Publications

Anthropogenic NO\\_2\\concentrations cause climate change and human health issues. Previous studies have focused on the contribution of traffic factors to NO\\_2\\emissions but have ignored the spatially varying impact of public transport supply and demand on high-resolution NO\\_2\\concentrations. This study first applies a two-stage interpolation model to generate a high-resolution urban NO\\_2\\concentration map originating from satellite measurement products. Then, we formulate 12 explanatory indicators derived from a fusion of massive big geo-data including smart card data and point of interest information, to represent the specific degree of public transport supply and citizens’ demand. Furthermore, a geographically weighted regression is applied to quantify the spatial variation in the effect of these indicators on the urban NO\\_2\\concentrations. The result shows that public transportation coverage, frequency, and capabilities as public transport supply indicators in metropolitan and suburban areas have a two-way influence on the NO\\_2\\emissions. However, among public transport demand indicators, the economic level has a significant positive impact in most areas. Our findings can provide policy implications for public transportation system optimization and air quality improvement.

Commuting flow prediction is a crucial issue for transport optimization and urban planning. However, the two existing types of solutions have inherent flaws. One is traditional models, such as the gravity model and radiation model. These models rely on fixed and simple mathematical formulas derived from physics, and ignore rich geographic semantics, which makes them difficult to model complex human mobility patterns. The other is the machine learning models, most of which simply leverage the features of Origin-Destination (OD), ignoring the topological nature of the interaction network and the spatial correlation brought by the nearby areas. In this paper, we propose a ‘preprocessing-encoder-decoder’ hybrid learning model, which can make full use of geographic semantic information and spatial neighborhood effects, thereby significantly improving the prediction performance. Specifically, in the preprocessing part, we divide the study area into grids, and then incorporates features such as location, population, and land use types. The second step of the encoder designs a convolutional neural network (CNN) to achieve the fusion of neighborhood features, constructs a spatial interaction network with the grids as nodes and the flows as edges, and then uses the graph convolutional network (GCN) to extract the embeddings of the nodes. In the last step of the decoder, a random forest regressor is trained to predict the commuting flow based on the learned embedding vectors. An empirical study on a commuter dataset in Beijing shows that our proposed model is approximately 20% better than XGBoost (state-of-the-art), thus proving its effectiveness.

Cross-city point of interest (POI) recommendation for tourists in an unfamiliar city has high application value but is challenging due to the data sparsity. Most existing models attempt to alleviate the sparsity problem by learning the user preference transfer and drift. However, they either fail to simultaneously model the preference transfer and drift in both long- and short-term user preferences or cannot accomplish the task of the next POI recommendation, which is crucial for a wide spectrum of applications ranging from transportation and urban planning to advertising. To address the limitation, we proposed a user preference transfer and drift network (UPTDNet) for cross-city next POI recommendation. UPTDNet excels at cross-city recommendations by learning the transfer and drift of both long- and short-term preferences. For short-term preference, dual recurrent neural network-based (RNN-based) branches are designed to model preference transfer from tourist’s current city and drift among different user roles. For long-term preference, a mapping function and user similarity calculation are employed for preference transfer from the tourist’s home city and drift among individual users. Experiments are conducted on the Gowalla and Foursquare datasets, and the results show that UPTDNet consistently and significantly outperforms state-of-the-art models by an average of 10.22% to 22.63% in the next POI recommendation task. Ablation study and further analysis validate the effectiveness and plausibility of considering both user preference transfer and drift in the cross-city recommendation.

Understanding the attractiveness of commercial agglomerations contributes to urban planning. Existing studies focus less on commercial agglomerations, and most directly use environmental supply factors to characterize attractiveness. This study measures attractiveness from the perspective of human demand. Specifically, we build a novel bipartite graph based on big geo-data of human mobility, using node centralities (degree, betweenness, and pagerank) to measure attractiveness. Next, we summarize multisource environmental features such as Point-of-Interests (POIs), land cover, transportation, and population, and use them as inputs to accurately predict attractiveness based on random forest. Finally, the spatial heterogeneity of the effects of these environmental variables on attractiveness is analyzed by multiscale geographically weighted regression. The results of the Beijing case show that: (1) All three centralities show a trend that the urban center is higher than the surrounding area, and betweenness is more reasonable. (2) Random forest can accurately predict attractiveness, with R 2 for degree, betweenness, and pagerank at 0.903, 0.846, and 0.760, respectively. (3) The number of shopping POIs, the length of main roads, and the number of bus stops positively affect attractiveness, while the effects of greening ratio and population density are bidirectional. As for the service scope, about 70% of commercial agglomerations have an average service radius of less than 15 km, which is significantly correlated with the Voronoi diagram. Our results can inspire understanding the human–environment relationship and guide urban policymakers in business planning.

This paper is a systematic review of the contemporary research progresses of urban vitality in China. Through examining the most related and advanced Chinese academic literatures, this paper introduces the core definitions and concepts and summarizes the methodology and findings of current Chinese urban vitality research. The data sources and quantitative research methods and paradigms such as vitality index frameworks are listed and discussed in detail regarding their strengths and limitations. From studies in multiple Chinese cities, we synthesize the effects and the influence mechanisms of multi-faceted factors on different types of urban vitality. Finally, we not only summarize and extrapolate the policy implications of these literatures for improving urban vitality but also propose recommendations for future research.

Identifying urban functional zones is of great significance for understanding urban structure and urban planning. The rapid growth and open accessibility of multisource big data, including remote sensing imagery and social sensing data, lead to a new way for dynamic identification of urban functional zones. In this article, we propose an SOE (scene-object-economy) based learning framework which integrates scene features from remote sensing imagery, object features from building footprints, and economy features from POIs (points of interest). From these three perspectives, rich information hidden in urban zone is excavated for function identification. Convolutional neural networks are used to extract high-level scene information from remote sensing images with different resolutions. Object features comprising a series of building indicators are constructed by measuring the area, perimeter, floor number, and year of the building. Moreover, we extract socioeconomic characteristics from POIs, which reflect different types of human activities in the urban zone. Last, random forest is used to identify functional zones based on SOE features. We apply the SOE-based framework to Shenzhen datasets and achieve 90.8% in accuracy with remote sensing images of 0.3-m spatial resolution. The experimental results show that the predicting performance of SOE-based framework is significantly better than other traditional methods, and the quantitative contribution of SOE factors is also revealed in determining functionality of urban zones.

Understanding quantitative relationships between urban elements is crucial for a wide range of applications. The observation at the macroscopic level demonstrates that the aggregated urban quantities (e.g., gross domestic product) scale systematically with population sizes across cities, also known as urban scaling laws. However, at the mesoscopic level, we lack an understanding of whether the simple scaling relationship holds within cities, which is a fundamental question regarding the spatial origin of scaling in urban systems. Here, by analyzing four extensive datasets covering millions of mobile phone users and urban facilities, we investigate the scaling phenomena within cities. We find that the mesoscopic infrastructure volume and socioeconomic activity scale sub- and super-linearly with the active population, respectively. For a same scaling phenomenon, however, the exponents vary in cities of similar population sizes. To explain these empirical observations, we propose a conceptual framework by considering the heterogeneous distributions of population and facilities, and the spatial interactions between them. Analytical and numerical results suggest that, despite the large number of complexities that influence urban activities, the simple interaction rules can effectively explain the observed regularity and heterogeneity in scaling behaviors within cities.

The outbreak of Corona Virus Disease 2019 (COVID-19) has affected the lives of people all over the world. It is particularly urgent and important to analyze the epidemic spreading law and support the implementation of epidemic prevention measures. It is found that there is a moderate to high correlations between the number of newly diagnosed cases per day and temperature and relative humidity in countries with more than 10,000 confirmed cases worldwide. In this paper, the correlation between temperature/relative humidity and the number of newly diagnosed cases is obvious. Governments can adjust the epidemic prevention measures according to climate change, which will more effectively control the spread of COVID-19.

Urban land use mapping is crucial for effective urban management and planning due to the rapid change of urban processes. State-of-the-art approaches rely heavily on the socioeconomic, topographical, infrastructural and land cover information of urban environments via feeding them into ad hoc classifiers for land use classification. Yet, the major challenge lies in the lack of a universal and reliable approach for the extraction and combination of physical and socioeconomic features derived from remote sensing imagery and social sensing data. This article proposes an ensemble-learning-approach-based solution of integrating a rich body of features derived from high resolution satellite images, street-view images, building footprints, points-of-interest (POIs) and social media check-ins for the urban land use mapping task. The proposed approach can statistically differentiate the importance of input feature variables and provides a good explanation for the relationships between land cover, socioeconomic activities and land use categories. We apply the proposed method to infer the land use distribution in fine-grained spatial granularity within the Fifth Ring Road of Beijing and achieve an average classification accuracy of 74.2% over nine typical land use types. The results also indicate that our model outperforms several alternative models that have been widely utilized as baselines for land use classification.

The spatial concentration of the human activity is a crucial indication of socioeconomic vitality. Accurately mapping activity volumes is fundamental to support the regional sustainable development. Current approaches rely on mobile positioning data, which record information about human daily activity but are inaccessible in most cities due to privacy and data sharing concerns. Alternative methods are needed to provide more generalized predictions on extensive areas while maintaining low cost. This study demonstrates how remote sensing imagery can be used through an end-to-end deep learning framework for reliable estimates of human activity volumes. The neighbor effect, representing the inherent nature of spatial autocorrelation in the volumes, is incorporated to improve the network. The proposed model exhibits strong predictive power and demonstrates great explainability of physical environment on variations of activity volumes. Landscape interpretations based on hierarchical features provide both object-based and region-based insights into the coevolvement of landscape and human activity. Our findings indicate the possibility of extensively predicting activity volumes, especially in areas with limited access to mobile data, and provide support for the promising framework to better comprehend broad aspects of the human society from observable physical environments.

Mixed use has been extensively applied as an urban planning principle and hinders the study of single urban functions. To address this problem, it is worth decomposing the mixed use. Inspired by the concept of spectral unmixing in remote sensing applications, this paper proposes a framework for mixed-use decomposition based on big geo-data. Mixed-use decomposition in terms of human activities differs from traditional land use research, and it is more reasonable to infer the actual urban function of land. The framework consists of four steps, namely temporal activity signature extraction, urban function base curve extraction, mixed-use decomposition, and result validation. First, the temporal activity signatures (TASs) of each zone are extracted as the proxy of human activity patterns. Second, the diurnal TASs of routine activities are extracted as urban function base curves (i.e. endmembers). Third, a linear decomposition model is used to decompose the mixed use and obtain multiple results (urban function composition, dynamic activity proportions, and the mixing index). Finally, result validation strategies are concluded. This framework offers method extensibility and has few requirements for the input data. It is validated by means of a case study of Beijing, based on a social media check-in dataset.

City image in general refers to the perception, the feeling, and the opinion of a city, which contributes great importance to urban management, urban planning, urban cultural perceptions, and tourism resource development. Traditionally, city image is often inferred by the ‘five-element’ model of physical factors while lacking the consideration of subjective perception. With the rising penetration of smart mobile devices and social media, massive data of location-related texts has been generated for a variety of urban areas. The accessibility to the big data leads to a new approach of understanding the subjective perception of city image, which is important since the new approach takes the subjective heterogeneity into account. Based on the Beijing’s Weibo (microblog) data in the year of 2016, we use a random forest model to categorize user backgrounds into locals and non-locals. Meanwhile, spatial clustering is applied to identify hotspots. Then two text analysis methods-term frequency-inverse document frequency (TF-IDF) and latent Dirichlet allocation (LDA)-are adopted to abstract topics regarding the different geographical hotspots in the city across the different groups of individuals. Our research shows text mining on geotagged big data for city image makes it possible to accommodate the heterogeneity of the activities of different groups of people and to understand their preferences for different points of interests in the city, and thereby reveals the socio-cultural and functional features for the city.

Inferring the unknown properties of a place relies on both its observed attributes and the characteristics of the places to which it is connected. Because place characteristics are unstructured and the metrics for place connections can be diverse, it is challenging to incorporate them in a spatial prediction task where the results could be affected by how the neighborhoods are delineated and where the true relevance among places is hard to identify. To bridge the gap, we introduce graph convolutional neural networks (GCNNs) to model places as a graph, where each place is formalized as a node, place characteristics are encoded as node features, and place connections are represented as the edges. GCNNs capture the knowledge of the relevant geographic context by optimizing the weights among graph neural network layers. A case study was designed in the Beijing metropolitan area to predict the unobserved place characteristics based on the observed properties and specific place connections. A series of comparative experiments was conducted to highlight the influence of different place connection measures on the prediction accuracy and to evaluate the predictability across different characteristic dimensions. This research enlightens the promising future of GCNNs in formalizing places for geographic knowledge representation and reasoning.

Abstract Public transport performance not only directly depicts the convenience of a city’s public transport, but also indirectly reflects urban dwellers’ life quality and urban attractiveness. Understanding why some regions are easier to get around by public transport helps to build a green transport friendly city. This paper initiates a new perspective and method to investigate how public transport network’s morphology contributes significantly to its performance. We investigate the significance of morphology from the perspective of graph classification – by extracting the typical local structures, called “motifs”, from the multi-modal public transport multigraph. A motif is seen as a certain connectivity pattern of different transport modes at a local scale. Combinations of various motifs decide the output of graph classification, particularly, public transport performance. We invent an innovative method to extract motifs on complex spatial multigraphs. The proposed method is adaptable to unify complex factors into one simple form for swift coding, and depends less on observational data to handle data unavailability. In the study area of Beijing, we validate that the measure can infer varied public transport efficiencies and access equalities of different regions. Some typical areas with undeveloped or unevenly distributed public transport are further discussed.

When travelling, people are accustomed to taking and uploading photos on social media websites, which has led to the accumulation of huge numbers of geotagged photos. Combined with multisource information (e.g. weather, transportation, or textual information), these geotagged photos could help us in constructing user preference profiles at a high level of detail. Therefore, using these geotagged photos, we built a personalised recommendation system to provide attraction recommendations that match a user’s preferences. Specifically, we retrieved a geotagged photo collection from the public API for Flickr (Flickr.com) and fetched a large amount of other contextual information to rebuild a user’s travel history. We then created a model-based recommendation method with a two-stage architecture that consists of candidate generation (the matching process) and candidate ranking. In the matching process, we used a support vector machine model that was modified for multiclass classification to generate the candidate list. In addition, we used a gradient boosting regression tree to score each candidate and rerank the list. Finally, we evaluated our recommendation results with respect to accuracy and ranking ability. Compared with widely used memory-based methods, our proposed method performs significantly better in the cold-start situation and when mining ‘long-tail’ data.

In the era of big data, spatial clustering is a very important means for geo-data analysis. When clustering big geo-data such as social media check-in data, geotagged photos, and taxi trajectory points, traditional spatial clustering algorithms are facing more challenges. On the one hand, existing spatial clustering tools cannot support the clustering of massive point sets; on the other hand, there is no perfect solution for self-adaptive spatial clustering. In order to achieve clustering of millions or even billions of points adaptively, a new spatial clustering tool—HiSpatialCluster—was proposed, in which the CFSFDP (clustering by fast search and finding density peaks) idea to find cluster centers and the DBSCAN (density-based spatial clustering of applications with noise) idea of density-connect filtering for classification are introduced. The tool’s source codes and other resources have been released on Github, and experimental evaluation was performed through clustering massive taxi trajectory points and Flickr geotagged photos in Beijing, China. The spatial clustering results were compared with those through K-means and DBSCAN as well. As a spatial clustering tool, HiSpatialCluster is expected to play a fundamental role in big geo-data research. First, this tool enables clustering adaptively on massive point datasets with uneven spatial density distribution. Second, the density-connect filter method is applied to generate homogeneous analysis units from geotagged data. Third, the tool is accelerated by both parallel CPU and GPU computing so that millions or even billions of points can be clustered efficiently.

The impacts of typhoons on coastal areas around the globe necessitate the risk assessments of typhoon events to analyze their paths, intensity, and impacts on the environment for disaster prevention and reduction as well as for the scientific assessments of typhoon impacts. To this end, the typhoon wind field needs to be obtained by inversion to attain its temporal and spatial scopes of influence and disaster-inducing intensities using simulation algorithms that are based on the existing typhoon path data. The wind field calculation is a typical kind of compute-intensive processing. It is time-consuming (especially when the temporal resolution and the spatial resolution are high) to an extent, which makes it difficult for a traditional stand-alone computation to meet the application needs for typhoon risk assessments. Therefore, studies need to be conducted to accelerate the wind field calculations. Currently, the most economical and relatively feasible method is to rapidly generate a large quantity of typhoon risk data using multi-thread, graphics processing unit computing or clustering technologies (e.g., cloud computing). Hence, we have attempted to use the latest cloud computing framework, Spark, for the rapid simulation of the typhoon wind field. This paper proposed a storage model for typhoon paths and wind fields under the Spark environment, as well as a wind field parallel acceleration method based on Spark. Using this approach, we have calculated a total of 1038 historical wind fields that impacted the northwestern Pacific Ocean from 1949 to 2014. The results indicate that the Spark-based wind field computation method proposed in this paper has a greater advantage in terms of performance, which facilitates the typhoon risk assessment feasibility.

The rapid development of social media and location-based service has generated a myriad of spatial data tagged with geo-information. Constructing a network of tourism hotspots using these geotagged data would improve our understanding of tourism activities. Thus, using Flickr data, we built a spatiallyembedded tourism hotspot network for Beijing and applied complex network analysis to study the network characteristics. The results indicate that the tourism hotspot network in Beijing is scale-free and smallworld. In the hotspot network, the interconnected triplets have a tendency to be formed by the edges with greater weight values, and a high-weighted edge is often connected by two high-degree vertices. Moreover, the statistics of the network provides insights for additional travel bus routes in Beijing. Finally, this paper provides a guide for building spatially-embedded hotspot networks based on geotagged social media data, which helps to understand the laws of travel and provides decision support for the development of tourism resources.

The rotating fan-beam scatterometer (RFSCAT) is a new type of satellite scatterometer that is proposed approximately 10 a ago. However, similar to other rotating scatterometers, relatively larger wind retrieval errors occur in the nadir and outer regions compared with the middle regions of the swath. For the RFSCAT with the given parameters, a wind direction retrieval accuracy decreases by approximately 9 in the outer regions compared with the middle region. To address this problem, an advanced wind vector retrieval algorithm for the RFSCAT is presented. The new algorithm features an adaptive extension of the range of wind direction for each wind vector cell position across the whole swath according to the distribution histogram of a retrieved wind direction bias. One hundred orbits of Level 2A data are simulated to validate and evaluate the new algorithm. Retrieval experiments demonstrate that the new advanced algorithm can effectively improve the wind direction retrieval accuracy in the nadir and outer regions of the RFSCAT swath. Approximately 1.6 and 9 improvements in the wind direction retrieval are achieved for the wind vector cells located at the nadir and the edge point of the swath, respectively.

Over recent years, massive geospatial information has been produced at a prodigious rate, and is usually geographically distributed across the Internet. Grid computing, as a recent development in the landscape of distributed computing, is deemed as a good solution for distributed geospatial data management and manipulation. Thus, the Grid computing technology can be applied to integrate various distributed resources into a ‘super-computer’ that enables efficient distributed geospatial query processing. In order to realize this vision, an effective mechanism for building the distributed geospatial query workflow in the Grid environment needs to be elaborately designed. The workflow-building technology aims to automatically transform the global geospatial query into an equivalent distributed query process in the Grid. In response to this goal, detailed steps and algorithms for building the distributed geospatial query workflow in the Grid environment are discussed in this article. Moreover, we develop corresponding software tools that enable Grid-based geospatial queries to be run against multiple data resources. Experimental results demonstrate that the proposed methodology is feasible and correct.

Grid computing is deemed as a good solution to the digital earth infrastructure. Various geographically dispersed geospatial resources can be connected and merged into a ‘supercomputer’ by using the grid-computing technology. On the other side, geosensor networks offer a new perspective for collecting physical data dynamically and modeling a real-time virtual world. Integrating geosensor networks and grid computing in geosensor grid can be compared to equipping the geospatial information grid with ‘eyes’ and ‘ears.’ Thus, real-time information in the physical world can be processed, correlated, and modeled to enable complex and advanced geospatial analyses on geosensor grid with capability of high-performance computation. There are several issues and challenges that need to be overcome before geosensor grid comes true. In this paper, we propose an integrated framework, comprising the geosensor network layer, the grid layer and the application layer, to address these design issues. Key technologies of the geosensor grid framework are discussed. And, a geosensor grid testbed is set up to illustrate the proposed framework and improve our geosensor grid design.

In recent years, geographical information systems have been employed in a wide variety of application domains, and as a result many research efforts are being devoted to those upcoming problems. Geospatial data security, especially access control, has attracted increased research interests within the academic community. The tendency towards sharing and interoperability of geospatial data and applications makes it common to acquire and integrate geospatial data from multiple organisations to accomplish a complex task. Meanwhile, many organisations have the requirement for securing access to possessed sensitive or proprietary geospatial data. In this heterogeneous and distributed environment, consistent access control functionality is crucial to promote controlled accessibility. As an extension of general access control mechanisms in the IT domain, the mechanism for geospatial data access control has its own requirements and characteristics of granularity and geospatial logic. In this paper, we address several fundamental aspects concerning the design and implementation of an access control system for geospatial data, including the classification, requirements, authorisation models, storage structures and management approaches for authorisation rules, matching and decision-making algorithms between authorisation rules and access requests, and its policy enforcement mechanisms. This paper also presents a system framework for realising access control functionality for geospatial data, and explain access control procedures in detail.

The highly efficient and stable collaborative computation platform for geospatial information can be constructed on the basis of Grid computing technology, combined with Peer-to-Peer (P2P) computing technology and geospatial database technology. This paper proposed the architecture and key technologies of the Grid GIS (Geographic Information System) incorporated with P2P structure, and correspondingly a Grid GIS prototype named Nebula was designed and then implemented. Nebula is a suite of middleware for geospatial Grid computing, which could be deployed onto various service nodes in network. Based on Grid protocols and infrastructure, Nebula provides invocation interfaces to users in form of Grid services. By using P2P message based communication mechanism, complex geospatial computation tasks could be accomplished by Nebula in a collaborative way. This paper introduced Nebula’s architecture and key modules, and according to experimental data, we discussed the Grid GIS’s advantages, application scenarios and future directions.