SE‐KGE: A location‐aware Knowledge Graph Embedding model for Geographic Question Answering and Spatial Semantic Lifting

Learning knowledge graph (KG) embeddings is an emerging technique for a variety of downstream tasks such as summarization, link prediction, information retrieval, and question answering. However, most existing KG embedding models neglect space and, therefore, do not perform well when applied to (geo)spatial data and tasks. Most models that do consider space primarily rely on some notions of distance. These models suffer from higher computational complexity during training while still losing information beyond the relative distance between entities. In this work, we propose a location‐aware KG embedding model called SE‐KGE. It directly encodes spatial information such as point coordinates or bounding boxes of geographic entities into the KG embedding space. The resulting model is capable of handling different types of spatial reasoning. We also construct a geographic knowledge graph as well as a set of geographic query–answer pairs called DBGeo to evaluate the performance of SE‐KGE in comparison to multiple baselines. Evaluation results show that SE‐KGE outperforms these baselines on the DBGeo data set for the geographic logic query answering task. This demonstrates the effectiveness of our spatially‐explicit model and the importance of considering the scale of different geographic entities. Finally, we introduce a novel downstream task called spatial semantic lifting which links an arbitrary location in the study area to entities in the KG via some relations. Evaluation on DBGeo shows that our model outperforms the baseline by a substantial margin.     

To The National Map and Beyond

Scientific understanding, technology, and social, economic, and environmental conditions have driven a rapidly changing demand for geographic information, both digital and analog. For more than a decade, the U.S. Geological Survey (USGS) has been developing innovative partnerships with other government agencies and private industry to produce and distribute geographic information efficiently; increase activities in remote sensing to ensure ongoing monitoring of the land surface; and develop new understanding of the causes and consequences of land surface change. These activities are now contributing to a more robust set of geographic information called The National Map (TNM). The National Map is designed to provide an up-to-date, seamless, horizontally and vertically integrated set of basic digital geographic data, a frequent monitoring of changes on the land surface, and an understanding of the condition of the Earth's surface and many of the processes that shape it. The USGS has reorganized its National Mapping Program into three programs to address the continuum of scientific activities—describing (mapping), monitoring, understanding, modeling, and predicting. The Cooperative Topographic Mapping Program focuses primarily on the mapping and revision aspects of TNM. The National Map also includes results from the Land Remote Sensing and Geographic Analysis and Monitoring Programs that provide continual updates, new insights, and analytical tools. The National Map is valuable as a framework for current research, management, and operational activities. It also provides a critical framework for the development of distributed, spatially enabled decision support systems.     

Seamless integration of spatial statistics and GIS: The S-PLUS for ArcView and the S+Grassland Links

The extension of the functional capacity of geographic information systems (GIS) with tools for statistical analysis in general and exploratory spatial data analysis (ESDA) in particular has been an increasingly active area of research in recent years. In this paper, two operational implementations that combine the functionality of spatial data analysis software with a GIS are considered more closely. They consist of linkages between the S-PLUS software for data analysis and two different GIS implementations, the ArcView desktop system, which is mostly vector-oriented, and the primarily raster-based Grassland open GIS environment. We emphasize conceptual and technical issues related to the software implementation of these approaches and suggest future directions for linking spatial statistics and GIS. Received: 14 January 1999 / Accepted: 11 May 1999     

A Network Perspective on Spatial Data Infrastructures: Application to the Sub-national SDI of Flanders (Belgium)

In order to provide a basis for quantitative and qualitative assessment of SDI-performance, a clear definition and a theoretical framework for SDI are needed. From the various definitions and frameworks of SDI available in the literature, the productional and the geographic information process perspective were selected, combined and extended. From the productional perspective, SDI-development is a dynamic process in which suppliers and users of spatial data interact to add value to the data by using them in applications and processes. The geographic information process perspective incorporates the "information acquisition – delivery – usage" chain. The extension proposed in this article leads to a network perspective on SDI. The nature of this perspective is described for the Flemish SDI. Its applicability to characterise and underpin the assessment of SDI is tested using a Social Network Analysis (SNA) focusing on the network structure parameters "density", "distance" and "centrality". The SNA confirms the applicability, usability and extensibility of the network perspective to characterize the SDI, to describe the data flows between stakeholders and to analyse the behaviour of the different (types) of stakeholders within the network. We conclude that SNA should likely be complemented by an impact analysis of different SDI setups on business processes which will provide a good basis for a holistic SDI-performance assessment.     

Human conceptions of spaces: Implications for GIS

The way people conceptualize space is an important consideration for the design of GIS, because a better match with people's thinking is expected to lead to easier-to-use information systems. Everyday space, the basis to GIS, has been characterized in the literature as being either small-scale (from table-top to room-size spaces) or large-scale (inside-of-building spaces to city-size spaces). While this dichotomy of space is grounded in the view from psychology that people's perception of space, spatial cognition, and spatial behaviour are experience-based, it is in contrast to current GIS, which enable us to interact with large-scale spaces as though they were small-scale or manipulable. We analyse different approaches to characterizing spaces and propose a unified view in which space is based on the physical properties of manipulability, locomotion, and size of space. Within the structure of our framework, we distinguish six types of spaces: manipulable object space (smaller than the human body), non-manipulable object space (greater than the human body, but less than the size of a building), environmental space (from inside-of-building spaces to city-size spaces), geographic space (state, country, and continent-size spaces), panoramic space (spaces perceived via scanning the landscape), and map space. Such a categorization is an important part of Naive Geography, a set of theories on how people intuitively or spontaneously conceptualize geographic space and time, because it has implications for various theoretical and methodological questions concerning the design and use of spatial information tools. Of particular concern is the design of effective spatial information tools that lead to better communication.     

Sonifying data uncertainty with sound dimensions

ABSTRACT

The communication of data uncertainty is a crucial problem in data science, information visualization, and geographic information science (GIScience). Effective ways to communicate the uncertainty of data enables data consumers to interpret the data as intended by the producer, reducing the possibilities of misinterpretation. In this article, we report on an empirical investigation of how sound can be used to convey information about data uncertainty in an intuitive way. To answer the research question How intuitive are sound dimensions to communicate uncertainty? we carry out a cognitive experiment, where participants were asked to interpret the certainty/uncertainty level in two sounds A and B (N = 33). We produce sound stimuli by varying sound dimensions, including loudness, duration, location, pitch, register, attack, decay, rate of change, noise, timbre, clarity, order, and harmony. In the stimuli, both synthetic and natural sounds are used to allow comparison. The experiment results identify three sound dimensions (loudness, order, and clarity) as significantly more intuitive to communicate uncertainty, providing guidelines for sonification and information visualization practitioners.     

VGDI – Advancing the Concept: Volunteered Geo‐Dynamic Information and its Benefits for Population Dynamics Modeling

The concept of Volunteered Geographic Information (VGI) has progressed from being an exotic prospect to making a profound impact on GIScience and geography in general, as initially anticipated. However, while massive and manifold data is continuously produced voluntarily and applications are built for information and knowledge extraction, the initially introduced concept of VGI lacks certain methodological perspectives in this regard which have not been fully elaborated. In this article we highlight and discuss an important gap in this concept, i.e. the lack of formal acknowledgment of temporal aspects. By coining the proposed advanced framework ‘Volunteered Geo‐Dynamic Information’ (VGDI), we attempt to lay the ground for full conceptual and applied spatio‐temporal integration. To illustrate that integrative approach of VGDI and its benefits, we describe the potential impact on the field of dynamic population distribution modeling. While traditional approaches in that domain rely on survey‐based data and statistics as well as static geographic information, the use of VGDI enables a dynamic setup. Foursquare venue and user check‐in data are presented for a test site in Lisbon, Portugal. Two core modules of spatio‐temporal population assessment are thereby addressed, namely time use profiling and target zone characterization, motivated by the potential integration in existing population dynamics frameworks such as the DynaPop model.     

A SEMINAR ON GEOGRAPHIC INFORMATION SYSTEMS

A paper describing the proceedings of a seminar on geographic information systems sponsored jointly by Tartu University and the USSR Academy of Sciences reveals major thrusts of Soviet research in this emerging field. Topics presented in the seminar include basic types of geographic information systems, the roles played by microcomputers and data base management systems in GIS, use of data from topographic maps in GIS, terrain modeling, remote sensing and GIS, GIS development based on Soviet-produced hardware and software, and the application of information systems in the solution of specific resource management problems. Translated from: Izvestiya AN SSSR, seriya geograficheskaya, 1986, No. 1, pp. 136–138.     

The GeoCitizen-approach: community-based spatial planning – an Ecuadorian case study

Over the last years, geospatial web platforms, social media, and volunteered geographic information (VGI) have opened a window of opportunity for traditional Public Participatory GIS (PPGIS) to usher in a new era. Taking advantage of these technological achievements, this paper presents a new approach for a citizen-orientated framework of spatial planning that aims at integrating participatory community work into existing decision-making structures. One major cornerstone of the presented approach is the application of a social geoweb platform (the GeoCitizen platform) that combines geo-web technologies and social media in one single tool allowing citizens to collaboratively report observations, discuss ideas, solve, and monitor problems in their living environment at a local level. This paper gives an account of an ongoing participatory land-zoning process in the Capital District of Quito, Ecuador, where the GeoCitizen platform is applied in a long-term study.     

基于地理实体的基础测绘生产组织模式探索

首先分析了目前我国基础地理信息资源建设存在的主要问题,提出了通过构建地理实体数据库实现基础地理信息资源的共享和深入应用的构想。其次,深入分析了目前国内外地理实体数据库的研究及建设现状。在以上基础上,最后以优先满足国家事权为原则,提出了基于地理实体数据采集的我国基础测绘国家、省、市县任务分工和生产组织模式构想。     

A GEOGRAPHIC INFORMATION SYSTEM FOR PHYSICAL-GEOGRAPHIC REGIONALIZATION

The design and functioning of a geographic information system established for the purpose of objectively delineating the boundaries of major physical geographic regions in the USSR is described. The basic components include an information input block for data collection and preliminary image processing; a recognition block for feature classification and analysis; a data base management system providing for repeated revision, addition, and use of spectral information; and a block for displaying results of processing in various forms. Applications of the system are demonstrated in the mapping of physical regions in a steppe and semi-desert area of the southern USSR. Translated from: Izvestiya Akademii Nauk SSSR, seriya geograficheskaya, 1988, No. 2, pp. 89-94.     

A CONCEPT FOR THE MAPPING OF MULTI-STATE SOCIAL AND ECONOMIC SYSTEMS

The paper investigates the use of maps in obtaining, based on the cartometric and geographic analysis of form, information about the content of multi-state social and economic systems. Examples of specially compiled maps of multi-state systems are described and various considerations in map design and compilation are discussed: scale selection, identification of typologies and design of map legends, principles for the location of geographic features on the map, and stages in cartographic research and mapping of multi-state systems. Translated by H. L. Haslett, Leamington Spa, UK from: Izvestiya Akademii Nauk SSSR, seriya geograficheskaya, 1990, No. 3, pp. 98–103.     

A stream ordering approach based on network analysis operations

Stream ordering is a technique for characterizing the constituent parts of a drainage network. Network analysis remains one of the most popular and persistent research and application areas in geographic information science. In this study, a new stream ordering approach based on geographic information systems tools and network analysis operations is proposed. The new method combines the concepts of modern network analysis operations, which mainly deal with derivations of the best route solution, and the previous stream ordering techniques. In this context, the method readily identifies the channel heads hierarchically in order to derive main stream channel and its tributaries, and assigns a unique order for each stream on the network.     

Characterizing European urban settlements from population data: a cartographic approach

ABSTRACT

The cartographic identification and characterization of urban settlements is problematic, particularly in varied areas or in large geographical extensions. This is due to the divergence between morphological area structures and data attribution, which is generally available at the level of administrative units. Most existing experiences focus on small regions or use indirect data, from which only indirect information can be derived. This paper proposes an identification of urban settlements in the European Union space, which combines urban population and shape through geographic information system (GIS) techniques. For that purpose, 1 km² cells with associated population data are used. A procedure is developed establishing three different types of urban settlements, according to population and population density values: high-density urban clusters, small and medium-sized towns, and very small towns. A validation of this procedure is performed using direct survey from local experts in 10 selected study areas. The final results show that 78,307 urban settlements can be identified: 88.17% of them are classified as “very small towns,” 10.75% as “small and medium-sized towns,” and 1.08% as high-density urban clusters. This exercise generates new information for the European Union and surrounding countries, and yields the basis for further research. All GIS operations are performed using vector layers, which is not usual in large-area regional studies.     

A Review and Evaluation of Uncertainty Classification and the Error‐Band Geometry Model

Advances in computer technologies have improved the quality of maps, making map comparison and analysis easier, but uncertainty and error still exist in GIS when overlaying geographic data with multiple or unknown confidence levels. The goals of this research are to review current geospatial uncertainty literature, present the Error‐Band Geometry Model (EBGM) for classifying the size and shape of spatial confidence intervals for vector GIS data, and to analyze the interpretability of the model by looking at how people use metadata to classify the uncertainty of geographic objects. The results from this research are positive and provide important insight into how people interpret maps and geographic data. They suggest that uncertainty is more easily interpreted for well defined point data and GPS data. When data is poorly defined, people are unable to determine an approach to model uncertainty and generate error‐bands. There is potential for using the EBGM to aid in the development of a GIS tool that can help individuals parameterize and model spatial confidence intervals, but more research is needed to refine the process by which people use the decision tree. A series of guiding questions or an “uncertainty wizard” tool that helps one select an uncertainty modeling approach might improve the way people apply this model to real‐world applications.     

#Earthquake: Twitter as a Distributed Sensor System

Social media feeds are rapidly emerging as a novel avenue for the contribution and dissemination of information that is often geographic. Their content often includes references to events occurring at, or affecting specific locations. Within this article we analyze the spatial and temporal characteristics of the twitter feed activity responding to a 5.8 magnitude earthquake which occurred on the East Coast of the United States (US) on August 23, 2011. We argue that these feeds represent a hybrid form of a sensor system that allows for the identification and localization of the impact area of the event. By contrasting this with comparable content collected through the dedicated crowdsourcing ‘Did You Feel It?’ (DYFI) website of the U.S. Geological Survey we assess the potential of the use of harvested social media content for event monitoring. The experiments support the notion that people act as sensors to give us comparable results in a timely manner, and can complement other sources of data to enhance our situational awareness and improve our understanding and response to such events.     

A framework for user-generated geographic content acquisition in an age of crowdsourcing

ABSTRACT

Obtaining useful geographic information from the flood of user-generated geographic content (UGGC) data is of significant interest, but comes with challenges in an age of crowdsourcing. To address this issue, we adopt Maslow’s model of human needs to frame UGGC. Synthesizing across literature about volunteered geographic information and participatory GIS, we present a conceptual framework for characterizing collection of UGGC. The framework is composed of multiple dimensions and levels that include perspectives about motivations, participatory methods, and participants. We also articulate four levels of participants (stakeholders, core-engaged participants, semi-core-engaged participants, and engaged citizens) together with four work principles (communication, cooperation, coordination, and collaboration). Finally, a case study describes an example we use to evaluate the conceptual framework for its suitability in design of a UGGC system. We conclude by reflecting on how and why this framework offers a valuable perspective for deriving useful geographic information and offer future research directions.     

Improvement of a location-aware recommender system using volunteered geographic information

Abstract

Recommender systems (RS), as supportive tools, filter information from a massive amount of data based on the determined preferences. Most of the RS require information about the context of users such as their locations. In such cases, location-aware recommender systems (LARS) can be employed to suggest more personalized items to the users. The most current research projects on LARS focus on the development of algorithms, evaluation methods and applications. However, the role of up-to-date spatial databases in LARS is not a well-researched area. The up-to-date spatial information would potentially improve the accuracy of items which are recommended by LARS. Volunteered geographic information (VGI) could be a low-cost source of up-to-date spatial information for LARS. This article proposes an approach to enrich spatial databases of LARS by VGI. Since not all records of VGI are fitted for use in LARS, a mechanism is developed to identify useful information. Some VGI data sets refer to existing spatial data in the database while other VGI data sets are shared for the first time. Therefore, the proposed method assessed the quality of VGI with reference source (for VGI which is existed in the database) and VGI without reference source (for VGI which is shared for the first time). To demonstrate the feasibility of the proposed approach, a mobile application has been developed to recommend suitable restaurants to the users based on their geospatial locations. The evaluation of the method indicates that VGI can potentially enhance the functionality of the LARS in predicting the users’ interests.     

Development of GIS-based environmental information system: an Indian scenario

Abstract

Ideally, scientists should be able to format, explore, analyse, and visualise data in a simple, powerful and fast application that would seamlessly integrate georeferenced data from a variety of data sources into an intuitive visualisation. The focus of an Environmental Information System is providing environmental information to decision makers, policy planners, scientists and engineers, research workers, etc. which ensures integration of data collection, collation, storage, retrieval and dissemination to all concerned. All such queries should be responded to supplying substantive information in the form of reports. The paper presents an innovative way to utilise the geographic information associated with the environmental data. The stand-alone application is the integration of using ArcObjects Environmental System Research Institute ArcGIS Engine 9.1 and VB.Net. The geographic information system (GIS)-based application, a framework of digital earth in terms of environmental information system provides a user-friendly query interface, which gives information about various environmental parameters in tabular as well as on map display. It also provides the visual interpretation to make further analysis and future decisions at multiple scales, locations and extents. The facility for modifying the map attributes and corresponding databases is integrated to update the information system. Output spatial data are produced in the form of reports using selected fields with display on map.     

VGIS-COLLIDE: an effective collision detection algorithm for multiple objects in virtual geographic information system

Abstract

Collision detection is an important component in simulation applications which are based on virtual geographic information system (VGIS). In this paper, an effective collision detection algorithm for multiple objects in VGIS, VGIS-COLLIDE, is presented. The algorithm firstly integrates existing quadtree, which is the global hierarchical structure of VGIS, with axis-aligned bounding box of object to perform the broad-phase of collision detection. After that, exact collision detection between two objects which have passed the broad-phase of collision detection is performed. The algorithm makes no assumption about input primitives or object's motion and is directly applicable to all triangulated models. It can be applicable to both rigid and deformable objects without preprocessing. The performance of the algorithm has been demonstrated in several environments consisting of a high number of objects with hundreds of thousands of triangles.