Search

Individual driving final destination prediction supports location-based services such as personalized service recommendations, traffic navigation, and public transport dispatching. However, real-time destination prediction is challenging due to the complexity of temporal dependencies, and the strong influence of travel spatiotemporal semantics and spatial correlations. Besides temporal context, the nearby urban functionalities of traveling zones and departure regions, and the crucial positions on the road network where trajectory points located would reflect the travel intentions of drivers. However, these spatial factors are rarely considered in existing studies. To fill this gap, we propose a real-time individual driving destination prediction model LSI-LSTM based on an attention-aware Long Short-Term Memory (LSTM) by taking Location Semantics and Location Importance of trajectory points into account. More specifically, a trajectory location semantics extraction method (t-LSE) enriches feature description with prior knowledge for implicit travel intentions learning. t-LSE represents urban functionality through Points of Interest (POIs) using Term Frequency-Inverse Document Frequency (TF-IDF). Meanwhile, a novel trajectory spatial attention mechanism (t-SAM) captures the trajectory points that strongly correlate to candidate destinations based on the location importance inferred from the driving status, i.e., turning angle, driving speed, and traveled distance. Comparative experiments with three baseline methods, i.e., Hidden Markov Model, Random Forest, and LSTM, demonstrate significant prediction accuracy improvements of LSI-LSTM on four individual trajectory datasets. Further analyses validate the effectiveness of the proposed semantic extraction method and attention mechanism, and also discuss the factors that may affect the prediction results.

Impervious surface has become one of the key factors of regional environmental problems and disasters. There rises an urgent need for mapping large-scale high-resolution impervious surfaces to help...

Parsing very high resolution (VHR) urban scene images into regions with semantic meaning, e.g. buildings and cars, is a fundamental task in urban scene understanding. However, due to the huge quantity of details contained in an image and the large variations of objects in scale and appearance, the existing semantic segmentation methods often break one object into pieces, or confuse adjacent objects and thus fail to depict these objects consistently. To address these issues uniformly, we propose a standalone end-to-end edge-aware neural network (EaNet) for urban scene semantic segmentation. For semantic consistency preservation inside objects, the EaNet model incorporates a large kernel pyramid pooling (LKPP) module to capture rich multi-scale context with strong continuous feature relations. To effectively separate confusing objects with sharp contours, a Dice-based edge-aware loss function (EA loss) is devised to guide the EaNet to refine both the pixel- and image-level edge information directly from semantic segmentation prediction. In the proposed EaNet model, the LKPP and the EA loss couple to enable comprehensive feature learning across an entire semantic object. Extensive experiments on three challenging datasets demonstrate that our method can be readily generalized to multi-scale ground/aerial urban scene images, achieving 81.7% in mIoU on Cityscapes Test set and 90.8% in the mean F1-score on the ISPRS Vaihingen 2D Test set. Code is available at: https://github.com/geovsion/EaNet .

Wildfire is an important ecosystem process, influencing land biogeophysical and biogeochemical dynamics and atmospheric composition. Fire-driven loss of vegetation cover, for example, directly modifies the surface energy budget as a consequence of changing albedo, surface roughness, and partitioning of sensible and latent heat fluxes. Carbon dioxide and methane emitted by fires contribute to a positive atmospheric forcing, whereas emissions of carbonaceous aerosols may contribute to surface cooling. Process-based modeling of wildfires in Earth system land models is challenging due to limited understanding of human, climate, and ecosystem controls on fire counts, fire size, and burned area. Integration of mechanistic wildfire models within Earth system models requires careful parameter calibration, which is computationally expensive and subject to equifinality. To explore alternative approaches, we present a deep neural network (DNN) scheme that surrogates the process-based wildfire model with the Energy Exascale Earth System Model (E3SM) interface. The DNN wildfire model accurately simulates observed burned area with over 90 % higher accuracy with a large reduction in parameterization time compared with the current process-based wildfire model. The surrogate wildfire model successfully captured the observed monthly regional burned area during validation period 2011 to 2015 (coefficient of determination, R2=0.93). Since the DNN wildfire model has the same input and output requirements as the E3SM process-based wildfire model, our results demonstrate the applicability of machine learning for high accuracy and efficient large-scale land model development and predictions.

Highlights • A hierarchical temporal attention based model is proposed to support short-term and long-term human mobility sequence prediction. • The proposed hierarchical temporal attention incorporates individual mobility patterns into the model architecture. • The model is compared with four baseline methods on individual trajectory datasets with varying degree of traveling uncertainty. • Experiments demonstrate the outperformance of the proposed method using three evaluation metrics. • The proposed model uncovers individual frequential and periodical mobility patterns in an interpretable manner., Prediction of individual mobility is crucial in human mobility related applications. Whereas, existing research on individual mobility prediction mainly focuses on next location prediction and short-term dependencies between traveling locations. Long-term location sequence prediction is of great importance for long-time traffic planning and location advertising, and long-term dependencies exist as individual mobility regularity typically occurs daily and weekly. This paper proposes a novel hierarchical temporal attention-based LSTM encoder-decoder model for individual location sequence prediction. The proposed hierarchical attention mechanism captures both long-term and short-term dependencies underlying in individual longitudinal trajectories, and uncovers frequential and periodical mobility patterns in an interpretable manner by incorporating the calendar cycle of individual travel regularities into location prediction. More specifically, the hierarchical attention consists of local temporal attention to identify highly related locations in each day, and global temporal attention to discern important travel regularities over a week. Experiments on individual trajectory datasets with varying degree of traveling uncertainty demonstrate that our method outperforms four baseline methods on three evaluation metrics. In addition, we explore the interpretability of the proposed model in understanding individual daily, and weekly mobility patterns by visualizing the temporal attention weights and frequent traveling patterns associated with locations.

The study of urban area is one of the hottest research topics in the field of remote sensing. With the accumulation of high-resolution (HR) remote sensing data and emerging of new satellite sensors, HR observation of urban areas has become increasingly possible, which provides us with more elaborate urban information. However, the strong heterogeneity in the spectral and spatial domain of HR imagery brings great challenges to urban remote sensing. In recent years, numerous approaches were proposed to deal with HR image interpretation over complex urban scenes, including a series of features from low level to high level, as well as state-of-the-art methods depicting not only the urban extent, but also the intra-urban variations. In this paper, we aim to summarize the major advances in HR urban remote sensing from the aspects of feature representation and information extraction. Moreover, the future trends are discussed from the perspectives of methodology, urban structure and pattern characterization, big data challenge, and global mapping.

Geocoding is an essential procedure in geographical information retrieval to associate place names with coordinates. Due to the inherent ambiguity of place names in natural language and the scarcity of place names in textual data, it is widely recognized that geocoding is challenging. Recent advances in deep learning have promoted the use of the neural network to improve the performance of geocoding. However, most of the existing approaches consider only the local context, e.g., neighboring words in a sentence, as opposed to the global context, e.g., the topic of the document. Lack of global information may have a severe impact on the robustness of the model. To fill the research gap, this paper proposes a novel global context embedding approach to generate linguistic and geospatial features through topic embedding and location embedding, respectively. A deep neural network called LGGeoCoder, which integrates local and global features, is developed to solve the geocoding as a classification problem. The experiments on a Wikipedia place name dataset demonstrate that LGGeoCoder achieves competitive performance compared with state-of-the-art models. Furthermore, the effect of introducing global linguistic and geospatial features in geocoding to alleviate the ambiguity and scarcity problem is discussed.

Existing spatial clustering methods primarily focus on points distributed in planar space. However, occurrence locations and background processes of most human mobility events within cities are con...

In the last half-century, geoscience research has advanced due to multidisciplinary technologies, among which Information and Communication Technology (ICT) has played a vital role. However, scientifically organizing these ICTs toward improving geoscience measurements, data processing, and information services has encountered tremendous challenges. This paper reviews a profound revolution in geoscience that has resulted from the Geospatial Sensor Web (GSW), serving as a new cyber-physical spatio-temporal information infrastructure for geoscience on the World Wide Web (WWW). In contrast to previous experiment-based and sensor-based paradigms, the GSW-based paradigm is able to accomplish the following: (1) achieve integrated and sharable management of diverse sensing resources, (2) obtain real-time or near real-time and spatiotemporal continuous data, (3) conduct interoperable and online geoscience data processing and analysis, and (4) provide focusing services with web-based geoscience information and knowledge. As a benefit of the GSW, increasingly more geoscience disciplines are enjoying the value of real-time data, multi-source monitoring, online processing, and intelligence services. This paper reviews the evolution of geoscience research paradigm to demonstrate the scientific background of GSW. Then, we elaborates on four key methods provided by GSW, namely, integrated management, collaborative observation, scalable processing and fusion, and focusing service web capacity. Furthermore, current GSW prototypes and applications for environmental, hydrological, and natural disaster analysis are also reviewed. Moreover, four challenges to the future GSW in geoscience research are identified and analyzed, including integration with the Model Web initiative for sophisticated geo-processing, integration with humans for pervasive sensing, integration with Internet of Things (IoT) to achieve high-quality performance and data mining, and integration with Artificial Intelligence (AI) to provide smart geoservices. We have concluded that GSW has become an indispensable cyber-physical infrastructure, and will play a greater role in geoscience research and application.

In massive spatio-temporal datasets, anomalies that deviate from the global or local distributions are not just useless noise but possibly imply significant changes, surprising patterns, and meaningful insights, and because of this, detection of spatio-temporal anomalies has become an important research hotspot in spatio-temporal data mining. For spatio-temporal flow data (e.g., traffic flow data), the existing anomaly detection methods cannot handle the embedded dynamic characteristic. Therefore, this paper proposes the approach of constructing dynamic neighbourhoods to detect the anomalies in spatio-temporal flow data (called spatio-temporal flow anomalies). In this approach, the dynamic spatio-temporal flow is first modelled based on the real-time attribute values of the flow data, e.g., the velocity of vehicles. The dynamic neighbourhoods are then constructed by considering attribute similarity in the spatio-temporal flow. On this basis, global and local anomalies are detected by employing the idea of the G ⁎ statistic and the problem of multiple hypothesis testing is further addressed to control the false discovery rate. The effectiveness and practicality of our proposed approach are demonstrated through comparative experiments on traffic flow data from the central road network of central London for both weekdays and weekends.

The integration and visualization of geospatial data on a virtual globe play an significant role in understanding and analysis of the Earth surface processes. However, the current virtual globes always sacrifice the accuracy to ensure the efficiency for global data processing and visualization, which devalue their functionality for scientific applications. In this article, we propose a high-accuracy multi-resolution TIN pyramid construction and visualization method for virtual globe. Firstly, we introduce the cartographic principles to formulize the level of detail (LOD) generation so that the TIN model in each layer is controlled with a data quality standard. A maximum z-tolerance algorithm is then used to iteratively construct the multi-resolution TIN pyramid. Moreover, the extracted landscape features are incorporated into each-layer TIN, thus preserving the topological structure of terrain surface at different levels. In the proposed framework, a virtual node (VN)-based approach is developed to seamlessly partition and discretize each triangulation layer into tiles, which can be organized and stored with a global quad-tree index. Finally, the real time out-of-core spherical terrain rendering is realized on a virtual globe system VirtualWorld1.0. The experimental results showed that the proposed method can achieve an high-fidelity terrain representation, while produce a high quality underlying data that satisfies the demand for scientific analysis.

With the advancement of Web technologies, the service-oriented approach has become increasingly popular to share and couple environmental models. Interoperability is critical to the access and integration of Web services. The OGC Web Processing Service (WPS) defines an interoperable protocol for process execution on the Web. However, it has limitations in supporting time-step calculations that are usually required by complex models, e.g., time marching models. The Open Modeling Interface (OpenMI) standard brings about interoperability for time-step based interactions between modeling components. This paper introduces an approach to sharing environmental models on the Web by coupling OpenMI and WPS. Key issues, including maintaining state, data representation, model description, and model execution, are considered in our approach. An open-source software is developed to support the deployment of the environment models in an interoperable way. TOPMODEL and SWMM5 use cases illustrate the applicability of the approach and implementation.

We propose to advance the scientific understanding through applications of geospatial service platforms, which can help students and researchers investigate various scientific problems in a Web-based environment with online tools and services. The platform also offers capabilities for sharing data, algorithm, and problem-solving knowledge. To fulfil this goal, the paper introduces a new course, named "Geospatial Service Platform for Education and Research", to be held in the ISPRS summer school in May 2014 at Wuhan University, China. The course will share cutting-edge achievements of a geospatial service platform with students from different countries, and train them with online tools from the platform for geospatial data processing and scientific research. The content of the course includes the basic concepts of geospatial Web services, service-oriented architecture, geoprocessing modelling and chaining, and problem-solving using geospatial services. In particular, the course will offer a geospatial service platform for handson practice. There will be three kinds of exercises in the course: geoprocessing algorithm sharing through service development, geoprocessing modelling through service chaining, and online geospatial analysis using geospatial services. Students can choose one of them, depending on their interests and background. Existing geoprocessing services from OpenRS and GeoPW will be introduced. The summer course offers two service chaining tools, GeoChaining and GeoJModelBuilder, as instances to explain specifically the method for building service chains in view of different demands. After this course, students can learn how to use online service platforms for geospatial resource sharing and problem-solving.

Different Earth-observing (EO) sensors have various capabilities for diverse observing tasks. Sensor planning services make the choice of web-ready sensors for specific observing tasks with regard to observing requests and sensor capabilities. Sensor capabilities rely on various parameters; thus, choosing EO sensors for specific observing tasks relying directly on these parameters is a multicriteria decision process. A sensor's capability can be drawn from these parameters with the help of an algorithm. Furthermore, if divided into different clusters based on capabilities, applicable sensors can be more easily chosen for a category of observing tasks. In this paper, a spaceborne EO optical sensor static capability index (SSCI) mechanism is drawn from an evaluation-and-clustering algorithm, which is composed of a self-organizing neural map in combination with weighted principal component analysis. The scheme of SSCI relies on no expert analysis system and thus is more flexible and efficient. EO scenarios of disaster reactions are among the application of this algorithm. In particular, scenarios of flooding disaster forecasting, relief aiding, and postdisaster loss assessment within the framework of International Charter on Space and Major Disasters have been utilized for experiments. They have shown that the SSCI assessing algorithm is feasible and stable, and the EO optical sensor clustering algorithm based on SSCI can offer reasonable clustering accuracies of EO optical sensors. In our experiments, the EO optical sensor SSCI computation and clustering algorithm had a time consumption within 2 s and 2 min, respectively, and memory consumption within 200 MB on a normal personal computer.

With the rapid development of geospatial service and sensor technologies, large volumes of geospatial data have been collected using various sensor networks, and accessible on the Web. Traditional geospatial data processing could be task-oriented, since a geoprocessing task can be described by a set of action steps, implemented as a workflow, and executed using distributed geoprocessing services. Tasks facilitate the expression of user requirements and capture the problem solving knowledge of users. In this paper, the task-oriented approach is extended to the OGC Sensor Web environment. It highlights how the event-driven technologies adopted by the Sensor Web can be leveraged with geoprocessing workflows to support environment monitoring tasks. The proposal of a Task Model Language (TaskML) and task trigger mechanism allows environmental events to be plugged into an existing model builder, GeoJModelBuilder. Tasks can be created in a stepwise manner, and their execution priority can be updated automatically using triggers. Compared to the traditional “reactive” task enactment mode, the trigger-augmented task can support “active” environmental monitoring. Use cases on PM2.5/PM10 monitoring demonstrate the applicability of the approach.

Geospatial web service composition is a promising means for processing and analyzing geospatial data in distributed computing environments. However, convenient and effective approaches for assisting the invocation of geoprocessing workflows are still missing. Invocation errors frustrate users and eventually impact the popularity and application of geoprocessing workflows due to their complexity, inadequate description, constraints, and prompts for input/output parameters, workflow models, and their components. This article proposes an extension method for easy invocation of geoprocessing workflows to solve these problems. The proposed method facilitates the generation of Graphical User Interfaces (GUIs) and invocation messages, for human-computer interaction and client-workflow interaction respectively, by supplementing verification and constraints for workflow descriptions. Furthermore, by providing descriptive information, constraint mechanisms, and visualization functions, this approach enhances human-computer interactivity during invocation. An exemplary user case demonstrates the feasibility of the method.

This study proposes a virtual globe-based vector data model named the quaternary quadrangle vector tile model (QQVTM) in order to better manage, visualize, and analyze massive amounts of global multi-scale vector data. The model integrates the quaternary quadrangle mesh (a discrete global grid system) and global image, terrain, and vector data. A QQVTM-based organization method is presented to organize global multi-scale vector data, including linear and polygonal vector data. In addition, tile-based reconstruction algorithms are designed to search and stitch the vector fragments scattered in tiles to reconstruct and store the entire vector geometries to support vector query and 3D analysis of global datasets. These organized vector data are in turn visualized and queried using a geometry-based approach. Our experimental results demonstrate that the QQVTM can satisfy the requirements for global vector data organization, visualization, and querying. Moreover, the QQVTM performs better than unorganized 2D v...

Recently, driven by innovation of GPS technology, mobile location-based applications were a development of blowout. Trajectory data which contains mining valve is widely distributed and large-scale. How to organize trajectory data on a global scale and support efficient range queries becomes a problem. This paper presents a framework of adaptive Geohash-Tree based on Secondo database to organize the worldwide and large-scale trajectory dataset. In our framework, according to the Geohash code, different trajectory datasets will be covered by the deepest Geohash grid, and then we take this Geohash grid as root node to generate adaptive Geohash-Tree. In order to speed up queries to locate the corresponding index, we design prefix-sharing tree on the basis of the feature of Geohash. Adaptive Geohash-Tree is a spatial index based on grid. It can divide the space according to the track density by adopting a variety of strategies which improves the efficiency of range query. Meanwhile, we design the algorithm of incremental insertion and update for the supporting of real-time update of trajectory data. Furthermore, adaptive Geohash-Tree has been migrated into Secondo database. By taking advantage of database, management and query of trajectories can be easier. The experiment results verify that our approach in several aspects such as range query and occupied disk size performs better than the commonly applied R-Tree.

Over the past few years, Earth Observation (EO) has been continuously generating much spatiotemporal data that serves for societies in resource surveillance, environment protection, and disaster prediction. The proliferation of EO data poses great challenges in current approaches for data management and processing. Nowadays, the Array Database technologies show great promise in managing and processing EO Big Data. This paper suggests storing and processing EO data as multidimensional arrays based on state-of-the-art array database technologies. A multidimensional spatiotemporal array model is proposed for EO data with specific strategies for mapping spatial coordinates to dimensional coordinates in the model transformation. It allows consistent query semantics in databases and improves the in-database computing by adopting unified array models in databases for EO data. Our approach is implemented as an extension to SciDB, an open-source array database. The test shows that it gains much better performance in the computation compared with traditional databases. A forest fire simulation study case is presented to demonstrate how the approach facilitates the EO data management and in-database computation.

A geospatial sensor web can be seen as a complex observation system consisting of distributed nodes with different functions and web-based access interfaces. Because of its heterogeneous characteristic, the precise discovery and efficient allocation of available nodes have become key problems in the field of sensor web resource integrated management. Considering the management requirements of a flood monitoring system, we propose a sensor web heterogeneous node meta-model and discuss the development of five basic metadata components, the design of a nine-tuple node information description structure. A prototype system GeosensorNodeManager is implemented to provide the functions of modeling, querying, and visualizing node resources. For the application scenario of flood monitoring, the flood forecasting task is selected as an example to test the versatility of the proposed node meta-model and the applicability of the formal expression based on the nine-tuple metadata framework. Results show that the proposed meta-model can be used in the modeling of three different types of sensor web nodes with the extension mechanism. By querying and visualizing the sensor web node instances in the Yangtze River basin, the node meta-model provides an effective way for the resource management of a flood monitoring sensor web system. Compared with the typical flood monitoring platform ''Sentinel Asia,'' the proposed meta-model can offer a succinct description of the system and lay the component model foundation for architecture design.

Cultural relics represent national or even global resources of inestimable value. How to efficiently manage and preserve these cultural relics is a vitally important issue. To achieve this goal, this study proposed, designed, and implemented an RFID and Sensor Web-enabled smart cultural relics management system (SCRMS). In this system, active photovoltaic subtle energy-powered Radio Frequency Identification (RFID) is used for long-range contactless identification and lifecycle management of cultural relics during their storage and circulation. In addition, different types of ambient sensors are integrated with the RFID tags and deployed around cultural relics to monitor their environmental parameters, helping to ensure that they remain in good condition. An Android-based smart mobile application, as middleware, is used in collaboration with RFID readers to collect information and provide convenient management for the circulation of cultural relics. Moreover, multiple sensing techniques are taken advantage of simultaneously for preservation of cultural relics. The proposed system was successfully applied to a museum in the Yongding District, Fujian Province, China, demonstrating its feasibility and advantages for smart and efficient management and preservation of cultural relics.

Visualization of geospatial data provenance aims to provide a user-friendly way for easy navigation and increased understanding of the derivation history of geoscientific results. Most existing work focuses on provenance modeling and management. This paper proposes to interleave map and faceted metadata for geospatial data provenance visualization and navigation. It shows how provenance in Web-geoprocessing workflows can be visualized at four levels: feature, dataset, service, and knowledge. A prototypical system, named GeoPWProv, is developed to demonstrate the applicability of the approach.

Geospatial data provenance records sources and processing steps that are used in deriving geospatial data products. In the Web of Data environment enabled by Linked Data technologies, sources and processing steps, such as geospatial data and geoprocessing services, can be published as part of the Web of Data. To take full advantages of the machine-understandable format and linkages among heterogeneous data items in the Web of Data, this paper proposes to publish geospatial data provenance into the Web of Data. In particular, it analyzes how a catalogue for provenance, i.e., geospatial data provenance managed by a geospatial metadata catalog service, can be published into the Web of Data using a Linked Data approach. Consequently, queries over linked geospatial data provenance are analyzed and tested to demonstrate the benefits of the approach.

Geospatial metadata from metadata catalogue can be published as part of Web of data used Linked Data technologies. The published data could be named as linked geospatial metadata. A key issue of Linked Data technologies is to create links among datasets. There are three important types of RDF links: relationship links, identity links, and vocabulary links. This paper proposes a matching method to construct linkages between linked geospatial metadata and geospatial datasets in the linking open data cloud (LOD). This matching method is based on semantic similarity to construct identity links. A matching algorithm using Tversky‘s contrast model and Jaro-Winkler distance is proposed and evaluated.

How to integrate and disseminate globally distributed multi-source and heterogeneous spatial information is an open problem in integration and sharing service of geographic information. Here we propose a new service architecture suitable for integration and sharing of distributed multi-source geographic information. We also propose a global virtual pyramid model, which can be applied in 3D virtual globes. In view of the difficulty of web multi-node geographic information sharing service, we propose a web multi-node service aggregation method, integrated in our autonomously developed virtual globe platform GeoGlobe and introduced in the National Platform for Common GeoSpatial Information Services named “TIANDITU”. It achieves 2D and 3D integration for geographic information service. virtual globe, service aggregation, National Platform for Common GeoSpatial Information Services

The emergence of Cloud Computing technologies brings a new information infrastructure to users. Providing geoprocessing functions in Cloud Computing platforms can bring scalable, on-demand, and cost–effective geoprocessing services to geospatial users. This paper provides a comparative analysis of geoprocessing in Cloud Computing platforms – Microsoft Windows Azure and Google App Engine. The analysis compares differences in the data storage, architecture model, and development environment based on the experience to develop geoprocessing services in the two Cloud Computing platforms; emphasizes the importance of virtualization; recommends applications of hybrid geoprocessing Clouds, and suggests an interoperable solution on geoprocessing Cloud services. The comparison allows one to selectively utilize Cloud Computing platforms or hybrid Cloud pattern, once it is understood that the current development of geoprocessing Cloud services is restricted to specific Cloud Computing platforms with certain ...

The long production cycle and huge cost of collecting road network data often leave the data lagging behind the latest real conditions. However, this situation is rapidly changing as the positioning techniques ubiquitously used in mobile devices are gradually being implemented in road network research and applications. Currently, the predominant approaches infer road networks from mobile location information (e.g., GPS trajectory data) directly using various extracting algorithms, which leads to expensive consumption of computational resources in the case of large-scale areas. For this reason, we propose an alternative that renews road networks with a novel spiral strategy, including a hidden Markov model (HMM) for detecting potential problems in existing road network data and a method to update the data, on the local scale, by generating new road segments from trajectory data. The proposed approach reduces computation costs on roads with completed or updated information by updating problem road segments in the minimum range of the road network. We evaluated the performance of our proposals using GPS traces collected from taxies and OpenStreetMap (OSM) road networks covering urban areas of Wuhan City.

Space-time interpolation is widely used to estimate missing or unobserved values in a dataset integrating both spatial and temporal records. Although space-time interpolation plays a key role in space-time modeling, existing methods were mainly developed for space-time processes that exhibit stationarity in space and time. It is still challenging to model heterogeneity of space-time data in the interpolation model. To overcome this limitation, in this study, a novel space-time interpolation method considering both spatial and temporal heterogeneity is developed for estimating missing data in space-time datasets. The interpolation operation is first implemented in spatial and temporal dimensions. Heterogeneous covariance functions are constructed to obtain the best linear unbiased estimates in spatial and temporal dimensions. Spatial and temporal correlations are then considered to combine the interpolation results in spatial and temporal dimensions to estimate the missing data. The proposed method is tested on annual average temperature and precipitation data in China (1984–2009). Experimental results show that, for these datasets, the proposed method outperforms three state-of-the-art methods—e.g., spatio-temporal kriging, spatio-temporal inverse distance weighting, and point estimation model of biased hospitals-based area disease estimation methods.

Many achievements in web-based geoprocessing focus on logically chaining Open Geospatial Consortium (OGC) web services, for example using Business Process Execution Language to orchestrate web services that are interfaced through the OGC Web Processing Service. For e-Science application in a sensor web environment, how to internally integrate the sensor system, observation, and processes (physical and non-physical) as a geoprocessing e-Science workflow model is a critical issue. The OGC Sensor Model Language offers the possibility to construct a geoprocessing e-Science workflow model in the form of observation processes. We propose a construction method for a geoprocessing e-Science workflow model that integrates logical and physical processes into a composite process chain for sensor observations. The three phases of geoprocessing e-Science workflow creation are abstract process chain modeling, process chain instantiation, and process chain workflow execution. An experiment on chaining-related sub-processes for deriving the Normalized Difference Vegetation Index of Hubei Province (China) was conducted to verify the feasibility of the proposed workflow model.

We propose to advance the scientific understanding and applications of geospatial data by coupling Sensor Web and Geoprocessing Services in Virtual Globes for higher-education teaching and research. The vision is the concept of "What You See is What You Get" geoprocessing, shortly known as WYSIWYG geoprocessing. Virtual Globes offer tremendous opportunities, such as providing a learning tool to help educational users and researchers digest global-scale geospatial information about the world, and acting as WYSIWYG platforms, where domain experts can see what their fingertips act in an interactive three-dimensional virtual environment. In the meantime, Sensor Web and Web Service technologies make a large amount of Earth observing sensors and geoprocessing functionalities easily accessible to educational users and researchers like their local resources. Coupling Sensor Web and geoprocessing Services in Virtual Globes will bring a virtual learning and research environment to the desktops of students and professors, empowering them with WYSIWYG geoprocessing capabilities. The implementation combines the visualization and communication power of Virtual Globes with the on-demand data collection and analysis functionalities of Sensor Web and geoprocessing services, to help students and researchers investigate various scientific problems in an environment with natural and intuitive user experiences. The work will contribute to the scientific and educational activities of geoinformatic communities in that they will have a platform that are easily accessible and help themselves perceive world space and perform live geoscientific processes.

The existing Spatial Data Infrastructure applications or virtual globes allow users to experiment with these tools for sharing and exploration of geospatial data. A typical application is the recently launched MapWorld, an interactive geospatial data browser developed based on GeoGlobe. Geospatial Service Web goes further by providing a geospatial infrastructure that integrates various geospatial-related resources through the Web and service technologies. The development of the Geospatial Service Web will be the establishment of a platform where data, information, and knowledge can be shared and exchanged in an interoperable and interworkable way. The fulfilment of this platform requires the integration of geospatial data acquisition system, data transformation system, distributed spatial data collection, high-capability server system, and large volume storage system etc., and exploration and extraction of useful information and knowledge from oceans of data. These are together known as Web-based Geospatial Intelligence (i.e. Web GeoIntelligence), which is an important content of the Geospatial Service Web.

This paper reviewed the developments of the last ten years in the field of international high-resolution earth observation, and introduced the developmental status and plans for China’s high-resolution earth observation program. In addition, this paper expounded the transformation mechanism and procedure from earth observation data to geospatial information and geographical knowledge, and examined the key scientific and technological issues, including earth observation networks, high-precision image positioning, image understanding, automatic spatial information extraction, and focus services. These analyses provide a new impetus for pushing the application of China’s high-resolution earth observation system from a “quantity” to “quality” change, from China to the world, from providing products to providing online service.

A geospatial cyberinfrastructure is needed to support advanced GIScience research and education activities. However, the heterogeneous and distributed nature of geospatial resources creates enormous obstacles for building a unified and interoperable geospatial cyberinfrastructure. In this paper, we propose the Geospatial Service Web (GSW) to underpin the development of a future geospatial cyberinfrastructure. The GSW excels over the traditional spatial data infrastructure by providing a highly intelligent geospatial middleware to integrate various geospatial resources through the Internet based on interoperable Web service technologies. The development of the GSW focuses on the establishment of a platform where data, information, and knowledge can be shared and exchanged in an interoperable manner. Theoretically, we describe the conceptual framework and research challenges for GSW, and then introduce our recent research toward building a GSW. A research agenda for building a GSW is also presented in the p...

Recent advances in sensor web geospatial data capture, have led to the generation of large numbers of real-time or near-real-time observations and measurements. As the magnitude of Web Coverage Service (WCS) and Sensor Observation Service (SOS) becomes increasingly large, a major problem is how to make fast and fully robust use of such data services in a Web-ready sensors environment. A new method is proposed, Real-time Coverage Service (RCS), for serving observational data based on the integration of WCS and SOS. The RCS method hides the complexity of a series of information models and service interfaces in the Earth Observation (EO) and Sensor Web world, allowing near-real-time on-demand access to geospatial observations. The core components-dynamical schema transformer and automatic information extractor-are designed and implemented based on service middleware technology. The Observations & Measurements (O&M) schema of SOS and coverage schema of WCS are matched by schema transformer dynamically. The coverage information is extracted from a SOS “GetObservation” operation by an information extractor and served by a WCS “GetCoverage” operation on-demand. Experiments on the feasibility of Earth Observing-1 (EO-1) Hyperion data retrieval for the RCS method and OGC Sensor Web SOS method were conducted and their efficiency compared. The results show that the proposed RCS has architecture that is more robust and performs more efficiently than the SOS method.

Aiming at the storage and management problems of massive remote sensing data, this paper gives a comprehensive analysis of the characteristics and advantages of thirteen data storage centers or systems at home and abroad. They mainly include the NASA EOS, World Wind, Google Earth, Google Maps, Bing Maps, Microsoft TerraServer, ESA, Earth Simulator, GeoEye, Map World, China Centre for Resources Satellite Data and Application, National Satellite Meteorological Centre, and National Satellite Ocean Application Service. By summing up the practical data storage and management technologies in terms of remote sensing data storage organization and storage architecture, it will be helpful to seek more suitable techniques and methods for massive remote sensing data storage and management.

One of the earliest investigations of provenance was inspired by applications in GIS in the early 1990’s. Provenance records the processing history of a data product. It provides an information context to help users determine the reliability of data products. Conventional provenance applications in GIS focus on provenance capture, representation, and usage in a stand-alone environment such as a desktop-based GIS software system. They cannot support wide sharing and open access of provenance in a distributed environment. The growth of service-oriented sharing and processing of geospatial data brings some new challenges in provenance-aware applications. One is how to share geospatial provenance in an interoperable way. This paper describes the development of provenance service for geospatial data products using the ebXML Registry Information Model (ebRIM) of a geospatial catalog service, which follows the interface specifications of the OGC Catalogue Services for the Web (CSW). This approach fits well the current service stack of the GIS domain and facilitates the management of geospatial data provenance in an open and distributed environment.

How to achieve a flexible data and sensor planning service to schedule, plan, and empower diverse sensors and heterogeneous data ordering systems is a big challenge. In this paper, a service-oriented framework of data and sensor planning service for virtual sensors is proposed. The framework includes an Open Geospatial Consortium (OGC)-compliant Sensor Planning Service (SPS), a Web Notification Service (WNS), a Sensor Observation Service (SOS), and virtual sensors. There are two important key technologies in this framework, namely a flexible SPS middleware and an asynchronous message notification mechanism. The flexible SPS middleware, based on a configuration file and standard interfaces, is adopted to integrate virtual sensors into a sensor Web. A WNS-based asynchronous notification middleware is used to inform the user of the status of a task that may need midterm or long-term actions. The framework has been successfully demonstrated in application scenarios for Simplified General Perturbations Satellite Orbit Model 4 (SGP4) and Earth Observation System ClearingHOuse (ECHO). The results show that the proposed method has the following improvements over the existing SPS implementation: a uniform planning service for more satellites, a seamless connection with data order systems, and a flexible service-oriented framework for virtual sensors.

Recent advances in Semantic Web and Web Service technologies has shown promise for automatically deriving geospatial information and knowledge from Earth science data distributed over the Web. In a service-oriented environment, the data, information, and knowledge are often consumed or produced by complex, distributed geoscientific workflows or service chains. In order for the chaining results to be consumable, sufficient metadata for data products to be delivered by service chains must be provided. This paper proposes automatic generation of geospatial metadata for Earth science virtual data products. A virtual data product is represented using process models, and can be materialized on demand by dynamically binding and chaining archived data and services, as opposed to requiring that Earth science data products be physically archived. Semantics-enabled geospatial metadata is generated, validated, and propagated during the materialization of a virtual data product. The generated metadata not only provides a context in which end-users can interpret data products before intensive execution of service chains, but also assures semantic consistency of the service chains.

A new method for serving observational data, based on a reusable geo-processing workflow (GPW), is proposed in order to meet the requirements of the automatic AutoChem data feed service in the sensor web environment. A service-oriented architecture (SOA) is adopted. The system has three roles: the GPW provider, registry center, and portal. The system has GPW design, deployment, registration, search, and invocation functions. The AutoChem data discovery, processing, and integration GPW is implemented by chaining NASA EOS ClearingHOuse data service system, the George Mason University (GMU) Catalogue Service for the Web, the GMU Web Coverage Service, and a series of preprocessing services wrapped with the Web Processing Service. The reused data feed flows have been tested using data from the NASA Aura Ozone Monitoring Instrument. Test results show that the proposed data feed service can also be used by the NASA Aqua Atmospheric Infrared Sounder and the Aura Microwave Limb Sounder. Its architecture is more flexible, and it performs more automatically than the traditional method.

Recent advances in Web-related technologies have significantly promoted the wide sharing and integrated analysis of distributed geospatial data. Geospatial applications often involve diverse sources of data and complex geoprocessing functions. Existing Web-based GIS focuses more on access to distributed geospatial data. In scientific problem solving, the ability to carry out geospatial analysis is essential to geoscientific discovery. This article presents the design and implementation of

Public participation is very important for the success of an urban planning project, since any urban planning project will ultimately become part of the everyday life of the public. Most members of the general public are not urban planning professionals; therefore, well-designed visualization and interactive tools can help expand their participation in urban planning processes. The emerging technology of virtual globe-based 3D visualization is a unique opportunity to facilitate public participation in urban planning projects by promoting intuitive 3D interaction, instant interoperability and seamless integration of 3D visualization with other traditional text and multimedia information channels. This paper discusses the technical issues of developing a virtual globe-based 3D visualization framework for publicizing urban planning information, using Web Services and Service Oriented Architecture (SOA) to support visual planning model sharing and interoperability. With 3D photorealistic visualization, end users can conveniently obtain both the macro-vision of a project on the global scale and the micro-details on the street scale, using swift zooming tools like Google Earth. End users can select any available urban planning solution for visual investigation and comparison in a virtual globe-based 3D visualization environment. The service oriented architecture allows urban planning information to be deployed as a service in one server or several geographically distributed servers, or even from the end user’s own computer. With the architecture’s capability for integrating distributed resources, other traditional interactive functions such as labeling, BBS, forum, and email, can also be conveniently integrated into the system. Auxiliary spatial analysis tools are integrated to help end users perform “professional” tasks such as sunlight analysis and 3D distance measurement. This highly distributed system is designed for the Internet; therefore, any personal computer connected to the Internet can easily access the system and participate in the interaction.

Massive volumes of global geospatial information are being collected by newly designed acquisition devices and generated by various geospatial applications. This poses a critical challenge to efficiently organize and effectively integrate global multi-source geospatial information. This paper introduces a global seamless data model for the organization of huge multi-source, multi-resolution and multi-temporal geospatial data. Based on this data model, the management of the global multi-resolution pyramid is discussed in detail. To integrate geospatial data and processing functions from various GIS systems, a service-oriented framework is presented through the technology of Virtual Globe. Finally, a Virtual Globe system, GeoGlobe, is developed and illustrated.

This paper explores the use of cloud computing for remote sensing image processing. The main contribution of our work is to develop a remote sensing image processing platform based on cloud computing technology (OpenRS-Cloud). This paper focuses on enabling methodical investigations into the development pattern, computational model, data management and service model exploring this novel distributed computing model. The experimental INSAR processing flow is implemented to verify the efficiency and feasibility of OpenRS-Cloud platform. The results show that cloud computing is well suited for computationally-intensive and data-intensive remote sensing services.

Virtual globe has been recognized as an appealing technology to support the digital earth. It provides an intuitive and appealing way to visualize geospatial information, and is being used frequently to bring the globe-scale geospatial information to our fingertips. The easy access to virtual globes such as Google Earth, Microsoft Virtual Earth, and NASA World Wind allows both the general public users and professionals to use them for educational and research purposes. While virtual globes provide a number of functions for geospatial data visualization and annotation, the geospatial analysis functions available in the current virtual globes are limited. This paper addresses an approach to the establishment of an analysis-enhanced virtual globe. The approach is based on the integration of virtual globe and interoperable geoprocessing services. Such an analysis-enhanced virtual globe combines the visualization and communication power of virtual globes with the conventional powerful analysis functions of GIS, thus meeting the analysis demands in digital earth.

Various measures are available for assessing image fusion quality. Some measures are from traditional image quality assessment and some are specially designed for image fusion evaluation. It has been found from a survey that there is a total of 27 measures in common use. It can be imagined that some of them are more reliable than others for certain applications and some of them may be quite highly correlated. Therefore, a thorough mathematical analysis of these measures is desirable to understand what measures should be adopted for a given application. This article describes a multivariate statistical analysis of these measures to reduce redundancy and find comparatively independent measures for assessing the quality of fused images. First, correlation coefficients are calculated for the 27 measures; then, factor analysis using principal components is performed based on correlation matrix; and finally, hierarchical clustering is carried out on the factors to obtain finer clusters and to find representativ...

Integrating Sensor Web Enablement (SWE) services with Geo-Processing Workflows (GPW) has become a bottleneck for Sensor Web-based applications, especially remote-sensing observations. This paper presents a common GPW framework for Sensor Web data service as part of the NASA Sensor Web project. This abstract framework includes abstract GPW model construction, GPW chains from service combination, and data retrieval components. The concrete framework consists of a data service node, a data processing node, a data presentation node, a Catalogue Service node, and a BPEL engine. An abstract model designer is used to design the top level GPW model, a model instantiation service is used to generate the concrete Business Process Execution Language (BPEL), and the BPEL execution engine is adopted. This framework is used to generate several kinds of data: raw data from live sensors, coverage or feature data, geospatial products, or sensor maps. A prototype, including a model designer, model instantiation service, and GPW engine-BPELPower is presented. A scenario for an EO-1 Sensor Web data service for wildfire hot pixel detection is used to test the feasibility of the proposed framework. The execution time and influences of the EO-1 live Hyperion data wildfire classification service framework are evaluated. The benefits and high performance of the proposed framework are discussed. The experiments of EO-1 live Hyperion data wildfire classification service show that this framework can improve the quality of services for sensor data retrieval and processing.

How to update spatial information in real time or near real time has become a bottleneck in the construction of the Antarctica Spatial Data Infrastructure (AntSDI). An automatic sensor processing workflow (SPW) approach consisting of sensor discovery and retrieval service; snow, water, ice, land and cloud (SWILC) Web processing service (WPS); and an SPW engine under the Sensor Web environment is used in this paper to generate live SWILC maps dynamically. A prototype consisting of a sensor processing model designer, a model instantiation service, and an SPW engine is presented. A scenario of an Earth Observing-1 (EO-1) Sensor Web data service for SWILC classification and feature extraction in Antarctica is used to test the feasibility of the proposed framework. The integration of SPW with Google Earth and updating of the spatial information for AntSDI using the Transactional Web Feature Service (WFS-T) are evaluated. The results show that the proposed approach is feasible for the update of spatial data in ...

A geospatial catalogue service provides a network-based meta-information repository and interface for advertising and discovering shared geospatial data and services. Descriptive information (i.e., metadata) for geospatial data and services is structured and organized in catalogue services. The approaches currently available for searching and using that information are often inadequate. Semantic Web technologies show promise for better discovery methods by exploiting the underlying semantics. Such development needs special attention from the Cyberinfrastructure perspective, so that the traditional focus on discovery of and access to geospatial data can be expanded to support the increased demand for processing of geospatial information and discovery of knowledge. Semantic descriptions for geospatial data, services, and geoprocessing service chains are structured, organized, and registered through extending elements in the ebXML Registry Information Model (ebRIM) of a geospatial catalogue service, which follows the interface specifications of the Open Geospatial Consortium (OGC) Catalogue Services for the Web (CSW). The process models for geoprocessing service chains, as a type of geospatial knowledge, are captured, registered, and discoverable. Semantics-enhanced discovery for geospatial data, services/service chains, and process models is described. Semantic search middleware that can support virtual data product materialization is developed for the geospatial catalogue service. The creation of such a semantics-enhanced geospatial catalogue service is important in meeting the demands for geospatial information discovery and analysis in Cyberinfrastructure.

In a Web service‐based distributed environment, individual services must be chained together dynamically to solve a complex real world problem. The Semantic Web Service has shown promise for automatic chaining of Web services. This paper addresses semi‐automatic geospatial service chaining through Semantic Web Services‐based process planning. Process planning includes three phases: process modeling, process model instantiation and workflow execution. Ontologies and Artificial Intelligence (AI) planning methods are employed in process planning to help a user dynamically create an executable workflow for earth science applications. In particular, the approach was implemented in a common data and service environment enabled by interoperable standards from OGC and W3C. A case study of the chaining process for wildfire prediction illustrates the applicability of this approach.