human mobility were analyzed, which demonstrated the necessity of integrating the complex spatiotemporal behavior, such as population-based or individual-based mobility, activity, and contact interaction, into the epidemiological models. Then, according to the modeling purpose and mechanism, the models integrated with human mobility were discussed by two types: short-term epidemic prediction models and process simulation models. Among them, based on the coupling methods of human mobility, short-term epidemic prediction models can further be divided into models coupled with first-order and second-order human mobility, while process simulation models can be divided into models coupled with population-based mobility and individual-based mobility. Finally, we concluded that epidemiological models integrating human mobility should be developed towards more complex human spatiotemporal behaviors with a fine spatial granularity. Besides, it is in urgent need to improve the model capability to better understand the disease spread processes over space and time, break through the bottleneck of the huge computational cost of fine-grained models, cooperate cutting-edge artificial intelligence approaches, and develop more universal and accessible modeling data sets and tools for general users.

Geography is a comprehensive discipline that studies the spatial-temporal pattern, evolution process, and interaction mechanism of various geographic elements. With the evolution of the real world from binary space to the ternary world, it is urgent to deepen and expand the understanding, expression, and mining of geographic information connotation. The existing geographic information expression model of "location + geometry + attributes" is difficult to support the expression of various geographic elements and their laws. From the perspective of geography, based on the concept of the ternary world, we sort out the information elements and the process of their transformation into geographical information and form an information expression system with the "seven elements" of time, place, character, object, event, phenomenon, and scene, and from the geography "seven dimensions" perspective of semantic, spatial location, geometric structure, attribute, interrelationship, evolution process, mechanism of effect to interpret. It realizes the all-around classification and description of the connotation of geographic information from the perspective of geography and provides theoretical support for the multidimensional description and computational analysis of geographic information for comprehensive and integrated research in geography.

The European Centre for Medium-Range Weather Forecasts (ECMWF) has developed ERA5, a global atmospheric reanalysis product with high spatiotemporal resolution. The Shortwave Downward Radiation (SWDN) of ERA5 is an important atmospheric forcing dataset which has important applications in regional climate assessment, agriculture, and solar energy resource utilization. In this study, the observed SWDN dataset after quality control was collected from 91 official radiation monitoring stations across mainland China in 2011-2018 and was applied to evaluate the SWDN in ERA5 on different spatial and temporal scales, together with other three reference SWDN datasets from global atmospheric reanalysis products (i.e., ERA-Interim, CFSR, and MERRA2) and the CERES satellite inversion product (SYN1deg). Results show that: ① On the monthly mean scale, the ERA5 product had the highest correlation coefficient (Corr) with the station observation data (0.939) and the lowest Root Mean Square Error (RMSE) (28.309 W/m²), compared with other reanalysis products. The average bias of ERA5 (15.4 W/m²) was slightly higher than that of the ERA-Interim product (13.2W/m²). The Corr between CERES satellite inversion product and observation data was 0.955, the RMSE was 20.042W/m², and the Bias was 5.3W/m²; ② The radiation values of all these five SWDN products were overestimated against the observation data. In general, the overall accuracy of the ERA5 product in mainland China was higher than the other reanalysis products, but was lower than the CERES satellite inversion product. The comparison of daily mean values between products also showed similar results; ③ Regional evaluation results show that the SWDN in ERA5 had a good consistency with observation data in four regions across mainland China. All five SWDN products performed poorly in the southern region. Compared to the northeastern and northern regions, the RSME and the bias of the ERA5 product and the CERES satellite inversion product relative to observations were larger in the western region.

The mining and prediction of ship behavior characteristics is an important research content of maritime intelligent transportation system and a key scientific problem in the field of transportation engineering. In order to systematically study the research status and development trend of ship behavior characteristic mining and prediction, the Vosviewer is used to generate the clustering map and trend evolution map of high-frequency keywords of research content from the perspective of bibliometrics, based on literatures collected from WOS database and CNKI database. After comprehensive analysis, three topics of data mining of maritime traffic elements based on Automatic Identification System (AIS), ship behavior clustering research and ship behavior prediction research are summarized. The research contents, methods and existing problems of each topic are systematically analyzed. The research results show that: ① In the aspect of data mining of maritime traffic elements based on AIS, the research mainly focuses on the mining of spatial features of maritime traffic and temporal features of traffic flow,and the results are lack of sufficient association mining of time features AIS data and background environment features. Further exploration needs to be made on the mining of space-time characteristics and data fusion. ②In the aspect of ship behavior clustering, the research mainly uses the unsupervised clustering method to study the clustering of ship track points and ship track segments to obtain the spatial-temporal distribution of ship navigation behavior patterns and the maneuvering intention. The similarity calculation method of ship trajectory integrating multidimensional features, identification of ship the adaptive selection of clustering parameters and the semantic modeling of ship behavior need to be further studied. ③ In the aspect of ship behavior prediction, it mainly focuses on the prediction of ship behavior based on dynamic equation, traditional intelligent algorithm and deep neural network. Considering the characteristics of randomness, diversity and coupling of ship behavior, the use of hybrid neural network model and combining neural network with vector machine. In the end, the paper proposes the promising research area which include mining of ship behavior feature based on semantic model, the prediction of ship behavior based on deep convolutional neural network, the mining of ship behavior feature based on knowledge graph and the visualization of prediction results.

Night-time economy refers to the related economic activities mainly in the services taking place in urban space and at night, which is an important representation of a city's economic development and consumption level. Currently, researchers at home and abroad mostly rest on the theoretical level, or small-scale refined research based on market research and questionnaire survey, lacking in-depth mining using models and mathematical statistics methods, and rarely intuitively show the specific temporal and spatial distribution of large-scale night-time economy. With the development of information technology, night lighting data and perception big data provide new data sources for quantitative research of night-time economy. This paper provides a new perspective for night-time economy by fusing multi-source data. Compared with the traditional survey data, it is more rapid, efficient, and extensive, which is suitable for large-scale research of night-time economy. Based on taxi OD flow, this paper uses spatial clustering algorithms such as DBSCAN and K-Means ++ to identify hot areas of night-time activities in Xiamen City from the perspective of consumers. Based on the night-time lighting image and POI, this paper analyzes the supply and demand relationship by the method of profit and loss and identifies the distribution area of night service facilities from the perspective of merchants. Then we analyze the temporal and spatial distribution pattern of night-time economy in Xiamen City. The results show that: ① The spatial distribution of night activities in Xiamen City is multi ring and decreases to the surrounding areas. The distribution of hot spots of night activities varies from place to place; ② The existing service facilities in some areas of Xiamen City fail to serve the night economy well, and the existing lighting infrastructure, such as lighting and nightscape, is insufficient; ③ There is a moderate positive correlation between residential population density and night activity density, and the results are valid. The profit and loss value and quantity of night service facilities, night lighting, and night activity density are moderately and weakly correlated, and catering facilities are more dependent on night lighting. Finally, we put forward some suggestions for Xiamen's future night-time economic construction, such as providing different night-time services according to different consumer groups and psychology, strengthening the construction of night light infrastructure and market support. The research conclusions are of positive significance to promote social employment, and enhance the utilization rate of infrastructure. At the same time, they can also provide reference for urban economic development and policy formulation.

The Qinghai-Tibet Plateau is sensitive to climate change. At present, relevant researches mostly focus on the dynamic changes of ice and snow in the Qinghai-Tibet Plateau, and seldom pay attention to the dynamic changes of the rocky desert left by the melting ice and snow. Through the earth-atmosphere interaction, rocky desert may change the regional heterogeneity of climate at a large scale. This paper sorted out the extraction methods of remote sensing monitoring of ice and snow melting and rocky desert dynamic changes in the Qinghai-Tibet Plateau, and analyzed the advantages, disadvantages and applicability of various remote sensing data and extraction methods. We also summarized the data and research methods of the dynamic monitoring of ice and snow and the dynamic changes of the rocky desert in the Qinghai-Tibet Plateau. At present, the remote sensing monitoring data of the snow and ice dynamic changes in the Qinghai-Tibet Plateau are diverse and the research methods are mature. However, the remote sensing monitoring of the rocky desert dynamic changes left by the melting ice and snow has not yet formed a systematic study. Besides, under the condition of insignificant human disturbance, the dynamic changes of the rocky desert in the ice and snow melting area can also be used as a supplement to remote sensing monitoring of ice and snow dynamic changes.

Accurately quantifying the spatiotemporal evolution of urban agglomerations is important for city management plan and urban agglomeration development strategy. In this study, the spatiotemporal evolution of the Yangtze River Delta (YRD) urban agglomeration was characterized based on the DMSP/OLS nighttime light (NTL) data from 1992 to 2012 and the NPP/VIIRS NTL data from 2012 to 2018. Considering that the discrepancy between the NTL data from different satellites or sensors and the oversaturation of DMSP/OLS NTL data in urban areas limit the applications of integrating NPP/VIIRS and DMSP/OLS NTL data in monitoring the urban expansion dynamics, discrepancy correction and saturation correction were conducted to produce a temporally consistent NTL dataset combining the two NTL datasets during 1992—2018. Using the city-level built-up data obtained from the statistical yearbook as the reference, the optimal threshold values were determined by a dichotomy method to extract annual urban build-up areas in the YRD urban agglomeration from the long-term NTL dataset. Based on the extracted annual urban build-up areas, the expansion rate, centroid (center of gravity), directional distribution, and city-size distribution of the YRD urban agglomeration were analyzed using the standard deviation ellipsoid method and the Zipf coefficient. Our results show that: (1) The discrepancy correction and saturation correction procedures employed in this study effectively improved the continuity and comparability of multi-source NTL data with less reference data. We produced a temporally consistent nighttime light dataset during the period of 1982—2018; (2) The annual build-up areas in the YRD urban agglomeration extracted by the dichotomy method achieved a good accuracy, with a mean relative error of 8.10% and a mean absolute error of 6.85 km²; (3) The city centroid of the YRD urban agglomeration was located along the Taihu Lake in Suzhou city and showed a trend of slowly moving southeast from 1982 to 2018. The YRD urban agglomeration was distributed along northwest-southeast direction, and the direction gradually shifted to the north-south then. The oblateness of weighted standard deviation ellipse gradually decreased, indicating a decrease of the directional distribution of the YRD urban agglomeration over time. This trend also suggested that the development of cities in this urban agglomeration had become more balanced in past two decades; (4) The Zipf index of the YRD urban agglomeration was close to 1 and slowly decreased, suggesting a relatively balanced pattern of the city-size distribution of this urban agglomeration.

Through various exploration and practice of poverty alleviation, China has embarked on a path of poverty alleviation with Chinese characteristics, which has greatly reduced the number of rural poor people and significantly improved the living standard in poverty-stricken areas. For a long time, the monitoring of socioeconomic and environmental conditions in poverty-stricken areas is based on all kinds of statistical data, reports, paper files, etc., based on administrative units, lacking effective and accurate spatial location information. With the rapid development of geo-information science such as Remote Sensing (RS) and Geographic Information System (GIS), the real-time and efficient capture and calculation ability of spatial information greatly improves the efficiency and decision support level of poverty alleviation. This paper expounds the contributions of geo-information science on China's poverty alleviation from the following aspects:① monitoring and evaluation of natural resources and environment in poverty-stricken areas based on multi-source geospatial data; ② monitoring, early warning, and management of natural disasters in poverty-stricken areas; ③ analysis of poverty causing factors and poverty prediction; ④ decision support system for targeted poverty alleviation based on the mechanism of targeted poverty alleviation. China aims to eradicate absolute poverty in 2020, so the application of geo-information science in poverty alleviation will mainly focus on the establishment of monitoring and assistance mechanism to prevent poverty returning and alleviate the relative poverty. Moreover, under the background of rural revitalization, using geo-information science and technology to promote rural infrastructure information construction will be the focus of the next step.

The Sky View Factor (SVF) is one of the most important indicators to characterize urban radiation fluxes and urban thermal environment. Therefore, it is a key morphological parameter to study the Urban Heat Island (UHI) effect. Studies have shown that SVF has a strong relationship with UHI intensity. Nevertheless, the relationships found can be contradictory. This is primarily due to the fact that the cases studied are often in different regions with different climatic conditions. In addition, the influences of trees are sometimes ignored due to the lack of vegetation data or the limitation of calculating methods. How to calculate SVF quickly and accurately is important to urban climate research. SVF is typically calculated by four types of methods: fisheye photo methods, 3D GIS methods, GPS methods, and street view image methods. Compared with the other types of methods, calculating SVF using street view images has many advantages, such as widely available data, low cost, high efficiency, and the ability to consider the influences of trees and other obstacles. On the one hand, street view images provide the possibility for fast and accurate calculation of SVF in large-scale areas. On the other hand, the street view image method is still at its developing stage and more work needs to be done to verify its application in various urban environments. In this study, we proposed an automatic SVF calculation method using street view images and deep learning algorithms, and then applied the method to the UHI study in the city center of Shanghai. Baidu static panoramas and Deeplabv3+ were used to detect sky range while MATLAB code was written to calculate SVF. A Landsat-8 OLI / TIRS image was also used to retrieve land surface temperature at street level in the study area. Based on the Local Climate Zones (LCZ) scheme, we combined large-scale SVF value with the land use and building morphology to examine the relationship between SVF and UHI intensity. The results showed that Deeplabv3+ can detect the sky and non-sky range effectively in different scenarios (MIOU=91.64%). The SVF calculated using the proposed method was in good agreement with that calculated using fish-eye photos (R²=0.8869). The LCZ scheme provides new insights for the relationship between SVF and UHI. For LCZ5 and LCZ1, the highest correlation coefficients were 0.68 and -0.79, respectively. The proposed method was shown to be applicable in high-density and complex urban environments. In addition, the calculation of large-scale continuous SVF provides the possibility for zonal understandings of the UHI effect based on the LCZ scheme.

The formation mechanism of landslide disasters is complicated and there are many influencing factors. It is imperative to explore a low-cost and highly applicable method to manage and prevent landslide disasters. As a hot spot in the current artificial intelligence field, deep learning can better simulate the formation of landslide disasters and accurately predict potential slopes. Thus, to explore the application potential of deep learning, this paper constructs one-dimensional, two-dimensional, and three-dimensional forms of landslide data, and then introduces three Convolutional Neural Networks (CNN)-based landslide susceptibility analysis frameworks, including CNN-based classifiers, integrated models, and ensemble models. The proposed deep learning methods were applied to Yanshan County, Jiangxi Province for experiments. 16 landslide influencing factors were first selected for modelling based on the geomorphological, hydrological, and geological environment conditions of the study area. These factors include altitude, aspect, distance to faults, land use, lithology, normalized difference vegetation index, plan curvature, profile curvature, rainfall, distance to rivers, distance to roads, slope, soil, stream power index, sediment transport index, and topographic wetness index. Then, the multi-collinearity analysis and relief-F algorithm were used to analyze and screen the influencing factors. All CNN-based methods were constructed and validated based on several statistical measures of accuracy, root mean square error, mean absolute error, sensitivity, specificity, and the receiver operation characteristic curve. Finally, the susceptibility value of each pixel in the study area was predicted based on the CNN-based methods, and the entire study areas were reclassified into five susceptibility categories: very low, low, moderate, high, and very high. The factor analysis results show that the plan curvature, profile curvature, stream power index, and sediment transport index are redundant factors and should be removed from further modelling process. The model evaluation results demonstrate that all CNN-based models can obtain accurate and reliable landslide susceptibility mapping results. The two-dimensional CNN model achieved the highest prediction accuracy of 78.95% among single CNN models. Moreover, the performance of logistic regression was effectively improved by combining the two-dimensional CNN for feature extraction, with an accuracy improvement of 7.9%. Besides, the heterogeneous ensemble strategy can greatly improve landslide prediction accuracy when using CNN classifiers, with an accuracy improvement between 4.35% and 8.78%. Generally, the CNN has been proven to have huge application potential in landslide susceptibility analysis and can be implemented in other landslide-prone areas with similar geo-environmental conditions.

For the current territory development planning in China, the Ministry of Natural Resources has put forward a method to evaluate the accessibility of urban centers based on isochrone maps. The use of dynamic traffic data in isochrone maps studies is becoming more and more recurrent, but comparative analyses between dynamic and static data are still rare. In this paper, Nanchang city is taken as a case study to generate the urban center isochrone maps using static and dynamic traffic data. The city is divided into 500 m×500 m grids, with each grid center point representing a given destination while Bayi Square and Greenland Central Square are set as origins. Using the above origins and destinations, the dynamic data were obtained daily from the Baidu open map platform at 15:00 and at 18:00 over nine days-time (Saturday-next Sunday). Subsequently, the confusion matrix and Kappa coefficient are used to test the consistency between the isochrone maps generated by the two datasets. The results suggest that most of Nanchang urban central areas are within a 60 min-circle and most of Nanchang's urban areas are within a 120 min-circle, when taking Bayi Square or Greenland Central Square as the origin. The isochrone maps generated by the static data has just a fair consistency with those generated by the dynamic data at evening peak time on workdays. Within the urban central areas, the isochrone maps generated by the static data have reached a substantial consistency with those generated by the dynamic data at off-peak time on workdays, indicating that the static data is more suitable for evaluating the urban center accessibility at off-peak time on workdays. Besides, the dynamic data can display the temporal characteristics of the isochrone maps. The isochrone maps of the dynamic data at 4 time-points show that the urban center accessibility at 15:00 on workdays is significantly better than others. But the proportions of isochrone surfaces to the total urban areas are found to increase with the drivetime, and their growth curves are in accordance with the trend of the Logistic curve. The key time nodes of each growth curve can provide more targeted division thresholds for isochrone maps. This research highlights the accuracy of the isochrone maps generated by the dynamic data and explores the applicability of the static data. The research also shows that using the key time nodes of the Logistic curve contributes to a more reasonable subdivision of the isochrone map.

Under the background of territorial spatial planning in the new period, delimiting the urban development boundary scientifically and reasonably and establishing a sound territorial space use control system are important measures to guide all kinds of territorial space development and protection. Taking Fuzhou City as an example, this paper constructs a global multi-dimensional territorial space control system. Management and control constraints are embedded in the future land use pattern simulation. At the same time, considering the regional spatial heterogeneity and spatial-temporal dependence, this paper designs the Spatial-temporal Cellular Automata (ST-CA) model which integrates geographical partition strategy, deep learning technology, and the functional module of FLUS model to delimit the urban development boundary. Based on the existing achievements, this study integrates three zones and three lines to carry out the application research of spatial management and control under the thinking of "combination of planning and control". The results show that: (1) The ST-CA model considering regional spatial heterogeneity and spatial-temporal dependence can effectively improve the accuracy of land use change simulation and achieve a more realistic and accurate geographical simulation process. The overall accuracy of the model increased from 95.95% to 98.34%; (2) Control constraints are embedded in the process of geographical simulation, which can guide the rational layout and controllable scale of urban, agricultural, and ecological spaces. Delimitation of urban development boundary based on simulation results can effectively avoid occupation on protected land; (3) The future simulation results combined with the control early warning value show that the urban expansion situation in the main urban area and surrounding districts and counties of Fuzhou City is relatively severe. In the future, it is urgent to reasonably regulate the territorial space pattern of Fuzhou City; (4) The characteristics of boundary change trend show that the delimitation results are consistent with the long-term development planning of Fuzhou City, which is in line with regional development demands. The territorial space pattern presents a multi-axis development trend. The research results can provide scientific planning for the development and protection of territorial space and practical reference for territorial space control and optimization in Fuzhou City.

As a new product of the Internet era, migration flowed is the basic carrier of information flow, capital flow, traffic flow and other flow space. It can objectively reflect the geographical behavior relationship between cities, and it is of great significance to depict the urban network structure. Based on the big data of Baidu migration in cities above prefecture level, this paper attempts to explore and study the characteristics of urban network structure in China from the perspective of full time and net migration, and extracts the hierarchy, association and influencing factors of urban network. The results show that: the national urban network presents a stable and hierarchical pyramid and four vertex "diamond" structure, which is consistent with the spatial distribution of economic scale of major urban agglomerations; the regional network shows the core periphery radial structure of agglomeration to high-level administrative centers. The typical small world characteristics with provincial capital cities as the core are relatively prominent, and the accessibility and connectivity of small world network are high. As far as cities are concerned, Zhoukou, Fuyang, Ganzhou, Shangrao and Chongqing are the main export areas of population resources, while Shenzhen, Dongguan, Guangzhou, Beijing and Shanghai have become the main gathering places of migrant population, and the corresponding population transportation network has been formed. Administrative status, economic scale, transportation hub construction, population resources and other factors all play a decisive role in the control and influence of cities in the urban network. Finally, combined with the characteristics of China's urban network structure and its main influencing factors, the paper puts forward relevant policy suggestions, in order to provide reference for the balanced development and construction of China's urban network structure.

Location description is the natural language expression of human spatial cognition. Since natural language is the primary and basic means of information transmission in human society, location description is an important medium for transmitting spatial location information in human communication. Spatial positioning based on spatial location description is the key to intelligent transformation of location-based services in the era of big data. To solve the problem that the vagueness of location description in different contexts is significantly different and results in difficulty in positioning, this paper proposes a representation method and reasoning mechanism for vague location description. Firstly, by combing the law of human spatial cognition, the types of elements concerned in the description of natural language are clarified. Based on the analysis of the sources of vagueness, a formal representation of vague location description is constructed. Different from the traditional spatial information modeling which focuses on spatial relationship, the formal representation proposed in this paper establishes the vagueness relation and influence among different information factors by the strategy of multi-factors representation. The formal representation also enhances the semantic analysis ability for the vagueness of location description. Secondly, based on supervaluation theory, the reasoning mechanism of vague location description is proposed from three aspects: spatial object, distance relation, and direction relation. Considering the context semantics of spatial location description, the threshold of observation value is used to carry out spatial reasoning. By being super-valued to different contexts, the reasoning results in different situations are obtained. The aim of the reasoning mechanism is to establish the mapping relationship between vague location description and real spatial location. Thirdly, a Question-Answering (Q&A) system is designed to collect contexts of location description, and a case study on the method is conducted. In the case study, a group of users' viewpoints from Q&A on spatial cognition are transformed into the spatial scope in the real world. These spatial scopes can establish the relationship between qualitative spatial concepts and quantitative spatial data, so as to realize the representation of vague location description in GIS. The results show that the proposed method in this paper can adjust the granularity of formal representation of location description in time according to actual application scenarios, and the spatial reasoning results fit intuitive cognition. In the future, knowledge graphs will be introduced to further improve the semantic reasoning ability and positioning accuracy for vague location description.

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.