Mingda Zhang

Adding Geospatial Data Provenance into SDI—A Service-Oriented Approach

Geospatial data provenance records the derivation history of a geospatial data product. It is important in evaluating the quality of data products. In a Geospatial Web Service environment where data are often disseminated and processed widely and frequently in an unpredictable way, it is even more important in identifying original data sources, tracing workflows, updating or reproducing scientific results, and evaluating reliability and quality of geospatial data products. Geospatial data provenance has become a fundamental issue in establishing the spatial data infrastructure (SDI). This paper investigates how to support provenance awareness in SDI. It addresses key issues including provenance modeling, capturing, and sharing in a SDI enabled by interoperable geospatial services. A reference architecture for provenance tracking is proposed, which can accommodate geospatial feature provenance at different levels of granularity. Open standards from ISO, World Wide Web Consortium (W3C), and OGC are leveraged to facilitate the interoperability. At the feature type level, this paper proposes extensions of W3C PROV-XML for ISO 19115 lineage and “Parent Level” provenance registration in the geospatial catalog service. At the feature instance level, light-weight lineage information entities for feature provenance are proposed and managed by Web Feature Services. Experiments demonstrate the applicability of the approach for creating provenance awareness in an interoperable geospatial service-oriented environment.

An SDI Approach for Big Data Analytics: The Case on Sensor Web Event Detection and Geoprocessing Workflow

In the big data era, scientific and social data could complement each other for enhanced data analysis and scientific discovery. Such capabilities could be achieved by taking an infrastructure-based approach, compared to existing algorithm-based approaches. This paper investigates how scientific and social data could work together in a spatial data infrastructure (SDI) enabled by interoperable services. It takes a human-as-sensor perspective and treats the social data as a special kind of sensor data, which could be mined and used for event detection in the Sensor Web environment. Sensor Web, social data mining, and geoprocessing workflows are combined together for timely decision support from social and sensor data. The result is an SDI approach for big data analytics. A use case on haze-related data mining and analysis illustrates the applicability of the approach.

A Linked Data Approach for Geospatial Data Provenance

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.

Fuzzy spatial relation ontology driven detection of complex geospatial features in a web service environment

Remote sensing images have been widely used by intelligence analysts to discover geospatial features. The overwhelming volume of remote sensing imagery requires automated methods or systems for feature discovery. Existing research focuses on automatic extraction of isolated or elementary features, such as buildings and roads. It is rather understudied to discover complex geospatial features, which is spatially composed of elementary features. From the e-Science perspective, service computing technologies have shown great promise for widespread automation of data analysis and computation. The discovery of complex features would benefit from service computing technologies by computing spatial relations and their fuzziness among elementary features using geoprocessing services. The discovery process can be automated using an ontology approach. The paper presents how ontologies for complex geospatial features, enriched with fuzzy sets of spatial relations, can automate the workflow generation. Spatial computation functions, fuzzy membership functions, and mathematical fuzzy logical operators, are provided as services, and plugged into workflows on demand to enjoy the benefits of service computing technologies. A prototype system demonstrates on-demand uncertainty-aware detection of complex geospatial features in a geoprocessing service environment.

Task-oriented Sensor Web data processing for environmental monitoring

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.

Granularity of geospatial data provenance

Provenance, the lineage of data products, has been identified as a basic research issue in distributed data and information infrastructures. Provenance could be captured at different levels of granularity. This paper investigates the granularity of provenance for both vector and raster data. In particular, it focuses on the feature and pixel level provenance, and their management in a distributed information environment. The approach is to augment existing geospatial services with provenance awareness. The results show how the provenance with different granularity can be supported in a service-oriented environment enabled by OGC services such as Web Coverage Services, Web Feature Services, Web Processing Services, thus creating a provenance-aware Geo-Cyber infrastructure.

A Sensor Web and Web Service-Based Approach for Active Hydrological Disaster Monitoring

Rapid advancements in Earth-observing sensor systems have led to the generation of large amounts of remote sensing data that can be used for the dynamic monitoring and analysis of hydrological disasters. The management and analysis of these data could take advantage of distributed information infrastructure technologies such as Web service and Sensor Web technologies, which have shown great potential in facilitating the use of observed big data in an interoperable, flexible and on-demand way. However, it remains a challenge to achieve timely response to hydrological disaster events and to automate the geoprocessing of hydrological disaster observations. This article proposes a Sensor Web and Web service-based approach to support active hydrological disaster monitoring. This approach integrates an event-driven mechanism, Web services, and a Sensor Web and coordinates them using workflow technologies to facilitate the Web-based sharing and processing of hydrological hazard information. The design and implementation of hydrological Web services for conducting various hydrological analysis tasks on the Web using dynamically updating sensor observation data are presented. An application example is provided to demonstrate the benefits of the proposed approach over the traditional approach. The results confirm the effectiveness and practicality of the proposed approach in cases of hydrological disaster.

Sensor Web event detection and geoprocessing over Big data

In the Big Data era, scientific and social data can complement each other for enhanced data analysis and scientific discovery. In the geospatial domain, Sensor Web technologies can provide real-time or near real-time geospatial data to support timely decision-making. Scientific workflows have been identified as a key approach to support Big Data analytics for scientists. In the human-as-sensor aspect, the social content, as a special kind of sensor data, could be mined and fused in a Sensor Event Service (SES), allowing social data to be used inside a Spatial Data Infrastructure (SDI). This paper investigates an infrastructural approach on how social and scientific data could work together in an interoperable service environment. Sensor Web and geoprocessing services technologies are leveraged together for timely decision support from social and sensor data. A use case on haze-related data mining and analysis illustrates the applicability of the approach.

GeoJModelBuilder: an open source geoprocessing workflow tool

BackgroundScientific workflows have been commonly used in geospatial data analysis and Cyberinfrastructure. They allow distributed geoprocessing algorithms, models, data, and sensors to be chained together to support geospatial data analysis, and environmental monitoring, and integrated environmental modelling.ResultsThis paper presents an open source geoprocessing workflow tool, GeoJModelBuilder. It leverages open standards, Sensor Web, geoprocessing commands and services, OpenMI-compliant models together.ConclusionThe implementation provides a flexible, reusable, interoperable, and user-friendly way for geoprocessing in an open environment.

Model provenance tracking and inference for integrated environmental modelling

Integrated environmental modeling (IEM) provides a systematic way to couple models for integrated analysis. Coupled models in IEM often exchange data at runtime for time-step based executions. It is a challenge to track which raw observations or intermediate data exchanged at runtime contribute to individual model outputs. Time-step level provenance is needed to audit the trail of model execution or perform diagnosis in case of anomalies. This paper introduces a method to support provenance awareness in IEM. It suggests that individual models should expose necessary interfaces for provenance capturing in IEM environments. The provenance is represented using the W3C PROV model for interoperability. Fine-grained provenance is inferred based on coarse-grained provenance and temporal characteristics of computations of numerical time marching models. The approach is implemented in OpenMI-compliant models. A case study of model provenance tracking and inference on the watershed runoff simulation scenario illustrates the applicability of the approach. Model provenance tracking in integrated environmental modelling.Inference for fine-grained model provenance.Provenance awareness for OpenMI.