Catálogo de publicaciones - libros

This chapter presents a toponym disambiguation approach based on supervised machine learning. The proposed approach uses a simple hierarchical geographic relationship model to describe geographic entities and geographic relationships among them. The disambiguation procedure begins with the identification of toponyms in documents by applying and extending the state-of-the-art named entity recognition technologies and then performs disambiguation as a supervised classification processes over a feature space of geographic relationships. A geographic knowledge base is modeled and constructed to support the whole disambiguation procedure. System performance is evaluated on a document collection consisting of 15,194 local Australian news articles. The experiment results show that the disambiguation accuracy ranges from 73.55 to 85.38 percent depending on the running parameters and the learning strategies used.

NASA's Mobile Agents project leads coordinated planetary exploration simulations at the Mars Desert Research Station. Through ScienceOrganizer, a Web-based tool for organizing and providing contextual information for scientific data sets, remote teams of scientists access and annotate data sets, images, documents and other forms of scientific information, applying predefined semantic links and metadata using a Web browser. We designed and developed an experimental geographic information server that integrates remotely sensed images of scientific activity areas with information regarding activity plans, actors and data that had been characterized semantically using ScienceOrganizer. The server automatically obtains remotely sensed photographs of geographic survey sites at various resolutions and combines these images with scientific survey data to generate “context maps” illustrating the paths of survey actors and the sequence and types of data collected during simulated surface “extra-vehicular activities.” The remotely located scientific team found the context maps were extremely valuable for achieving and conveying activity plan consensus.

The research presented in this chapter introduces a graph-based and computational modeling approach to the analysis of Web-based networks. The aim is to derive a social network and compute its emerging spatial and thematic properties from the semantics embedded in a series of Web pages. We apply several graph-based operators and complement them with thematic, spatial and similarity operators. The principles of the modeling approach are applied to the study of research communities as they appear over the World Wide Web. This allows us to infer the degree of correlation between the different properties of the semantic networks that emerge from research communities on the World Wide Web.

In 2005, Google, Microsoft and Yahoo! released free Web mapping applications that opened up digital mapping to mainstream Internet users. Importantly, these companies also released free APIs for their platforms, allowing users to geo-locate and map their own data. These initiatives have spurred the growth of the Geospatial Web and represent spatially aware online communities and new ways of enabling communities to share information from the bottom up. This chapter explores how the emerging Geospatial Web can meet some of the fundamental needs of Participatory GIS projects to incorporate local knowledge into GIS, as well as promote public access and collaborative mapping.

In recent years the availability of GPS devices and the development in Web technologies have produced a considerable growth in geographical applications available on the Web. In particular, the growing popularity of digital photography and photo sharing services has opened the way to a myriad of possible applications related to geotagged pictures. In this work we present an overview of the creation, sharing and use of geotagged pictures. We propose an approach to providing a new browsing experience of photo collections based on location and heading information metadata.

The aim of this chapter is to show how the need for advanced cooperative annotation and information exchange can be addressed using a paradigm called “Interconnected Geo-Semantic Web Communities”. The use cases and its associated needs are highlighted, and then the base tool for this work, the DBin Semantic Web information manager, is focused on. DBin enables users to create and experience the Semantic Web by exchanging RDF knowledge in peer-to-peer (P2P) “topic” channels. Once sufficient information has been collected locally, rich and fast browsing of semantically structured knowledge becomes possible, even offline, without generating external traffic or computational load. DBin has a number of modules to support cooperative tagging and annotations of geographical objects. Different communities of users, e.g., concerned with different kinds of geographic objects, can each exploit DBin to cooperate in enriched geo-semantic spaces. Advanced users, e.g., cultural heritage agencies, can join multiple groups at the same time and use collective cross-domain knowledge.

The work of natural hazard exposure assessment involves various geographic data sets (referential, hazard, assets) and various disciplines intended for insurance professionals (catastrophe modeling, prevention engineering). The emergence of Geospatial Web technology induces the emergence of new sets of online services. Mission Risques Naturels (MRN) is a French actor in the mutualization and diffusion of information on natural hazards knowledge and prevention for the general interest of insurance professionals. The MRN Web-GIS platform has been built to address these requirements. This chapter starts by presenting the role of MRN in the network of natural hazard assessment. It then presents Geospatial Web tools for natural hazard exposure assessment as well as the system architecture of the MRN Web-GIS platform, including all its services.

Since 1990, “Heavy Metals in Mosses Surveys” have been performed every five years in at least 21 European countries, including Germany, in order to map spatial and temporal trends of the metal bioac-cumulation in terrestrial ecosystems. The monitoring data consist of measurement data on metal loads in ectohydrical mosses as well as site-specific metadata to characterize the sampling locations with regard to, e.g., vegetation, land use and the distance of the sites to emission sources. To optimize the data handling for the moss survey 2005/06, we developed the WebGIS MossMet with the help of open-source components. Thus, the metadata can be integrated with the information system via the Internet by the moss samplers. The WebGIS MossMet comprehensively documents the metadata, the measurement values and statistically derived metal bioaccumulation indices regionalized for ecoregions depicting the landscape coverage of Germany. In the German moss survey 2005/06, the WebGIS MossMet was applied routinely.

An air quality information system should offer the most complete information about air quality in a given region. AirBase contains thousands of monitoring stations across Europe, but the density varies across regions. For both public information and assessments of the exposure on human health and ecosystems, which are important indicators for air quality policy developments, the situation between stations should be known. Traditionally, assessment is based on monitoring data, but information in between stations requires accurate interpolation methods. This chapter reviews, examines and applies interpolation methodologies with special attention to the differences between urban/suburban and rural data. The methodologies are applied to ozone and PM_ 10 indicators. Maps of annual average PM _ 10 are shown to illustrate the recommended methodology in obtaining integrated rural- and urban-scale maps for Europe.

Several large-scale data and information infrastructures (SDI) are being created (INSPIRE, GMES) to support management and decision-making processes, and they are also used for solving a wide range of problems, including crisis management. These solutions require updated, precise, interoperable and integrated spatial data and information equipped with metadata. Up-to-date information, their suitable structuring and easy access to them are necessary for supporting timely and correct decision making in emergency/crisis situations. Most such information is geo-referenced. Cartographic visualization plays an important role for a user's orientation. Visualization is not an isolated element of the information transfer process; it depends on the status of source databases, decision support models, and the behavior of users. Current solutions of crisis management employ static cartographic visualizations based on prepared models of crisis situations. The chapter concentrates on ubiquitous cartography and dynamic geovisualization of real-time models and on the project “Dynamic Geovisualization in Crisis Management” undertaken at Masaryk University in the Czech Republic.