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.

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.

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.

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.

In recent years, with the continuous development and rapid iteration of emerging technologies such as mobile communication, big data, the Internet of Things (IoT), Artificial Intelligence (AI), digital twins, and autonomous driving, new smart cities have become a significant frontier in the field of Geographic Information Systems (GIS) applications. Digital twin cities represent a complex integrated technological system that underpins the development of next-generation smart cities. Intelligent, holistic mapping for digital twin cities relies on comprehensive urban sensing, and the interactive control of urban sensing facilities plays a pivotal role in achieving the seamless integration of the physical and digital aspects of digital twin cities, fostering the convergence of entities within the urban environment. Describing spatiotemporal entities of the real world through a spatiotemporal data model, as well as modeling the behavioral capabilities of these entities using spatiotemporal object behavior, represents not only an innovative extension of GIS spatiotemporal data models but also addresses the practical requirements of triadic fusion and interactive analysis of human, machine, and object components with the development of digital twin city. As a crucial facet of urban infrastructure, urban sensing facilities epitomize distinctive spatiotemporal entities. Current research into the interactive control of these facilities is predominantly concentrated within the domains of the IoT, Virtual Reality/Augmented Reality (VR/AR), and GIS. However, these domains often lack research pertaining to interactive control of urban sensing facilities within the GIS-based digital realm. To tackle these issues, a viable approach involves mapping the direct physical control processes of humans over objects in the Internet of Things domain to the realm of GIS. Specifically, this involves using a GIS spatiotemporal data model to abstractly represent urban sensing facilities in the real world as spatiotemporal entities. These entities are then expressed as spatiotemporal objects within a spatial information system. Subsequently, the changes or actions of these facility spatiotemporal entities are uniformly abstracted as the behavioral capabilities of these spatiotemporal facility objects. Ultimately, the interaction control of these sensing facilities by humans is transformed into a process where humans invoke the behavioral capabilities of facility spatiotemporal objects, resulting in specific outcomes. Based on the aforementioned idea, this study employs a multi-granular spatiotemporal object data model to construct behavior capabilities for urban sensing facilities. Building upon this foundation, a spatiotemporal object behavior-driven approach for interactive control of urban sensing facilities with virtual-reality integration is introduced. By constructing a "quintuple" model for interactive control of facility objects, this approach facilitates users in engaging in interactive control through a reciprocal linkage between virtual scenarios and physical facilities. This mechanism effectively translates the process of urban sensing facility interaction control based on direct communication commands into the digital world, providing theoretical and technical support for the intelligent and interactive analytical applications of sensing facilities within digital twin cities. Experimental results substantiate the effectiveness and feasibility of the proposed method for interactive control of urban sensing facilities.

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.

Knowledge graphs are an important data infrastructure in AI technologies and applications, and have become a hot research topic in geosciences. The size and topological features in geographic knowledge graphs are usually different from universal knowledge graphs, which are not typical small-world networks. However, existing studies often use the default network search depth when learning geographic knowledge graph representations, and its rationality needs further demonstration. For this purpose, this paper constructs a metro travel knowledge graph based on the topological structure features of metro line network, combined with passenger flow data, POI (Point of Interest) data and built environment data, etc.; then GraphSAGE model is used to learn node multidimensional feature embedding and combine POI data for semantic recognition of station classification results to verify the suitable network search depth for metro travel knowledge graph. The results showed that, compared to the default 2 layers search depth, the node embedding features of this metro travel knowledge graph work optimally when the search depth is 3 layers. This study shows that the hyperparameter selection of the geographic knowledge graph representation is supposed to take into account the geographic features, and it is important to avoid the use of results from fields such as computer science that have not been distinguished. When the search depth is 3 layers, the metro station classification results are also more reasonable and explanatory, which can provide a basis for station planning and passenger flow prediction using knowledge graph and AI methods.

Harbor detection is the top priority of maritime ship supervision, and the ship activity information acquired by Automatic Identification System (AIS) can provide high temporal and spatial accuracy of ship activity information for harbor detection. In order to explore the application of AIS data in harbor detection, a harbor detection method based on multi-source data and semantic modeling of ship stop trajectory is proposed. Firstly, the semantic model of ship stop trajectory is constructed through data mining and semantic information enhancement to identify ship stop trajectory in the harbor area. Secondly, a classification model based on random forest is established to classify ship berthing trajectories and ship anchoring trajectories, and then harbor berths and anchorages are extracted by using spatial step-by-step merging method. Finally, the data of ship berthing trajectories, roads, coastline, bathymetry, and land use and land cover data are integrated to identify harbor objects considering situational-domain knowledge. Based on over 83 million AIS trajectory records of 96,790 ships in 2017, the proposed method is applied to detect harbor object in the South China Sea study area. The experimental results show that the overall classification accuracy of ship stop behavior is 0.9477 and the Kappa coefficient is 0.8948. 447 harbor areas in the South China Sea study area are extracted, and the overlay verification results with Google Earth images show that the extraction results are all located within the real harbor images. In addition, compared with the 24 harbor locations in the South China Sea region contained in the Natural Earth dataset, the integrity of the extraction results is greatly enhanced. Therefore, the harbor detection method based on multi-source data and semantic modeling of ship stop trajectory has high accuracy and completeness for harbor detection. Meanwhile, the harbor areas extracted by this method can provide target areas for harbor identification based on remote sensing images, thus improving the efficiency of dynamic identification of harbor object in a large region or even globally.

This study aims to explore the complex spatiotemporal patterns of bicycle-sharing trips, reveal the influence of urban factors on the OD of bicycle-sharing trips, and improve the accuracy of OD prediction. Combining the theory of urban computing, urban factors such as the epidemic, months, weather conditions (minimum temperature, maximum temperature, and wind speed), and whether it is a weekday along with the length information of non-motorized lanes are selected to construct a bicycle-sharing demand prediction model (USTARN) that integrates urban computing and spatiotemporal attention residual network. USTARN first captures the spatiotemporal dependence of sharing bicycle flow through spatial area division and time series slicing, then combines the attention mechanism for deep residual learning, and finally adjusts the deep residual prediction results according to the urban factor prediction results to improve the model performance. Using the big data from bicycle orders and urban factor datasets in Shenzhen obtained from the government data open platform, this study visualizes the spatiotemporal distribution patterns of bicycle-sharing trips and analyzes their influencing factors using the Python development environment. The OD data set is divided into training set, verification set, and test set in a 7: 1:2 ratio, and the model training, model parameter adaptive adjustment, and model result comparison are carried out, respectively. The results show that the average error of the USTARN model for OD prediction of bike-sharing trips is 7.68%, which is 5.93%, 7.55%, and 6.07% lower than that of the STARN model without urban computing and the traditional CNN model, which is good at data feature extraction, and the BiLSTM model, which is good at dealing with bi-directional time-series data, respectively. The USTARN model fully reflects the influence of time, space, epidemic, weather, and other factors on the OD of bike-sharing trips. Our results have theoretical guiding significance for the accurate prediction of bike-sharing trip OD, which can provide a scientific basis for urban non-motorized roadway planning and have practical application value for the promotion of bike-sharing travel mode and solving the 'last mile' problem of residents travel.

How to use a small number of topographic features to restore the topography has been a difficult problem in the field of geology. In this paper, we extract topographic features from open source datasets, and construct Conditional Generative Adversarial Networks (CGAN) for DEM generation using topographic features as constraints, a comparative experiment was designed based on the combination of open-source DEM, open-source DEM and remote sensing image, as well as the generation of DEM by extracting topographic features from the high-precision DEM with a resolution of 5 m, the results were compared and evaluated by visual effect, correlation analysis and topographic factors. The results show that: (1) in the visual effect, the DEM generated by three different methods are very close to the original DEM with a resolution of 5m, which is much better than the traditional interpolation method, (2) the correlation between DEM generated by three different methods and the original DEM with a resolution of 5m is more than 0.75, and the result of reconstruction based on dem with a resolution of 5 m extracted from open source and remote sensing image with a resolution of 1m is closest to that of the original DEM with a resolution of 5m, the correlation between DEM and original 5m DEM can reach more than 0.85. (3) in the aspect of terrain factor, based on dem with a resolution of 5 m and remote sensing image with a resolution of 1m, the distribution trend of slope and aspect of reconstructed DEM is most consistent with the original DEM with a resolution of 5 m. This paper provides a new idea for high-precision DEM modeling. In the areas where high-precision DEM is difficult to obtain, high-precision terrain modeling can be carried out by using open source data sets and Conditional Generative Adversarial Networks, so as to conduct geoscience analysis and geographical simulation.

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.

Web texts are an important data source for constructing and completing a large-scale knowledge graph that contains a great deal of ubiquitous geographic information. However, the extensive sources, casual expression, and dynamic nature of web texts, as well as the varied quality of implicit geo-information bring great challenges such as multi-level evaluation objects, unclear quality dimensions, diversified evaluation indicators, difficult access to deep-seated indicators, and diversified evaluation methods in the process of geographic information quality assessment. Therefore, a Quality Assessment Framework for implicit Geographic Information from Web Texts (QAF-GIWT) is proposed in this study. The QAF-GIWT is oriented to the process of acquiring geographic information from web texts and defines three levels of quality evaluation objects, i.e., data source level, data item level, and dataset level. The data source level contains websites and web pages, the data item level includes the triplet-formed information extracted from the webpage, and the dataset level is the information aggregated into a Geographic Knowledge Graph (GeoKG). The QAF-GIWT defines four quality dimensions including relevance, novelty, reliability, and integrity, and proposes the corresponding quantitative evaluation indicators for different level evaluation objects including Cell Geographic Semantic Ratio (CGSR), Geographic Semantic Ratio (GSR), Average Geographic Information Ratio (AGIR), Geographic Information Ratio(GIR), Event Time Length, Triplet Existence, Publish Time, Time Validation, Domain Name Time Length, Update Frequency, Average Freshness, Comprehensive Ranking, Category Ranking, Daily Page Visit, Daily User Visit, User Attention, Picture Number, Word Number, Geographic Entities Ratio (GER), Window's Geo-Information Ratio (GIWR), Triplet Missing Rate, Event Information Missing Rate, Relation Missing Rate, Attribute Missing Rate, Location Missing Rate, Relation Redundancy, Attribute Redundancy, etc. It systematically summarizes the characteristics and applicability of the indicator calculation, indicator synthesis, and quality prediction methods involved in the quality evaluation process. Among them, with the help of natural language processing technology and corresponding quality indicator calculation methods, quality indicators are newly constructed from the deep mining of the web texts including CGSR, GSR, AVGIR, GIR, GIWR, GER, etc. In our experiment, the QAF-GIWT framework was designed to adapt to the characteristics of various types of websites e.g., Mafengwo. Aiming at the comprehensive evaluation of multi-level quality indicators, the analytic hierarchy process was used for comprehensive reliability evaluation. Our experiment verified the effectiveness of the QAF-GIWT framework. The QAF-GIWT provides a systematic scheme including quality dimensions, quality indicators, and quality assessment methods for the quality evaluation of geographic information extracted from massive, heterogeneous, and dynamic web texts. The proposed QAF-GIWT can assist in the screening of data sources and filtering of acquired information, greatly reducing the complexity of information acquisition and the redundancy of data storage, and assisting the quality control process of the acquisition of geographic information from web texts.

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.

At present, China government and bike-sharing companies mostly use electronic fence parking stations to manage the shared bicycles normatively. Electric fence parking stations for free-floating bike-sharing are predetermined 'virtual fences' to guide users to park bikes in designated zones and regulate inappropriate parking behaviors. However, due to the randomness and uncertainty of the inflow and outflow of bicycles at a single parking station, the scheduling of bicycles based on an independent parking station is hard to realize. Therefore, it is necessary to group fence stations into clusters and implement regional management. In this paper, we proposed a network clustering algorithm based on spatiotemporal constraints, which comprehensively considered spatial factors (location and geographical environment of the parking stations) and temporal factors (historical bike-sharing system orders) as the clustering partition basis, and this algorithm can realize the multi-scale groups division of parking stations only by setting a distance threshold. We chose Xiamen Island as the research region. Using the distance thresholds of 3000 m and 700 m respectively, we carried out clustering experiments on the electronic fence parking stations in the whole Xiamen Island and its Wushipu block. The results showed that this algorithm can not only gather the parking stations with similar temporal and spatial characteristics into the same group, but also make the shared bike flow mainly concentrated in the streets within each group, which is convenient for regional management. Then, we mined the characteristics of shared bikes among the partitioned groups, which can effectively identify and locate hot areas for shared bikes. The results showed that subway stations, office buildings, parks, hospitals, shopping malls, and residential areas had a greater impact on the usage pattern of shared bikes. In particular, it is necessary to focus on the accumulation of shared bikes near office buildings, shopping malls, hospitals, and subway stations, and the shortage of bicycles near the residential areas, parks, and factories during the morning rush hours. Finally, we used the Long Short Time Memory network (LSTM) to predict the orders of shared bikes. The results showed that 84% of the groups had a prediction accuracy of more than 85%, and the average of the overall prediction accuracy was 91.301%, which can meet the needs of bike-sharing system scheduling. Our research provides scientific suggestions for relevant departments to arrange electronic fence parking stations, and the LSTM model has high accuracy in predicting bicycle flow, which is effective in reducing the scheduling cost of bike-sharing system and improve the management efficiency.

The geographically and temporally weighted regression method based on weighted least squares estimation achieves optimal estimates under the assumption of Gauss-Markov independent identical distributions. However, these conditions cannot be always satisfied. If there are outliers or heavy-tailed distributions in the data, the least squares estimates may be significantly biased. On the other hand, quantile regression is less affected by outliers and is more robust than least squares regression, which can be applied in a broader range of applications under more relaxed conditions. More importantly, the least squares regression model only focuses on the mean of the response, while quantile regression explores the global distribution of the response variable (e.g., quantiles of the response variable) and can obtain richer information. In this paper, we propose the geographically and temporally weighted quantile regression model based on the local polynomial estimation. This model allows for different optimal bandwidths for different explanatory variables and use a two-step estimation method to obtain the estimates of the coefficients. To illustrate the superiority of the proposed method, we compare the proposed method with the geographically and temporally weighted least squares regression through numerical simulations. The simulation results show that the mean square error and the mean absolute error of the coefficient estimates for the proposed quantile regression model are both smaller than those of the least squares regression model. For example, at the 0.75 quantile, the mean square error and mean absolute error of the coefficient estimates based on the least squares regression are 10 times and 4 times those based on the quantile regression, respectively. This indicates that our proposed method is robust and can explore the global distribution of the response variable compared to the least squares regression model. Finally, to illustrate the practical ability of the method, we apply it to the data of Shanghai's commercial residential neighborhoods from 2017 to 2021 to investigate the effects of different factors on residential prices at different quantiles (e.g., high house prices, medium house prices, and low house prices). The results show that the explanatory variables have different effects on house prices at different quantiles. The spatial and temporal distributions of the coefficients of the variables differ significantly among high house prices, medium house prices, and low house prices, and the optimal bandwidths for different explanatory variables also differ. Compared to the MGTWR based on least squares regression, the quantile regression model proposed in this paper is more robust with the presence of outliers. After removing 1% of extreme values, the change in the mean absolute error of the fitting based on the quantile regression model is 1% smaller than that based on the least squares regression model. Additionally, the quantile regression model can explore the factors affecting the different price levels of the housing such as the high house prices, medium house prices, and low house prices.

Triple Collocation (TC) is a technique for assessing the uncertainties of three samples individually without knowledge of the true values. This method is based on the assumptions of linearity, orthogonality, and zero cross-correlation. In practical use, these three assumptions are often difficult to achieve, particularly the orthogonality and zero cross-correlation assumptions, which often encounter significant violations. Moreover, we are uncertain about the impact of these assumption violations on the errors of the method's results. In this study, we simulated multiple sets of synthetic samples with varying degrees of two assumption violations to investigate the impact of assumption violations on the accuracy of the TC method. The results of synthetic samples experiment indicate that, in general, when there is an increase in the violation of orthogonality or zero cross-correlation assumptions, the error of the method's results increases linearly or quadratically. However, under certain specific conditions of assumption violation, there is a sudden and spike-like increase in the error of TC method results. This phenomenon is referred to as "outliers". To understand the origin of the outliers, we derived the complete mathematical relationship between the violation of assumptions and the errors of the results. This relationship exhibits a fractional structure rather than a linear one, contributing to the emergence of outliers. From the perspective of the difference notation, this fractional structure results from rescaling coefficients. Continuing to analyze this mathematical relationship, we can draw two conclusions. Firstly, merely ensuring the approximate independence of the three samples does not necessarily lead to improved method results. When the structural relationships among the three samples meet certain conditions, outliers emerge. Additionally, previous attempts at method improvement have aimed at overall reducing the sensitivity of this method to assumptions, neglecting the presence of outliers. Considering these factors, the key to suppressing outliers lies in better designing these rescaling coefficients. The paper presents two possible improvement methods:(1) Ignoring the additive bias, so that the rescaling coefficients are not affected by the orthogonality or zero cross-correlation assumptions. (2) Limiting the upper and lower bounds of the rescaling coefficients. We achieved favorable results in suppressing outliers by constraining the absolute values of the rescaling coefficients between 0.25 and 4. Both improvement methods can suppress the occurrence of outliers. However, when the additive bias is significant, the first improvement method generates substantial extreme errors due to its inherent structure, which is insufficient to eliminate outliers. The second method performs effectively even in complex scenarios. Lastly, we conducted a simple estimation of the probability of outliers occurring in practical usage, which was approximately 3.2%. In addition, we used SMOS, SMAP, and AMSR2 soil moisture data to validate the phenomenon of outliers and compared the two improved methods. According to real data, some outliers appear as negative values and are removed because the calculated results cannot be negative. Therefore, A portion of the outlier does not cause a significant deviation in the calculation result; instead, they simply prevent the calculation of meaningful results. Therefore, when employing the TC method with fewer repetitions for calculations (e.g., with fewer than 500 repetitions), the influence of outliers can be disregarded.

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.

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.

The Yellow River Basin serves as an ecological barrier in the eastern plain of China. Analyzing the spatiotemporal change of vegetation cover in Yellow River Basin and its topographic effects is helpful for ecological environment management. In this study, we first calculated the annual Fractional Vegetation Cover (FVC) of the Yellow River Basin for 1990—2020 through the GEE cloud computing platform using pixel binary model and Landsat images. Then, the spatiotemporal trend of FVC was obtained through Theil-Sen Median trend analysis and Mann-Kendall test. Finally, the topographic effects on FVC was quantified based on Digital Elevation Model (DEM) data (i.e., SRTM Plus) through ArcGIS. The results show that: (1) the FVC in the Yellow River Basin presented a spatial distribution of low in the northwest and high in the southeast. Low-level FVC values accounted for 45% of the entire basin area, which were mainly concentrated in the arid and semi-arid areas in the northwest; (2) the vegetation coverage in the middle of the basin was improved significantly, which accounted for 57.07% of the entire region. The degradation trend of the northwest and west region was stronger than that in other regions of the Yellow River Basin; (3) the vegetation coverage was significantly affected by the topography. High-level FVC occurred in regions where the slope was greater than 40° and the elevation was between -31~637 m. The vegetation recovery was good within the range of slope of 8~18° and elevation of 1852~2414 m. The results can provide scientific support for the ecological environment protection and high-quality development of the Yellow River Basin.

Dockless sharing bicycles are one of the most effective options for connecting to the subway. However, the uneven spatial-temporal distribution of sharing bicycles has caused great inconvenience to users and managers, especially during the morning peak period, which will greatly reduce the operating efficiency of a transportation system. Therefore, studying the characteristics of spatial-temporal distribution of dockless sharing bicycles used to connect to the subway has certain significance for improving the commuting efficiency during the morning peak period. In order to understand the spatial-temporal characteristics of feeder metro riding, this paper takes Xiamen city as the experimental area, takes the riding of feeder metro stations during the morning peak as the main research object, proposes a new method to establish the attraction area of metro stations based on travel OD, and proposes a bicycle clustering method considering metro stations based on travel characteristics. This article also analyzes the overall travel balance of each subway station during the morning rush hour from the perspective of mathematical statistics, tide ratio statistics, and the point of attraction area, and analyzes the spatial-temporal balance of cycling around subway stations at different times during the morning rush hour. Through analysis, the similarities and differences of the balance of each subway station under three perspectives are obtained. The results show that: ①According to the characteristics of the tide ratio, the connection function of the subway station for cycling can be divided into 4 categories: the start type, balanced type, arrival type, and not suitable for connecting to the subway type, reflecting the overall connection characteristics of each subway station; ②The attraction area of the subway station connecting to the riding is different from the characteristics of the tide ratio, and its main influencing factors are the geographic location of the subway station and the surrounding land use type; ③ For the analysis results of the spatial-temporal balance, the tide ratio has no significant impact on the spatial-temporal balance level, and the major influencing factor is the surrounding land use type. The analysis results can reflect the difference in the operation of sharing bicycles that connect to the surrounding subway stations during the morning rush hours in Xiamen and the efficiency of connecting to the subway, so as to support the scheduling and supervision of key areas of bicycle sharing companies.

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 design and compilation of comprehensive maritime atlas integrating sea and land information serve the national development initiative of "building a marine community with shared future", it is also an important thrust to promote the culture fusion and friendly cooperation between marine and land areas. Therefore, it has attracted widespread attention in the field of cartography. This paper firstly discusses the special characteristics of marine-land integrated atlas through the comparative analysis with nautical charts and land atlas, referring to the thematic topic, map scale, map projection, and geographic subdivision. Then it proposes a top-level design of fundamental geographic framework for the comprehensive maritime atlas from the perspective of marine and land combination, including both the content system and construction strategy. Next, taking "Maritime Atlas of the World" as an instance, the paper puts forward the specific establishment of fundamental geographic framework in details: (1) the coordinate system of WGS84 should be used for medium and small scale maps, while the CGCS2000 should be used for large scale maps; (2) according to the map thematic and content, cartographic area, and deformation needs, mapping units can use various projections such as qual difference latitude parallel polyconic projection, Mercator projection, Goode projection, and so on; (3) six types of geographic base maps are adopted, i.e. typical reginal map, land map, sea map, navigation area map, and port map, their contents are generated in series by further selection and simplification; (4) all the mapping units should be arranged to the north, and map layouts are various with flexible geographic subdivision and map subdivision. The “Maritime Atlas of the world” complication practice shows that this proposed fundamental geographic framework can well support the integration of marine and land information into a cohesive coordinative manner.

The most direct and effective way to distinguish geographical entities is to delineate their boundaries. At present, the delineation of the geomorphic boundary of the Loess Plateau is mostly based on classification boundaries and natural division boundaries. Based on different data sources and their expressions, this article reviews the previous research progress on the demarcation of the natural geographic boundary of loess landform types and summarizes the connotation of loess landforms boundary from morphological genetic geomorphic classification, digital geomorphic classification, and other classification systems. The advantages and disadvantages of quantitative description based on natural language and digital environment are analyzed. Besides, we sort out the quantitative identification and classification methods of the Loess Plateau landform types based on digital terrain analysis. Furthermore, we discuss and prospect the geomorphic boundaries from three aspects: (1) the relationship between the determination of the landform boundary and the classification system; (2) the reference of the delineation of the landform boundary; (3) the scale effect of the landform boundary. This review summarizes the background of the relevant theoretical studies on loess geomorphic regionalization and provides the theoretical basis and support for local practical work.

Network science provides abstract models for analyzing complex phenomena in the real world. With the support of network science theories and methods, researchers are able to explore the dynamic relationship between research objects in tourism domains from a more systematic perspective. This unique viewpoint is of great significance for further understanding the operation rules of tourism and promoting the balanced and sustainable development of related industries. With the digitalization of tourism, tourism information has become more flexible and scalable, which has significantly increased the applicability of network science theories and methods in tourism domains. Against this background, research on the applications of network science theories and methods in tourism domains has received extensive attention in recent years. In view of this, this paper systematically reviews the published articles related to the applications of network science theories and methods in tourism domains and summarizes the main research contents through a multi-scale perspective. Specifically, this paper first outlines the backgrounds of related theoretical foundations and application scenarios. The most common types of tourism networks, including interpersonal networks, tourist flow networks, economic networks, etc., are summarized through a "node-edge" structure. Important concepts and terms in network science, especially the differences and relations between complex networks and social networks as two "research paradigms", are also highlighted. Following that, this paper summarizes the progress of the applications of network science theories and methods in tourism domains at different scales of observation (i.e., microscopic, mesoscopic, and macroscopic). Among these scales, the microscopic scale focuses on the interactive properties of tourism actors, the mesoscopic scale is often used to describe the aggregation phenomena of tourism actors, and the macroscopic scale focuses on the global topological structural features of the tourism actor networks in tourism domains. Common methods or measures in network science, such as centrality, structural holes, community/cohesive subgroups, core-periphery structure, small worlds, and scale-free effect are also introduced. Based on the review of the research progress, this paper identifies the research problems in current research, including reliability deficiencies in the research data, negligence of multi-scale phenomena, interpretability challenges in the research results, and lack of highlighting theoretical contributions in tourism domains. The aim of this paper is to review the research literature on applications of network science theories and methods in tourism domains from the perspective of research practice, in order to effectively present the substance and compatibility of research at the intersection of network science and tourism.

Inland river ports are important nodes of inland river shipping links. Evaluation of the regional advantage of inland river ports is of great significance for port infrastructure construction in the Yangtze River Economic Belt. Taking the inland ports along the Yangtze River in 2021 as the research object, the original model is improved by using multi-source data and combining three indicators within the radiation range of inland ports on the Yangtze River. The AHP-EWM model is used to calculate the location advantage of 28 ports along the Yangtze River in the Yangtze River economic belt. Results show that: (1) except Chongqing and Wuhan, the density of traffic network in the port radiation range beyond Jiangsu province is relatively low. From the perspective of the influence of traffic networks, its distribution is relatively balanced, and the value is relatively similar. The influence of the spatial distribution of urban economics is disordered; (2) The spatial pattern of freight ports in the Yangtze River Economic Belt is characterized by "three centers, one cluster" according to their regional advantages and spatial distribution; (3) By dividing inland ports at the provincial level along the Yangtze River, it is found that the regional difference of dominance between the three ports in Jiangxi Province is the smallest, and the overall degree of dominance is also low. The result of Anhui Province is similar to Jiangxi Province. The overall degree of dominance of ports in Jiangsu Province is high with a small regional difference. The regional dominance of ports in Hubei Province has the largest difference, indicating that there might be issues such as unbalanced infrastructure construction that needs to be improved in future. The research results can provide guidance for infrastructure construction, road traffic planning, and port site selection of various ports in the Yangtze River Economic Belt, and help open up the "last kilometer" of railway and high-grade highway access to ports.

In recent years, with the improvement of public awareness of environmental protection, the pursuit of harmonious coexistence between man and nature of ecotourism has attracted more and more people's attention. In the face of rich and diverse ecotourism resources and the contradiction between supply and demand of domestic ecotourism, how to orderly develop and make rational use of resources under the premise of maximum protection, and transform "lucid waters and lush mountains" into "gold and silver mountains" scientifically and rationally is a major issue to be addressed at present. Taking Shennongjia Forestry District as an example, based on multi-source geospatial data, we use the XGBoost algorithm to evaluate its ecotourism suitability. The following conclusions are drawn: (1) The ecotourism suitability evaluation model based on XGBoost algorithm integrates machine learning technology and achieves good classification results with the idea of ​​data mining. The overall classification accuracy of the model under 10-fold cross-validation is 89.44%, with a high recall rate (89.68%). The F1 score is 0.8745, based on both the precision and recall. The AUC value of the model is 0.9593, and the overall classification performance of the model is excellent; (2) According to the ranking results of feature importance, the NDVI of ecological environment elements (26.86%), annual average temperature (11.61%), and distance from social and economic factors to the road (8.90%) has the highest contribution to the model; (3) The classification results of ecotourism suitability show that the overall ecotourism resources in Shennongjia Forestry District are rich. Highly suitable areas, moderately suitable areas, marginally suitable areas, and unsuitable areas account for 44.13%, 15.93%, 11.89%, and 28.05% of the total forest area, respectively. The research method of this paper breaks through the limitations of traditional ecotourism suitability assessment methods which are highly subjective, and solves practical problems based on data mining ideas and machine learning technology.

Geospatial simulation based on agent-based modeling is an effective method to recognize and understand dynamic geographic phenomena. As the scale and complexity of geospatial simulation continues to increase, the challenges in model computation increase. Distributed parallel simulation could be used to solve the complex simulation issue of large-scale agents. However, the existing research on building parallel simulation system based on agent modeling/simulation software is not suitable for modeling of spatial agent with high-mobility and behavioral interaction with others, and real-time visualization of simulation process. To solve this problem, this paper proposes a distributed geospatial simulation framework, namely DGSimF, for massive dynamic spatial agent modeling, which supports real-time representation and analysis of the simulation process. A simple but efficient spatial modeling agent for spatial-temporal data is designed, which supports the modeling of integrated geoscience models directly based on agent behavior, adopts the time differentiation method to coordinate the execution of the behavior of each computing node, supports distributed computation in the way of "task parallel" to improve the simulation performance, and constructs a Virtual Geographic Environment (VGE) based on three-dimensional earth rendering engine to support real-time visualization of intermediate simulation results. Finally, the experiments based on the "Red vs. Blue" case are carried out, and the simulation performance with different computation cost and different number of clients is analyzed. The results show that DGSimF can provide an effective platform for massive spatial agent simulation of spatio-temporal feature change and behavior interaction. By expanding the computing nodes, the pressure of complex simulation calculation can be effectively alleviated. Meanwhile, the simulation performance of the proposed framework is high, and the parallel efficiency remains above 0.7 in these experiments.

Traditional topographic change detection methods often ignore the spatial autocorrelation of DEM errors. To solve this problem, a topographic change detection method that considers the spatial autocorrelation of DEM errors is proposed in this paper. Firstly, the DEM of Difference (DoD) is obtained from two original DEMs, and the spatial distribution of DEM errors is evaluated by the Monte Carlo method. Secondly, based on spatially distributed DEM errors, DoD errors are calculated by error propagation and their spatial autocorrelation degree is analyzed using the semi-variance function. Finally, topographic changes (erosion, deposition, and net changes) are calculated based on the spatial autocorrelation analysis and significance detection. The results in four small catchments show that the elevation errors of UAV-photogrammetry DEM are spatially autocorrelated, which can be simulated by the Monte Carlo method. The use of spatially distributed error instead of RMSE for topographic change detection effectively reduces the sensitivity of the detection results to the significance threshold. When the significance threshold is increased from 68% to 95%, the loss of observations using the spatially distributed error is 5.39%~6.75% lower than that using the RMSE. The proposed method can be effectively used in the fields of surface deformation monitoring, erosion monitoring, sediment transport assessment, and so on.